Merge pull request #1631 from open-webui/dev

0.1.120
refac: include archived flag in exports
2024-04-20 17:41:00 -07:00 · 2024-04-20 19:32:32 -05:00 · 2024-04-20 19:24:58 -05:00 · 2024-04-20 19:20:46 -05:00 · 2024-04-20 19:15:11 -05:00 · 2024-04-20 19:15:04 -05:00
202 changed files with 22788 additions and 6387 deletions
@@ -9,4 +9,8 @@ OPENAI_API_KEY=''

 # DO NOT TRACK
 SCARF_NO_ANALYTICS=true
-DO_NOT_TRACK=true
+DO_NOT_TRACK=true
+
+# Use locally bundled version of the LiteLLM cost map json
+# to avoid repetitive startup connections
+LITELLM_LOCAL_MODEL_COST_MAP="True"
@@ -24,6 +24,9 @@ assignees: ''

 ## Environment

+- **Open WebUI Version:** [e.g., 0.1.120]
+- **Ollama (if applicable):** [e.g., 0.1.30, 0.1.32-rc1]
+
 - **Operating System:** [e.g., Windows 10, macOS Big Sur, Ubuntu 20.04]
 - **Browser (if applicable):** [e.g., Chrome 100.0, Firefox 98.0]

@@ -29,11 +29,11 @@ jobs:
    - name: Extract latest CHANGELOG entry
      id: changelog
      run: |
-        CHANGELOG_CONTENT=$(awk '/^## \[/{n++} n==1' CHANGELOG.md)
-        echo "CHANGELOG_CONTENT<<EOF" 
-        echo "$CHANGELOG_CONTENT"
-        echo "EOF" 
-        echo "::set-output name=content::${CHANGELOG_CONTENT}"
+        CHANGELOG_CONTENT=$(awk 'BEGIN {print_section=0;} /^## \[/ {if (print_section == 0) {print_section=1;} else {exit;}} print_section {print;}' CHANGELOG.md)
+        CHANGELOG_ESCAPED=$(echo "$CHANGELOG_CONTENT" | sed ':a;N;$!ba;s/\n/%0A/g')
+        echo "Extracted latest release notes from CHANGELOG.md:" 
+        echo -e "$CHANGELOG_CONTENT" 
+        echo "::set-output name=content::$CHANGELOG_ESCAPED"

    - name: Create GitHub release
      uses: actions/github-script@v5
@@ -57,3 +57,14 @@ jobs:
        path: .
      env:
        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Trigger Docker build workflow
+      uses: actions/github-script@v7
+      with:
+        script: |
+          github.rest.actions.createWorkflowDispatch({
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            workflow_id: 'docker-build.yaml',
+            ref: 'v${{ steps.get_version.outputs.version }}',
+          })
@@ -1,8 +1,7 @@
-#
-name: Create and publish a Docker image
+name: Create and publish Docker images with specific build args

-# Configures this workflow to run every time a change is pushed to the branch called `release`.
 on:
+  workflow_dispatch:
  push:
    branches:
      - main
@@ -10,30 +9,39 @@ on:
    tags:
      - v*

-# Defines two custom environment variables for the workflow. These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
 env:
  REGISTRY: ghcr.io
  IMAGE_NAME: ${{ github.repository }}
+  FULL_IMAGE_NAME: ghcr.io/${{ github.repository }}

-# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
 jobs:
-  build-and-push-image:
+  build-main-image:
    runs-on: ubuntu-latest
-    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
    permissions:
      contents: read
      packages: write
-      #
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
    steps:
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
      - name: Checkout repository
        uses: actions/checkout@v4
-      # Required for multi architecture build
+
      - name: Set up QEMU
        uses: docker/setup-qemu-action@v3
-      # Required for multi architecture build
+
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3
-      # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
+
      - name: Log in to the Container registry
        uses: docker/login-action@v3
        with:
@@ -41,12 +49,11 @@ jobs:
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

-      - name: Extract metadata for Docker images
+      - name: Extract metadata for Docker images (default latest tag)
        id: meta
        uses: docker/metadata-action@v5
        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-          # This configuration dynamically generates tags based on the branch, tag, commit, and custom suffix for lite version.
+          images: ${{ env.FULL_IMAGE_NAME }}
          tags: |
            type=ref,event=branch
            type=ref,event=tag
@@ -56,11 +63,322 @@ jobs:
          flavor: |
            latest=${{ github.ref == 'refs/heads/main' }}

-      - name: Build and push Docker image
+      - name: Build Docker image (latest)
        uses: docker/build-push-action@v5
+        id: build
        with:
          context: .
          push: true
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ steps.meta.outputs.tags }}
+          platforms: ${{ matrix.platform }}
          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-main-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  build-cuda-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
+    steps:
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (default latest tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=cuda
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+            suffix=-cuda,onlatest=true
+
+      - name: Build Docker image (cuda)
+        uses: docker/build-push-action@v5
+        id: build
+        with:
+          context: .
+          push: true
+          platforms: ${{ matrix.platform }}
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          build-args: USE_CUDA=true
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-cuda-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  build-ollama-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
+    steps:
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (ollama tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=ollama
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+            suffix=-ollama,onlatest=true
+
+      - name: Build Docker image (ollama)
+        uses: docker/build-push-action@v5
+        id: build
+        with:
+          context: .
+          push: true
+          platforms: ${{ matrix.platform }}
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          build-args: USE_OLLAMA=true
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-ollama-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  merge-main-images:
+    runs-on: ubuntu-latest
+    needs: [ build-main-image ]
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          pattern: digests-main-*
+          path: /tmp/digests
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (default latest tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
+
+
+  merge-cuda-images:
+    runs-on: ubuntu-latest
+    needs: [ build-cuda-image ]
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          pattern: digests-cuda-*
+          path: /tmp/digests
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (default latest tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=cuda
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+            suffix=-cuda,onlatest=true
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
+
+  merge-ollama-images:
+    runs-on: ubuntu-latest
+    needs: [ build-ollama-image ]
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          pattern: digests-ollama-*
+          path: /tmp/digests
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (default ollama tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=ollama
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+            suffix=-ollama,onlatest=true
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
@@ -1,27 +1,39 @@
 name: Python CI
+
 on:
  push:
-    branches: ['main']
+    branches:
+      - main
+      - dev
  pull_request:
+    branches:
+      - main
+      - dev
+
 jobs:
  build:
    name: 'Format Backend'
-    env:
-      PUBLIC_API_BASE_URL: ''
    runs-on: ubuntu-latest
+
    strategy:
      matrix:
-        node-version:
-          - latest
+        python-version: [3.11]
+
    steps:
      - uses: actions/checkout@v4
-      - name: Use Python
-        uses: actions/setup-python@v4
-      - name: Use Bun
-        uses: oven-sh/setup-bun@v1
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
-          pip install yapf
+          pip install black
+
      - name: Format backend
-        run: bun run format:backend
+        run: npm run format:backend
+
+      - name: Check for changes after format
+        run: git diff --exit-code
@@ -1,22 +1,36 @@
-name: Bun CI
+name: Frontend Build
+
 on:
  push:
-    branches: ['main']
+    branches:
+      - main
+      - dev
  pull_request:
+    branches:
+      - main
+      - dev
+
 jobs:
  build:
    name: 'Format & Build Frontend'
-    env:
-      PUBLIC_API_BASE_URL: ''
    runs-on: ubuntu-latest
    steps:
-      - uses: actions/checkout@v4
-      - name: Use Bun
-        uses: oven-sh/setup-bun@v1
-      - run: bun --version
-      - name: Install frontend dependencies
-        run: bun install
-      - name: Format frontend
-        run: bun run format
-      - name: Build frontend
-        run: bun run build
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: '20' # Or specify any other version you want to use
+
+      - name: Install Dependencies
+        run: npm install
+
+      - name: Format Frontend
+        run: npm run format
+
+      - name: Check for Changes After Format
+        run: git diff --exit-code
+
+      - name: Build Frontend
+        run: npm run build
@@ -166,7 +166,7 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+.idea/

 # Logs
 logs
@@ -5,6 +5,177 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

+## [0.1.120] - 2024-04-20
+
+### Added
+
+- **📦 Archive Chat Feature**: Easily archive chats with a new sidebar button, and access archived chats via the profile button > archived chats.
+- **🔊 Configurable Text-to-Speech Endpoint**: Customize your Text-to-Speech experience with configurable OpenAI endpoints.
+- **🛠️ Improved Error Handling**: Enhanced error message handling for connection failures.
+- **⌨️ Enhanced Shortcut**: When editing messages, use ctrl/cmd+enter to save and submit, and esc to close.
+- **🌐 Language Support**: Added support for Georgian and enhanced translations for Portuguese and Vietnamese.
+
+### Fixed
+
+- **🔧 Model Selector**: Resolved issue where default model selection was not saving.
+- **🔗 Share Link Copy Button**: Fixed bug where the copy button wasn't copying links in Safari.
+- **🎨 Light Theme Styling**: Addressed styling issue with the light theme.
+
+## [0.1.119] - 2024-04-16
+
+### Added
+
+- **🌟 Enhanced RAG Embedding Support**: Ollama, and OpenAI models can now be used for RAG embedding model.
+- **🔄 Seamless Integration**: Copy 'ollama run <model name>' directly from Ollama page to easily select and pull models.
+- **🏷️ Tagging Feature**: Add tags to chats directly via the sidebar chat menu.
+- **📱 Mobile Accessibility**: Swipe left and right on mobile to effortlessly open and close the sidebar.
+- **🔍 Improved Navigation**: Admin panel now supports pagination for user list.
+- **🌍 Additional Language Support**: Added Polish language support.
+
+### Fixed
+
+- **🌍 Language Enhancements**: Vietnamese and Spanish translations have been improved.
+- **🔧 Helm Fixes**: Resolved issues with Helm trailing slash and manifest.json.
+
+### Changed
+
+- **🐳 Docker Optimization**: Updated docker image build process to utilize 'uv' for significantly faster builds compared to 'pip3'.
+
+## [0.1.118] - 2024-04-10
+
+### Added
+
+- **🦙 Ollama and CUDA Images**: Added support for ':ollama' and ':cuda' tagged images.
+- **👍 Enhanced Response Rating**: Now you can annotate your ratings for better feedback.
+- **👤 User Initials Profile Photo**: User initials are now the default profile photo.
+- **🔍 Update RAG Embedding Model**: Customize RAG embedding model directly in document settings.
+- **🌍 Additional Language Support**: Added Turkish language support.
+
+### Fixed
+
+- **🔒 Share Chat Permission**: Resolved issue with chat sharing permissions.
+- **🛠 Modal Close**: Modals can now be closed using the Esc key.
+
+### Changed
+
+- **🎨 Admin Panel Styling**: Refreshed styling for the admin panel.
+- **🐳 Docker Image Build**: Updated docker image build process for improved efficiency.
+
+## [0.1.117] - 2024-04-03
+
+### Added
+
+- 🗨️ **Local Chat Sharing**: Share chat links seamlessly between users.
+- 🔑 **API Key Generation Support**: Generate secret keys to leverage Open WebUI with OpenAI libraries.
+- 📄 **Chat Download as PDF**: Easily download chats in PDF format.
+- 📝 **Improved Logging**: Enhancements to logging functionality.
+- 📧 **Trusted Email Authentication**: Authenticate using a trusted email header.
+
+### Fixed
+
+- 🌷 **Enhanced Dutch Translation**: Improved translation for Dutch users.
+- ⚪ **White Theme Styling**: Resolved styling issue with the white theme.
+- 📜 **LaTeX Chat Screen Overflow**: Fixed screen overflow issue with LaTeX rendering.
+- 🔒 **Security Patches**: Applied necessary security patches.
+
+## [0.1.116] - 2024-03-31
+
+### Added
+
+- **🔄 Enhanced UI**: Model selector now conveniently located in the navbar, enabling seamless switching between multiple models during conversations.
+- **🔍 Improved Model Selector**: Directly pull a model from the selector/Models now display detailed information for better understanding.
+- **💬 Webhook Support**: Now compatible with Google Chat and Microsoft Teams.
+- **🌐 Localization**: Korean translation (I18n) now available.
+- **🌑 Dark Theme**: OLED dark theme introduced for reduced strain during prolonged usage.
+- **🏷️ Tag Autocomplete**: Dropdown feature added for effortless chat tagging.
+
+### Fixed
+
+- **🔽 Auto-Scrolling**: Addressed OpenAI auto-scrolling issue.
+- **🏷️ Tag Validation**: Implemented tag validation to prevent empty string tags.
+- **🚫 Model Whitelisting**: Resolved LiteLLM model whitelisting issue.
+- **✅ Spelling**: Corrected various spelling issues for improved readability.
+
+## [0.1.115] - 2024-03-24
+
+### Added
+
+- **🔍 Custom Model Selector**: Easily find and select custom models with the new search filter feature.
+- **🛑 Cancel Model Download**: Added the ability to cancel model downloads.
+- **🎨 Image Generation ComfyUI**: Image generation now supports ComfyUI.
+- **🌟 Updated Light Theme**: Updated the light theme for a fresh look.
+- **🌍 Additional Language Support**: Now supporting Bulgarian, Italian, Portuguese, Japanese, and Dutch.
+
+### Fixed
+
+- **🔧 Fixed Broken Experimental GGUF Upload**: Resolved issues with experimental GGUF upload functionality.
+
+### Changed
+
+- **🔄 Vector Storage Reset Button**: Moved the reset vector storage button to document settings.
+
+## [0.1.114] - 2024-03-20
+
+### Added
+
+- **🔗 Webhook Integration**: Now you can subscribe to new user sign-up events via webhook. Simply navigate to the admin panel > admin settings > webhook URL.
+- **🛡️ Enhanced Model Filtering**: Alongside Ollama, OpenAI proxy model whitelisting, we've added model filtering functionality for LiteLLM proxy.
+- **🌍 Expanded Language Support**: Spanish, Catalan, and Vietnamese languages are now available, with improvements made to others.
+
+### Fixed
+
+- **🔧 Input Field Spelling**: Resolved issue with spelling mistakes in input fields.
+- **🖊️ Light Mode Styling**: Fixed styling issue with light mode in document adding.
+
+### Changed
+
+- **🔄 Language Sorting**: Languages are now sorted alphabetically by their code for improved organization.
+
+## [0.1.113] - 2024-03-18
+
+### Added
+
+- 🌍 **Localization**: You can now change the UI language in Settings > General. We support Ukrainian, German, Farsi (Persian), Traditional and Simplified Chinese and French translations. You can help us to translate the UI into your language! More info in our [CONTRIBUTION.md](https://github.com/open-webui/open-webui/blob/main/docs/CONTRIBUTING.md#-translations-and-internationalization).
+- 🎨 **System-wide Theme**: Introducing a new system-wide theme for enhanced visual experience.
+
+### Fixed
+
+- 🌑 **Dark Background on Select Fields**: Improved readability by adding a dark background to select fields, addressing issues on certain browsers/devices.
+- **Multiple OPENAI_API_BASE_URLS Issue**: Resolved issue where multiple base URLs caused conflicts when one wasn't functioning.
+- **RAG Encoding Issue**: Fixed encoding problem in RAG.
+- **npm Audit Fix**: Addressed npm audit findings.
+- **Reduced Scroll Threshold**: Improved auto-scroll experience by reducing the scroll threshold from 50px to 5px.
+
+### Changed
+
+- 🔄 **Sidebar UI Update**: Updated sidebar UI to feature a chat menu dropdown, replacing two icons for improved navigation.
+
+## [0.1.112] - 2024-03-15
+
+### Fixed
+
+- 🗨️ Resolved chat malfunction after image generation.
+- 🎨 Fixed various RAG issues.
+- 🧪 Rectified experimental broken GGUF upload logic.
+
+## [0.1.111] - 2024-03-10
+
+### Added
+
+- 🛡️ **Model Whitelisting**: Admins now have the ability to whitelist models for users with the 'user' role.
+- 🔄 **Update All Models**: Added a convenient button to update all models at once.
+- 📄 **Toggle PDF OCR**: Users can now toggle PDF OCR option for improved parsing performance.
+- 🎨 **DALL-E Integration**: Introduced DALL-E integration for image generation alongside automatic1111.
+- 🛠️ **RAG API Refactoring**: Refactored RAG logic and exposed its API, with additional documentation to follow.
+
+### Fixed
+
+- 🔒 **Max Token Settings**: Added max token settings for anthropic/claude-3-sonnet-20240229 (Issue #1094).
+- 🔧 **Misalignment Issue**: Corrected misalignment of Edit and Delete Icons when Chat Title is Empty (Issue #1104).
+- 🔄 **Context Loss Fix**: Resolved RAG losing context on model response regeneration with Groq models via API key (Issue #1105).
+- 📁 **File Handling Bug**: Addressed File Not Found Notification when Dropping a Conversation Element (Issue #1098).
+- 🖱️ **Dragged File Styling**: Fixed dragged file layover styling issue.
+
 ## [0.1.110] - 2024-03-06

 ### Added
@@ -1,77 +1,117 @@
 # syntax=docker/dockerfile:1
+# Initialize device type args
+# use build args in the docker build commmand with --build-arg="BUILDARG=true"
+ARG USE_CUDA=false
+ARG USE_OLLAMA=false
+# Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
+ARG USE_CUDA_VER=cu121
+# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
+# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard 
+# for better performance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
+# IMPORTANT: If you change the default model (all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
+ARG USE_EMBEDDING_MODEL=all-MiniLM-L6-v2

-FROM node:alpine as build
+######## WebUI frontend ########
+FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build

 WORKDIR /app

-# wget embedding model weight from alpine (does not exist from slim-buster)
-RUN wget "https://chroma-onnx-models.s3.amazonaws.com/all-MiniLM-L6-v2/onnx.tar.gz" -O - | \
-    tar -xzf - -C /app
-
 COPY package.json package-lock.json ./
 RUN npm ci

 COPY . .
 RUN npm run build

-
+######## WebUI backend ########
 FROM python:3.11-slim-bookworm as base

-ENV ENV=prod
-ENV PORT ""
+# Use args
+ARG USE_CUDA
+ARG USE_OLLAMA
+ARG USE_CUDA_VER
+ARG USE_EMBEDDING_MODEL

-ENV OLLAMA_BASE_URL "/ollama"
+## Basis ##
+ENV ENV=prod \
+    PORT=8080 \
+    # pass build args to the build
+    USE_OLLAMA_DOCKER=${USE_OLLAMA} \
+    USE_CUDA_DOCKER=${USE_CUDA} \
+    USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
+    USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL}

-ENV OPENAI_API_BASE_URL ""
-ENV OPENAI_API_KEY ""
+## Basis URL Config ##
+ENV OLLAMA_BASE_URL="/ollama" \
+    OPENAI_API_BASE_URL=""

-ENV WEBUI_SECRET_KEY ""
+## API Key and Security Config ##
+ENV OPENAI_API_KEY="" \
+    WEBUI_SECRET_KEY="" \
+    SCARF_NO_ANALYTICS=true \
+    DO_NOT_TRACK=true

-ENV SCARF_NO_ANALYTICS true
-ENV DO_NOT_TRACK true
+# Use locally bundled version of the LiteLLM cost map json
+# to avoid repetitive startup connections
+ENV LITELLM_LOCAL_MODEL_COST_MAP="True"

-######## Preloaded models ########
-# whisper TTS Settings
-ENV WHISPER_MODEL="base"
-ENV WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"

-# RAG Embedding Model Settings
-# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
-# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard 
-# for better persormance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
-# IMPORTANT: If you change the default model (all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
-ENV RAG_EMBEDDING_MODEL="all-MiniLM-L6-v2"
-# device type for whisper tts and ebbeding models - "cpu" (default), "cuda" (nvidia gpu and CUDA required) or "mps" (apple silicon) - choosing this right can lead to better performance
-ENV RAG_EMBEDDING_MODEL_DEVICE_TYPE="cpu"
-ENV RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models"
-ENV SENTENCE_TRANSFORMERS_HOME $RAG_EMBEDDING_MODEL_DIR
+#### Other models #########################################################
+## whisper TTS model settings ##
+ENV WHISPER_MODEL="base" \
+    WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"

-######## Preloaded models ########
+## RAG Embedding model settings ##
+ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
+    RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models" \
+    SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
+#### Other models ##########################################################

 WORKDIR /app/backend

+RUN if [ "$USE_OLLAMA" = "true" ]; then \
+        apt-get update && \
+        # Install pandoc and netcat
+        apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
+        # for RAG OCR
+        apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
+        # install helper tools
+        apt-get install -y --no-install-recommends curl && \
+        # install ollama
+        curl -fsSL https://ollama.com/install.sh | sh && \
+        # cleanup
+        rm -rf /var/lib/apt/lists/*; \
+    else \
+        apt-get update && \
+        # Install pandoc and netcat
+        apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
+        # for RAG OCR
+        apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
+        # cleanup
+        rm -rf /var/lib/apt/lists/*; \
+    fi
+
 # install python dependencies
 COPY ./backend/requirements.txt ./requirements.txt

-RUN apt-get update && apt-get install ffmpeg libsm6 libxext6  -y
+RUN pip3 install uv && \
+    if [ "$USE_CUDA" = "true" ]; then \
+        # If you use CUDA the whisper and embedding model will be downloaded on first use
+        pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
+        uv pip install --system -r requirements.txt --no-cache-dir && \
+        python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
+        python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
+    else \
+        pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
+        uv pip install --system -r requirements.txt --no-cache-dir && \
+        python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
+        python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
+    fi

-RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir
-RUN pip3 install -r requirements.txt --no-cache-dir

-# Install pandoc and netcat
-# RUN python -c "import pypandoc; pypandoc.download_pandoc()"
-RUN apt-get update \
-    && apt-get install -y pandoc netcat-openbsd \
-    && rm -rf /var/lib/apt/lists/*
-
-# preload embedding model
-RUN python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device=os.environ['RAG_EMBEDDING_MODEL_DEVICE_TYPE'])"
-# preload tts model
-RUN python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='auto', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"

 # copy embedding weight from build
-RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
-COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx
+# RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
+# COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx

 # copy built frontend files
 COPY --from=build /app/build /app/build
@@ -81,4 +121,6 @@ COPY --from=build /app/package.json /app/package.json
 # copy backend files
 COPY ./backend .

+EXPOSE 8080
+
 CMD [ "bash", "start.sh"]
@@ -8,6 +8,8 @@ remove:

 start:
 	@docker-compose start
+startAndBuild: 
+	docker-compose up -d --build

 stop:
 	@docker-compose stop
@@ -11,7 +11,7 @@
 [![Discord](https://img.shields.io/badge/Discord-Open_WebUI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
 [![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/tjbck)

-User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
+Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).

 ![Open WebUI Demo](./demo.gif)

@@ -53,8 +53,6 @@ User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-co

 - 💬 **Collaborative Chat**: Harness the collective intelligence of multiple models by seamlessly orchestrating group conversations. Use the `@` command to specify the model, enabling dynamic and diverse dialogues within your chat interface. Immerse yourself in the collective intelligence woven into your chat environment.

- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations alongside Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
-
 - 🔄 **Regeneration History Access**: Easily revisit and explore your entire regeneration history.

 - 📜 **Chat History**: Effortlessly access and manage your conversation history.
@@ -65,12 +63,24 @@ User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-co

 - ⚙️ **Fine-Tuned Control with Advanced Parameters**: Gain a deeper level of control by adjusting parameters such as temperature and defining your system prompts to tailor the conversation to your specific preferences and needs.

+- 🎨🤖 **Image Generation Integration**: Seamlessly incorporate image generation capabilities using AUTOMATIC1111 API (local) and DALL-E, enriching your chat experience with dynamic visual content.
+
+- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations alongside Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
+
+- ✨ **Multiple OpenAI-Compatible API Support**: Seamlessly integrate and customize various OpenAI-compatible APIs, enhancing the versatility of your chat interactions.
+
 - 🔗 **External Ollama Server Connection**: Seamlessly link to an external Ollama server hosted on a different address by configuring the environment variable.

+- 🔀 **Multiple Ollama Instance Load Balancing**: Effortlessly distribute chat requests across multiple Ollama instances for enhanced performance and reliability.
+
+- 👥 **Multi-User Management**: Easily oversee and administer users via our intuitive admin panel, streamlining user management processes.
+
 - 🔐 **Role-Based Access Control (RBAC)**: Ensure secure access with restricted permissions; only authorized individuals can access your Ollama, and exclusive model creation/pulling rights are reserved for administrators.

 - 🔒 **Backend Reverse Proxy Support**: Bolster security through direct communication between Open WebUI backend and Ollama. This key feature eliminates the need to expose Ollama over LAN. Requests made to the '/ollama/api' route from the web UI are seamlessly redirected to Ollama from the backend, enhancing overall system security.

+- 🌐🌍 **Multilingual Support**: Experience Open WebUI in your preferred language with our internationalization (i18n) support. Join us in expanding our supported languages! We're actively seeking contributors!
+
 - 🌟 **Continuous Updates**: We are committed to improving Open WebUI with regular updates and new features.

 ## 🔗 Also Check Out Open WebUI Community!
@@ -84,24 +94,27 @@ Don't forget to explore our sibling project, [Open WebUI Community](https://open

 ### Quick Start with Docker 🐳

-> [!IMPORTANT]
+> [!WARNING]
 > When using Docker to install Open WebUI, make sure to include the `-v open-webui:/app/backend/data` in your Docker command. This step is crucial as it ensures your database is properly mounted and prevents any loss of data.

- **If Ollama is on your computer**, use this command:
+> [!TIP]  
+> If you wish to utilize Open WebUI with Ollama included or CUDA acceleration, we recommend utilizing our official images tagged with either `:cuda` or `:ollama`. To enable CUDA, you must install the [Nvidia CUDA container toolkit](https://docs.nvidia.com/dgx/nvidia-container-runtime-upgrade/) on your Linux/WSL system.

-  ```bash
-  docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
-  ```
+**If Ollama is on your computer**, use this command:

- **If Ollama is on a Different Server**, use this command:
+```bash
+docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+```

- To connect to Ollama on another server, change the `OLLAMA_BASE_URL` to the server's URL:
+**If Ollama is on a Different Server**, use this command:

-  ```bash
-  docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https://example.com -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
-  ```
+To connect to Ollama on another server, change the `OLLAMA_BASE_URL` to the server's URL:

- After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄
+```bash
+docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https://example.com -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+```
+
+After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄

 #### Open WebUI: Server Connection Error

@@ -172,4 +185,4 @@ If you have any questions, suggestions, or need assistance, please open an issue

 ---

-Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Open Web UI even more amazing together! 💪
+Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Open WebUI even more amazing together! 💪
@@ -1,4 +1,5 @@
 import os
+import logging
 from fastapi import (
    FastAPI,
    Request,
@@ -9,8 +10,19 @@ from fastapi import (
    File,
    Form,
 )
+
+from fastapi.responses import StreamingResponse, JSONResponse, FileResponse
+
 from fastapi.middleware.cors import CORSMiddleware
 from faster_whisper import WhisperModel
+from pydantic import BaseModel
+
+
+import requests
+import hashlib
+from pathlib import Path
+import json
+

 from constants import ERROR_MESSAGES
 from utils.utils import (
@@ -21,7 +33,20 @@ from utils.utils import (
 )
 from utils.misc import calculate_sha256

-from config import CACHE_DIR, UPLOAD_DIR, WHISPER_MODEL, WHISPER_MODEL_DIR
+from config import (
+    SRC_LOG_LEVELS,
+    CACHE_DIR,
+    UPLOAD_DIR,
+    WHISPER_MODEL,
+    WHISPER_MODEL_DIR,
+    WHISPER_MODEL_AUTO_UPDATE,
+    DEVICE_TYPE,
+    AUDIO_OPENAI_API_BASE_URL,
+    AUDIO_OPENAI_API_KEY,
+)
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["AUDIO"])

 app = FastAPI()
 app.add_middleware(
@@ -33,12 +58,108 @@ app.add_middleware(
 )


-@app.post("/transcribe")
+app.state.OPENAI_API_BASE_URL = AUDIO_OPENAI_API_BASE_URL
+app.state.OPENAI_API_KEY = AUDIO_OPENAI_API_KEY
+
+# setting device type for whisper model
+whisper_device_type = DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu"
+log.info(f"whisper_device_type: {whisper_device_type}")
+
+SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
+SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
+
+
+class OpenAIConfigUpdateForm(BaseModel):
+    url: str
+    key: str
+
+
+@app.get("/config")
+async def get_openai_config(user=Depends(get_admin_user)):
+    return {
+        "OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL,
+        "OPENAI_API_KEY": app.state.OPENAI_API_KEY,
+    }
+
+
+@app.post("/config/update")
+async def update_openai_config(
+    form_data: OpenAIConfigUpdateForm, user=Depends(get_admin_user)
+):
+    if form_data.key == "":
+        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
+
+    app.state.OPENAI_API_BASE_URL = form_data.url
+    app.state.OPENAI_API_KEY = form_data.key
+
+    return {
+        "status": True,
+        "OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL,
+        "OPENAI_API_KEY": app.state.OPENAI_API_KEY,
+    }
+
+
+@app.post("/speech")
+async def speech(request: Request, user=Depends(get_verified_user)):
+    body = await request.body()
+    name = hashlib.sha256(body).hexdigest()
+
+    file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
+    file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
+
+    # Check if the file already exists in the cache
+    if file_path.is_file():
+        return FileResponse(file_path)
+
+    headers = {}
+    headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
+    headers["Content-Type"] = "application/json"
+
+    r = None
+    try:
+        r = requests.post(
+            url=f"{app.state.OPENAI_API_BASE_URL}/audio/speech",
+            data=body,
+            headers=headers,
+            stream=True,
+        )
+
+        r.raise_for_status()
+
+        # Save the streaming content to a file
+        with open(file_path, "wb") as f:
+            for chunk in r.iter_content(chunk_size=8192):
+                f.write(chunk)
+
+        with open(file_body_path, "w") as f:
+            json.dump(json.loads(body.decode("utf-8")), f)
+
+        # Return the saved file
+        return FileResponse(file_path)
+
+    except Exception as e:
+        log.exception(e)
+        error_detail = "Open WebUI: Server Connection Error"
+        if r is not None:
+            try:
+                res = r.json()
+                if "error" in res:
+                    error_detail = f"External: {res['error']['message']}"
+            except:
+                error_detail = f"External: {e}"
+
+        raise HTTPException(
+            status_code=r.status_code if r != None else 500,
+            detail=error_detail,
+        )
+
+
+@app.post("/transcriptions")
 def transcribe(
    file: UploadFile = File(...),
    user=Depends(get_current_user),
 ):
-    print(file.content_type)
+    log.info(f"file.content_type: {file.content_type}")

    if file.content_type not in ["audio/mpeg", "audio/wav"]:
        raise HTTPException(
@@ -54,15 +175,27 @@ def transcribe(
            f.write(contents)
            f.close()

-        model = WhisperModel(
-            WHISPER_MODEL,
-            device="auto",
-            compute_type="int8",
-            download_root=WHISPER_MODEL_DIR,
-        )
+        whisper_kwargs = {
+            "model_size_or_path": WHISPER_MODEL,
+            "device": whisper_device_type,
+            "compute_type": "int8",
+            "download_root": WHISPER_MODEL_DIR,
+            "local_files_only": not WHISPER_MODEL_AUTO_UPDATE,
+        }
+
+        log.debug(f"whisper_kwargs: {whisper_kwargs}")
+
+        try:
+            model = WhisperModel(**whisper_kwargs)
+        except:
+            log.warning(
+                "WhisperModel initialization failed, attempting download with local_files_only=False"
+            )
+            whisper_kwargs["local_files_only"] = False
+            model = WhisperModel(**whisper_kwargs)

        segments, info = model.transcribe(file_path, beam_size=5)
-        print(
+        log.info(
            "Detected language '%s' with probability %f"
            % (info.language, info.language_probability)
        )
@@ -72,7 +205,7 @@ def transcribe(
        return {"text": transcript.strip()}

    except Exception as e:
-        print(e)
+        log.exception(e)

        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
@@ -18,10 +18,33 @@ from utils.utils import (
    get_current_user,
    get_admin_user,
 )
+
+from apps.images.utils.comfyui import ImageGenerationPayload, comfyui_generate_image
 from utils.misc import calculate_sha256
 from typing import Optional
 from pydantic import BaseModel
-from config import AUTOMATIC1111_BASE_URL
+from pathlib import Path
+import uuid
+import base64
+import json
+import logging
+
+from config import (
+    SRC_LOG_LEVELS,
+    CACHE_DIR,
+    ENABLE_IMAGE_GENERATION,
+    AUTOMATIC1111_BASE_URL,
+    COMFYUI_BASE_URL,
+    OPENAI_API_BASE_URL,
+    OPENAI_API_KEY,
+)
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["IMAGES"])
+
+IMAGE_CACHE_DIR = Path(CACHE_DIR).joinpath("./image/generations/")
+IMAGE_CACHE_DIR.mkdir(parents=True, exist_ok=True)

 app = FastAPI()
 app.add_middleware(
@@ -32,46 +55,106 @@ app.add_middleware(
    allow_headers=["*"],
 )

+app.state.ENGINE = ""
+app.state.ENABLED = ENABLE_IMAGE_GENERATION
+
+app.state.OPENAI_API_BASE_URL = OPENAI_API_BASE_URL
+app.state.OPENAI_API_KEY = OPENAI_API_KEY
+
+app.state.MODEL = ""
+
+
 app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
-app.state.ENABLED = app.state.AUTOMATIC1111_BASE_URL != ""
+app.state.COMFYUI_BASE_URL = COMFYUI_BASE_URL
+
+
 app.state.IMAGE_SIZE = "512x512"
 app.state.IMAGE_STEPS = 50


-@app.get("/enabled", response_model=bool)
-async def get_enable_status(request: Request, user=Depends(get_admin_user)):
-    return app.state.ENABLED
+@app.get("/config")
+async def get_config(request: Request, user=Depends(get_admin_user)):
+    return {"engine": app.state.ENGINE, "enabled": app.state.ENABLED}


-@app.get("/enabled/toggle", response_model=bool)
-async def toggle_enabled(request: Request, user=Depends(get_admin_user)):
-    try:
-        r = requests.head(app.state.AUTOMATIC1111_BASE_URL)
-        app.state.ENABLED = not app.state.ENABLED
-        return app.state.ENABLED
-    except Exception as e:
-        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
+class ConfigUpdateForm(BaseModel):
+    engine: str
+    enabled: bool


-class UrlUpdateForm(BaseModel):
-    url: str
+@app.post("/config/update")
+async def update_config(form_data: ConfigUpdateForm, user=Depends(get_admin_user)):
+    app.state.ENGINE = form_data.engine
+    app.state.ENABLED = form_data.enabled
+    return {"engine": app.state.ENGINE, "enabled": app.state.ENABLED}
+
+
+class EngineUrlUpdateForm(BaseModel):
+    AUTOMATIC1111_BASE_URL: Optional[str] = None
+    COMFYUI_BASE_URL: Optional[str] = None


@app.get("/url")
-async def get_openai_url(user=Depends(get_admin_user)):
-    return {"AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL}
+async def get_engine_url(user=Depends(get_admin_user)):
+    return {
+        "AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL,
+        "COMFYUI_BASE_URL": app.state.COMFYUI_BASE_URL,
+    }


@app.post("/url/update")
-async def update_openai_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
+async def update_engine_url(
+    form_data: EngineUrlUpdateForm, user=Depends(get_admin_user)
+):

-    if form_data.url == "":
+    if form_data.AUTOMATIC1111_BASE_URL == None:
        app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
    else:
-        app.state.AUTOMATIC1111_BASE_URL = form_data.url.strip("/")
+        url = form_data.AUTOMATIC1111_BASE_URL.strip("/")
+        try:
+            r = requests.head(url)
+            app.state.AUTOMATIC1111_BASE_URL = url
+        except Exception as e:
+            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
+
+    if form_data.COMFYUI_BASE_URL == None:
+        app.state.COMFYUI_BASE_URL = COMFYUI_BASE_URL
+    else:
+        url = form_data.COMFYUI_BASE_URL.strip("/")
+
+        try:
+            r = requests.head(url)
+            app.state.COMFYUI_BASE_URL = url
+        except Exception as e:
+            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))

    return {
        "AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL,
+        "COMFYUI_BASE_URL": app.state.COMFYUI_BASE_URL,
+        "status": True,
+    }
+
+
+class OpenAIKeyUpdateForm(BaseModel):
+    key: str
+
+
+@app.get("/key")
+async def get_openai_key(user=Depends(get_admin_user)):
+    return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
+
+
+@app.post("/key/update")
+async def update_openai_key(
+    form_data: OpenAIKeyUpdateForm, user=Depends(get_admin_user)
+):
+
+    if form_data.key == "":
+        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
+
+    app.state.OPENAI_API_KEY = form_data.key
+    return {
+        "OPENAI_API_KEY": app.state.OPENAI_API_KEY,
        "status": True,
    }

@@ -132,9 +215,34 @@ async def update_image_size(
@app.get("/models")
 def get_models(user=Depends(get_current_user)):
    try:
-        r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/sd-models")
-        models = r.json()
-        return models
+        if app.state.ENGINE == "openai":
+            return [
+                {"id": "dall-e-2", "name": "DALL·E 2"},
+                {"id": "dall-e-3", "name": "DALL·E 3"},
+            ]
+        elif app.state.ENGINE == "comfyui":
+
+            r = requests.get(url=f"{app.state.COMFYUI_BASE_URL}/object_info")
+            info = r.json()
+
+            return list(
+                map(
+                    lambda model: {"id": model, "name": model},
+                    info["CheckpointLoaderSimple"]["input"]["required"]["ckpt_name"][0],
+                )
+            )
+
+        else:
+            r = requests.get(
+                url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/sd-models"
+            )
+            models = r.json()
+            return list(
+                map(
+                    lambda model: {"id": model["title"], "name": model["model_name"]},
+                    models,
+                )
+            )
    except Exception as e:
        app.state.ENABLED = False
        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
@@ -143,10 +251,14 @@ def get_models(user=Depends(get_current_user)):
@app.get("/models/default")
 async def get_default_model(user=Depends(get_admin_user)):
    try:
-        r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
-        options = r.json()
-
-        return {"model": options["sd_model_checkpoint"]}
+        if app.state.ENGINE == "openai":
+            return {"model": app.state.MODEL if app.state.MODEL else "dall-e-2"}
+        elif app.state.ENGINE == "comfyui":
+            return {"model": app.state.MODEL if app.state.MODEL else ""}
+        else:
+            r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
+            options = r.json()
+            return {"model": options["sd_model_checkpoint"]}
    except Exception as e:
        app.state.ENABLED = False
        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
@@ -157,16 +269,23 @@ class UpdateModelForm(BaseModel):


 def set_model_handler(model: str):
-    r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
-    options = r.json()
+    if app.state.ENGINE == "openai":
+        app.state.MODEL = model
+        return app.state.MODEL
+    if app.state.ENGINE == "comfyui":
+        app.state.MODEL = model
+        return app.state.MODEL
+    else:
+        r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
+        options = r.json()

-    if model != options["sd_model_checkpoint"]:
-        options["sd_model_checkpoint"] = model
-        r = requests.post(
-            url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options", json=options
-        )
+        if model != options["sd_model_checkpoint"]:
+            options["sd_model_checkpoint"] = model
+            r = requests.post(
+                url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options", json=options
+            )

-    return options
+        return options


@app.post("/models/default/update")
@@ -181,45 +300,170 @@ class GenerateImageForm(BaseModel):
    model: Optional[str] = None
    prompt: str
    n: int = 1
-    size: str = "512x512"
+    size: Optional[str] = None
    negative_prompt: Optional[str] = None


+def save_b64_image(b64_str):
+    image_id = str(uuid.uuid4())
+    file_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.png")
+
+    try:
+        # Split the base64 string to get the actual image data
+        img_data = base64.b64decode(b64_str)
+
+        # Write the image data to a file
+        with open(file_path, "wb") as f:
+            f.write(img_data)
+
+        return image_id
+    except Exception as e:
+        log.error(f"Error saving image: {e}")
+        return None
+
+
+def save_url_image(url):
+    image_id = str(uuid.uuid4())
+    file_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.png")
+
+    try:
+        r = requests.get(url)
+        r.raise_for_status()
+
+        with open(file_path, "wb") as image_file:
+            image_file.write(r.content)
+
+        return image_id
+    except Exception as e:
+        log.exception(f"Error saving image: {e}")
+        return None
+
+
@app.post("/generations")
 def generate_image(
    form_data: GenerateImageForm,
    user=Depends(get_current_user),
 ):

-    print(form_data)
+    width, height = tuple(map(int, app.state.IMAGE_SIZE.split("x")))

+    r = None
    try:
-        if form_data.model:
-            set_model_handler(form_data.model)
+        if app.state.ENGINE == "openai":

-        width, height = tuple(map(int, app.state.IMAGE_SIZE.split("x")))
+            headers = {}
+            headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
+            headers["Content-Type"] = "application/json"

-        data = {
-            "prompt": form_data.prompt,
-            "batch_size": form_data.n,
-            "width": width,
-            "height": height,
-        }
+            data = {
+                "model": app.state.MODEL if app.state.MODEL != "" else "dall-e-2",
+                "prompt": form_data.prompt,
+                "n": form_data.n,
+                "size": form_data.size if form_data.size else app.state.IMAGE_SIZE,
+                "response_format": "b64_json",
+            }

-        if app.state.IMAGE_STEPS != None:
-            data["steps"] = app.state.IMAGE_STEPS
+            r = requests.post(
+                url=f"{app.state.OPENAI_API_BASE_URL}/images/generations",
+                json=data,
+                headers=headers,
+            )

-        if form_data.negative_prompt != None:
-            data["negative_prompt"] = form_data.negative_prompt
+            r.raise_for_status()
+            res = r.json()

-        print(data)
+            images = []

-        r = requests.post(
-            url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/txt2img",
-            json=data,
-        )
+            for image in res["data"]:
+                image_id = save_b64_image(image["b64_json"])
+                images.append({"url": f"/cache/image/generations/{image_id}.png"})
+                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.json")
+
+                with open(file_body_path, "w") as f:
+                    json.dump(data, f)
+
+            return images
+
+        elif app.state.ENGINE == "comfyui":
+
+            data = {
+                "prompt": form_data.prompt,
+                "width": width,
+                "height": height,
+                "n": form_data.n,
+            }
+
+            if app.state.IMAGE_STEPS != None:
+                data["steps"] = app.state.IMAGE_STEPS
+
+            if form_data.negative_prompt != None:
+                data["negative_prompt"] = form_data.negative_prompt
+
+            data = ImageGenerationPayload(**data)
+
+            res = comfyui_generate_image(
+                app.state.MODEL,
+                data,
+                user.id,
+                app.state.COMFYUI_BASE_URL,
+            )
+            log.debug(f"res: {res}")
+
+            images = []
+
+            for image in res["data"]:
+                image_id = save_url_image(image["url"])
+                images.append({"url": f"/cache/image/generations/{image_id}.png"})
+                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.json")
+
+                with open(file_body_path, "w") as f:
+                    json.dump(data.model_dump(exclude_none=True), f)
+
+            log.debug(f"images: {images}")
+            return images
+        else:
+            if form_data.model:
+                set_model_handler(form_data.model)
+
+            data = {
+                "prompt": form_data.prompt,
+                "batch_size": form_data.n,
+                "width": width,
+                "height": height,
+            }
+
+            if app.state.IMAGE_STEPS != None:
+                data["steps"] = app.state.IMAGE_STEPS
+
+            if form_data.negative_prompt != None:
+                data["negative_prompt"] = form_data.negative_prompt
+
+            r = requests.post(
+                url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/txt2img",
+                json=data,
+            )
+
+            res = r.json()
+
+            log.debug(f"res: {res}")
+
+            images = []
+
+            for image in res["images"]:
+                image_id = save_b64_image(image)
+                images.append({"url": f"/cache/image/generations/{image_id}.png"})
+                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.json")
+
+                with open(file_body_path, "w") as f:
+                    json.dump({**data, "info": res["info"]}, f)
+
+            return images

-        return r.json()
    except Exception as e:
-        print(e)
-        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
+        error = e
+
+        if r != None:
+            data = r.json()
+            if "error" in data:
+                error = data["error"]["message"]
+        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(error))
@@ -0,0 +1,234 @@
+import websocket  # NOTE: websocket-client (https://github.com/websocket-client/websocket-client)
+import uuid
+import json
+import urllib.request
+import urllib.parse
+import random
+import logging
+
+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["COMFYUI"])
+
+from pydantic import BaseModel
+
+from typing import Optional
+
+COMFYUI_DEFAULT_PROMPT = """
+{
+  "3": {
+    "inputs": {
+      "seed": 0,
+      "steps": 20,
+      "cfg": 8,
+      "sampler_name": "euler",
+      "scheduler": "normal",
+      "denoise": 1,
+      "model": [
+        "4",
+        0
+      ],
+      "positive": [
+        "6",
+        0
+      ],
+      "negative": [
+        "7",
+        0
+      ],
+      "latent_image": [
+        "5",
+        0
+      ]
+    },
+    "class_type": "KSampler",
+    "_meta": {
+      "title": "KSampler"
+    }
+  },
+  "4": {
+    "inputs": {
+      "ckpt_name": "model.safetensors"
+    },
+    "class_type": "CheckpointLoaderSimple",
+    "_meta": {
+      "title": "Load Checkpoint"
+    }
+  },
+  "5": {
+    "inputs": {
+      "width": 512,
+      "height": 512,
+      "batch_size": 1
+    },
+    "class_type": "EmptyLatentImage",
+    "_meta": {
+      "title": "Empty Latent Image"
+    }
+  },
+  "6": {
+    "inputs": {
+      "text": "Prompt",
+      "clip": [
+        "4",
+        1
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Prompt)"
+    }
+  },
+  "7": {
+    "inputs": {
+      "text": "Negative Prompt",
+      "clip": [
+        "4",
+        1
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Prompt)"
+    }
+  },
+  "8": {
+    "inputs": {
+      "samples": [
+        "3",
+        0
+      ],
+      "vae": [
+        "4",
+        2
+      ]
+    },
+    "class_type": "VAEDecode",
+    "_meta": {
+      "title": "VAE Decode"
+    }
+  },
+  "9": {
+    "inputs": {
+      "filename_prefix": "ComfyUI",
+      "images": [
+        "8",
+        0
+      ]
+    },
+    "class_type": "SaveImage",
+    "_meta": {
+      "title": "Save Image"
+    }
+  }
+}
+"""
+
+
+def queue_prompt(prompt, client_id, base_url):
+    log.info("queue_prompt")
+    p = {"prompt": prompt, "client_id": client_id}
+    data = json.dumps(p).encode("utf-8")
+    req = urllib.request.Request(f"{base_url}/prompt", data=data)
+    return json.loads(urllib.request.urlopen(req).read())
+
+
+def get_image(filename, subfolder, folder_type, base_url):
+    log.info("get_image")
+    data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
+    url_values = urllib.parse.urlencode(data)
+    with urllib.request.urlopen(f"{base_url}/view?{url_values}") as response:
+        return response.read()
+
+
+def get_image_url(filename, subfolder, folder_type, base_url):
+    log.info("get_image")
+    data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
+    url_values = urllib.parse.urlencode(data)
+    return f"{base_url}/view?{url_values}"
+
+
+def get_history(prompt_id, base_url):
+    log.info("get_history")
+    with urllib.request.urlopen(f"{base_url}/history/{prompt_id}") as response:
+        return json.loads(response.read())
+
+
+def get_images(ws, prompt, client_id, base_url):
+    prompt_id = queue_prompt(prompt, client_id, base_url)["prompt_id"]
+    output_images = []
+    while True:
+        out = ws.recv()
+        if isinstance(out, str):
+            message = json.loads(out)
+            if message["type"] == "executing":
+                data = message["data"]
+                if data["node"] is None and data["prompt_id"] == prompt_id:
+                    break  # Execution is done
+        else:
+            continue  # previews are binary data
+
+    history = get_history(prompt_id, base_url)[prompt_id]
+    for o in history["outputs"]:
+        for node_id in history["outputs"]:
+            node_output = history["outputs"][node_id]
+            if "images" in node_output:
+                for image in node_output["images"]:
+                    url = get_image_url(
+                        image["filename"], image["subfolder"], image["type"], base_url
+                    )
+                    output_images.append({"url": url})
+    return {"data": output_images}
+
+
+class ImageGenerationPayload(BaseModel):
+    prompt: str
+    negative_prompt: Optional[str] = ""
+    steps: Optional[int] = None
+    seed: Optional[int] = None
+    width: int
+    height: int
+    n: int = 1
+
+
+def comfyui_generate_image(
+    model: str, payload: ImageGenerationPayload, client_id, base_url
+):
+    host = base_url.replace("http://", "").replace("https://", "")
+
+    comfyui_prompt = json.loads(COMFYUI_DEFAULT_PROMPT)
+
+    comfyui_prompt["4"]["inputs"]["ckpt_name"] = model
+    comfyui_prompt["5"]["inputs"]["batch_size"] = payload.n
+    comfyui_prompt["5"]["inputs"]["width"] = payload.width
+    comfyui_prompt["5"]["inputs"]["height"] = payload.height
+
+    # set the text prompt for our positive CLIPTextEncode
+    comfyui_prompt["6"]["inputs"]["text"] = payload.prompt
+    comfyui_prompt["7"]["inputs"]["text"] = payload.negative_prompt
+
+    if payload.steps:
+        comfyui_prompt["3"]["inputs"]["steps"] = payload.steps
+
+    comfyui_prompt["3"]["inputs"]["seed"] = (
+        payload.seed if payload.seed else random.randint(0, 18446744073709551614)
+    )
+
+    try:
+        ws = websocket.WebSocket()
+        ws.connect(f"ws://{host}/ws?clientId={client_id}")
+        log.info("WebSocket connection established.")
+    except Exception as e:
+        log.exception(f"Failed to connect to WebSocket server: {e}")
+        return None
+
+    try:
+        images = get_images(ws, comfyui_prompt, client_id, base_url)
+    except Exception as e:
+        log.exception(f"Error while receiving images: {e}")
+        images = None
+
+    ws.close()
+
+    return images
@@ -0,0 +1,100 @@
+import logging
+
+from litellm.proxy.proxy_server import ProxyConfig, initialize
+from litellm.proxy.proxy_server import app
+
+from fastapi import FastAPI, Request, Depends, status, Response
+from fastapi.responses import JSONResponse
+
+from starlette.middleware.base import BaseHTTPMiddleware, RequestResponseEndpoint
+from starlette.responses import StreamingResponse
+import json
+
+from utils.utils import get_http_authorization_cred, get_current_user
+from config import SRC_LOG_LEVELS, ENV
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["LITELLM"])
+
+
+from config import (
+    MODEL_FILTER_ENABLED,
+    MODEL_FILTER_LIST,
+)
+
+
+proxy_config = ProxyConfig()
+
+
+async def config():
+    router, model_list, general_settings = await proxy_config.load_config(
+        router=None, config_file_path="./data/litellm/config.yaml"
+    )
+
+    await initialize(config="./data/litellm/config.yaml", telemetry=False)
+
+
+async def startup():
+    await config()
+
+
+@app.on_event("startup")
+async def on_startup():
+    await startup()
+
+
+app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+
+
+@app.middleware("http")
+async def auth_middleware(request: Request, call_next):
+    auth_header = request.headers.get("Authorization", "")
+    request.state.user = None
+
+    try:
+        user = get_current_user(get_http_authorization_cred(auth_header))
+        log.debug(f"user: {user}")
+        request.state.user = user
+    except Exception as e:
+        return JSONResponse(status_code=400, content={"detail": str(e)})
+
+    response = await call_next(request)
+    return response
+
+
+class ModifyModelsResponseMiddleware(BaseHTTPMiddleware):
+    async def dispatch(
+        self, request: Request, call_next: RequestResponseEndpoint
+    ) -> Response:
+
+        response = await call_next(request)
+        user = request.state.user
+
+        if "/models" in request.url.path:
+            if isinstance(response, StreamingResponse):
+                # Read the content of the streaming response
+                body = b""
+                async for chunk in response.body_iterator:
+                    body += chunk
+
+                data = json.loads(body.decode("utf-8"))
+
+                if app.state.MODEL_FILTER_ENABLED:
+                    if user and user.role == "user":
+                        data["data"] = list(
+                            filter(
+                                lambda model: model["id"]
+                                in app.state.MODEL_FILTER_LIST,
+                                data["data"],
+                            )
+                        )
+
+                # Modified Flag
+                data["modified"] = True
+                return JSONResponse(content=data)
+
+        return response
+
+
+app.add_middleware(ModifyModelsResponseMiddleware)
@@ -1,24 +1,49 @@
-from fastapi import FastAPI, Request, Response, HTTPException, Depends, status
+from fastapi import (
+    FastAPI,
+    Request,
+    Response,
+    HTTPException,
+    Depends,
+    status,
+    UploadFile,
+    File,
+    BackgroundTasks,
+)
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse
 from fastapi.concurrency import run_in_threadpool

 from pydantic import BaseModel, ConfigDict

+import os
+import copy
 import random
 import requests
 import json
 import uuid
 import aiohttp
 import asyncio
+import logging
+from urllib.parse import urlparse
+from typing import Optional, List, Union
+

 from apps.web.models.users import Users
 from constants import ERROR_MESSAGES
 from utils.utils import decode_token, get_current_user, get_admin_user
-from config import OLLAMA_BASE_URLS

-from typing import Optional, List, Union

+from config import (
+    SRC_LOG_LEVELS,
+    OLLAMA_BASE_URLS,
+    MODEL_FILTER_ENABLED,
+    MODEL_FILTER_LIST,
+    UPLOAD_DIR,
+)
+from utils.misc import calculate_sha256
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["OLLAMA"])

 app = FastAPI()
 app.add_middleware(
@@ -29,6 +54,10 @@ app.add_middleware(
    allow_headers=["*"],
 )

+
+app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+
 app.state.OLLAMA_BASE_URLS = OLLAMA_BASE_URLS
 app.state.MODELS = {}

@@ -52,6 +81,12 @@ async def check_url(request: Request, call_next):
    return response


+@app.head("/")
+@app.get("/")
+async def get_status():
+    return {"status": True}
+
+
@app.get("/urls")
 async def get_ollama_api_urls(user=Depends(get_admin_user)):
    return {"OLLAMA_BASE_URLS": app.state.OLLAMA_BASE_URLS}
@@ -65,7 +100,7 @@ class UrlUpdateForm(BaseModel):
 async def update_ollama_api_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
    app.state.OLLAMA_BASE_URLS = form_data.urls

-    print(app.state.OLLAMA_BASE_URLS)
+    log.info(f"app.state.OLLAMA_BASE_URLS: {app.state.OLLAMA_BASE_URLS}")
    return {"OLLAMA_BASE_URLS": app.state.OLLAMA_BASE_URLS}


@@ -86,7 +121,7 @@ async def fetch_url(url):
                return await response.json()
    except Exception as e:
        # Handle connection error here
-        print(f"Connection error: {e}")
+        log.error(f"Connection error: {e}")
        return None


@@ -94,13 +129,14 @@ def merge_models_lists(model_lists):
    merged_models = {}

    for idx, model_list in enumerate(model_lists):
-        for model in model_list:
-            digest = model["digest"]
-            if digest not in merged_models:
-                model["urls"] = [idx]
-                merged_models[digest] = model
-            else:
-                merged_models[digest]["urls"].append(idx)
+        if model_list is not None:
+            for model in model_list:
+                digest = model["digest"]
+                if digest not in merged_models:
+                    model["urls"] = [idx]
+                    merged_models[digest] = model
+                else:
+                    merged_models[digest]["urls"].append(idx)

    return list(merged_models.values())

@@ -109,16 +145,16 @@ def merge_models_lists(model_lists):


 async def get_all_models():
-    print("get_all_models")
+    log.info("get_all_models()")
    tasks = [fetch_url(f"{url}/api/tags") for url in app.state.OLLAMA_BASE_URLS]
    responses = await asyncio.gather(*tasks)
-    responses = list(filter(lambda x: x is not None, responses))

    models = {
        "models": merge_models_lists(
-            map(lambda response: response["models"], responses)
+            map(lambda response: response["models"] if response else None, responses)
        )
    }
+
    app.state.MODELS = {model["model"]: model for model in models["models"]}

    return models
@@ -129,9 +165,19 @@ async def get_all_models():
 async def get_ollama_tags(
    url_idx: Optional[int] = None, user=Depends(get_current_user)
 ):
-
    if url_idx == None:
-        return await get_all_models()
+        models = await get_all_models()
+
+        if app.state.MODEL_FILTER_ENABLED:
+            if user.role == "user":
+                models["models"] = list(
+                    filter(
+                        lambda model: model["name"] in app.state.MODEL_FILTER_LIST,
+                        models["models"],
+                    )
+                )
+                return models
+        return models
    else:
        url = app.state.OLLAMA_BASE_URLS[url_idx]
        try:
@@ -140,7 +186,7 @@ async def get_ollama_tags(

            return r.json()
        except Exception as e:
-            print(e)
+            log.exception(e)
            error_detail = "Open WebUI: Server Connection Error"
            if r is not None:
                try:
@@ -167,11 +213,18 @@ async def get_ollama_versions(url_idx: Optional[int] = None):
        responses = await asyncio.gather(*tasks)
        responses = list(filter(lambda x: x is not None, responses))

-        lowest_version = min(
-            responses, key=lambda x: tuple(map(int, x["version"].split(".")))
-        )
+        if len(responses) > 0:
+            lowest_version = min(
+                responses,
+                key=lambda x: tuple(map(int, x["version"].split("-")[0].split("."))),
+            )

-        return {"version": lowest_version["version"]}
+            return {"version": lowest_version["version"]}
+        else:
+            raise HTTPException(
+                status_code=500,
+                detail=ERROR_MESSAGES.OLLAMA_NOT_FOUND,
+            )
    else:
        url = app.state.OLLAMA_BASE_URLS[url_idx]
        try:
@@ -180,7 +233,7 @@ async def get_ollama_versions(url_idx: Optional[int] = None):

            return r.json()
        except Exception as e:
-            print(e)
+            log.exception(e)
            error_detail = "Open WebUI: Server Connection Error"
            if r is not None:
                try:
@@ -206,18 +259,33 @@ async def pull_model(
    form_data: ModelNameForm, url_idx: int = 0, user=Depends(get_admin_user)
 ):
    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    r = None

    def get_request():
        nonlocal url
        nonlocal r
+
+        request_id = str(uuid.uuid4())
        try:
+            REQUEST_POOL.append(request_id)

            def stream_content():
-                for chunk in r.iter_content(chunk_size=8192):
-                    yield chunk
+                try:
+                    yield json.dumps({"id": request_id, "done": False}) + "\n"
+
+                    for chunk in r.iter_content(chunk_size=8192):
+                        if request_id in REQUEST_POOL:
+                            yield chunk
+                        else:
+                            log.warning("User: canceled request")
+                            break
+                finally:
+                    if hasattr(r, "close"):
+                        r.close()
+                        if request_id in REQUEST_POOL:
+                            REQUEST_POOL.remove(request_id)

            r = requests.request(
                method="POST",
@@ -238,8 +306,9 @@ async def pull_model(

    try:
        return await run_in_threadpool(get_request)
+
    except Exception as e:
-        print(e)
+        log.exception(e)
        error_detail = "Open WebUI: Server Connection Error"
        if r is not None:
            try:
@@ -278,7 +347,7 @@ async def push_model(
            )

    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.debug(f"url: {url}")

    r = None

@@ -310,7 +379,7 @@ async def push_model(
    try:
        return await run_in_threadpool(get_request)
    except Exception as e:
-        print(e)
+        log.exception(e)
        error_detail = "Open WebUI: Server Connection Error"
        if r is not None:
            try:
@@ -338,9 +407,9 @@ class CreateModelForm(BaseModel):
 async def create_model(
    form_data: CreateModelForm, url_idx: int = 0, user=Depends(get_admin_user)
 ):
-    print(form_data)
+    log.debug(f"form_data: {form_data}")
    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    r = None

@@ -362,7 +431,7 @@ async def create_model(

            r.raise_for_status()

-            print(r)
+            log.debug(f"r: {r}")

            return StreamingResponse(
                stream_content(),
@@ -375,7 +444,7 @@ async def create_model(
    try:
        return await run_in_threadpool(get_request)
    except Exception as e:
-        print(e)
+        log.exception(e)
        error_detail = "Open WebUI: Server Connection Error"
        if r is not None:
            try:
@@ -413,7 +482,7 @@ async def copy_model(
            )

    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    try:
        r = requests.request(
@@ -423,11 +492,11 @@ async def copy_model(
        )
        r.raise_for_status()

-        print(r.text)
+        log.debug(f"r.text: {r.text}")

        return True
    except Exception as e:
-        print(e)
+        log.exception(e)
        error_detail = "Open WebUI: Server Connection Error"
        if r is not None:
            try:
@@ -460,7 +529,7 @@ async def delete_model(
            )

    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    try:
        r = requests.request(
@@ -470,11 +539,11 @@ async def delete_model(
        )
        r.raise_for_status()

-        print(r.text)
+        log.debug(f"r.text: {r.text}")

        return True
    except Exception as e:
-        print(e)
+        log.exception(e)
        error_detail = "Open WebUI: Server Connection Error"
        if r is not None:
            try:
@@ -500,7 +569,7 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_current_use

    url_idx = random.choice(app.state.MODELS[form_data.name]["urls"])
    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    try:
        r = requests.request(
@@ -512,7 +581,7 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_current_use

        return r.json()
    except Exception as e:
-        print(e)
+        log.exception(e)
        error_detail = "Open WebUI: Server Connection Error"
        if r is not None:
            try:
@@ -543,8 +612,13 @@ async def generate_embeddings(
    user=Depends(get_current_user),
 ):
    if url_idx == None:
-        if form_data.model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[form_data.model]["urls"])
+        model = form_data.model
+
+        if ":" not in model:
+            model = f"{model}:latest"
+
+        if model in app.state.MODELS:
+            url_idx = random.choice(app.state.MODELS[model]["urls"])
        else:
            raise HTTPException(
                status_code=400,
@@ -552,7 +626,7 @@ async def generate_embeddings(
            )

    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    try:
        r = requests.request(
@@ -564,7 +638,7 @@ async def generate_embeddings(

        return r.json()
    except Exception as e:
-        print(e)
+        log.exception(e)
        error_detail = "Open WebUI: Server Connection Error"
        if r is not None:
            try:
@@ -580,6 +654,60 @@ async def generate_embeddings(
        )


+def generate_ollama_embeddings(
+    form_data: GenerateEmbeddingsForm,
+    url_idx: Optional[int] = None,
+):
+
+    log.info(f"generate_ollama_embeddings {form_data}")
+
+    if url_idx == None:
+        model = form_data.model
+
+        if ":" not in model:
+            model = f"{model}:latest"
+
+        if model in app.state.MODELS:
+            url_idx = random.choice(app.state.MODELS[model]["urls"])
+        else:
+            raise HTTPException(
+                status_code=400,
+                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
+            )
+
+    url = app.state.OLLAMA_BASE_URLS[url_idx]
+    log.info(f"url: {url}")
+
+    try:
+        r = requests.request(
+            method="POST",
+            url=f"{url}/api/embeddings",
+            data=form_data.model_dump_json(exclude_none=True).encode(),
+        )
+        r.raise_for_status()
+
+        data = r.json()
+
+        log.info(f"generate_ollama_embeddings {data}")
+
+        if "embedding" in data:
+            return data["embedding"]
+        else:
+            raise "Something went wrong :/"
+    except Exception as e:
+        log.exception(e)
+        error_detail = "Open WebUI: Server Connection Error"
+        if r is not None:
+            try:
+                res = r.json()
+                if "error" in res:
+                    error_detail = f"Ollama: {res['error']}"
+            except:
+                error_detail = f"Ollama: {e}"
+
+        raise error_detail
+
+
 class GenerateCompletionForm(BaseModel):
    model: str
    prompt: str
@@ -603,16 +731,21 @@ async def generate_completion(
 ):

    if url_idx == None:
-        if form_data.model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[form_data.model]["urls"])
+        model = form_data.model
+
+        if ":" not in model:
+            model = f"{model}:latest"
+
+        if model in app.state.MODELS:
+            url_idx = random.choice(app.state.MODELS[model]["urls"])
        else:
            raise HTTPException(
                status_code=400,
-                detail="error_detail",
+                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
            )

    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    r = None

@@ -633,7 +766,7 @@ async def generate_completion(
                        if request_id in REQUEST_POOL:
                            yield chunk
                        else:
-                            print("User: canceled request")
+                            log.warning("User: canceled request")
                            break
                finally:
                    if hasattr(r, "close"):
@@ -688,7 +821,7 @@ class GenerateChatCompletionForm(BaseModel):
    format: Optional[str] = None
    options: Optional[dict] = None
    template: Optional[str] = None
-    stream: Optional[bool] = True
+    stream: Optional[bool] = None
    keep_alive: Optional[Union[int, str]] = None


@@ -701,8 +834,13 @@ async def generate_chat_completion(
 ):

    if url_idx == None:
-        if form_data.model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[form_data.model]["urls"])
+        model = form_data.model
+
+        if ":" not in model:
+            model = f"{model}:latest"
+
+        if model in app.state.MODELS:
+            url_idx = random.choice(app.state.MODELS[model]["urls"])
        else:
            raise HTTPException(
                status_code=400,
@@ -710,11 +848,15 @@ async def generate_chat_completion(
            )

    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    r = None

-    print(form_data.model_dump_json(exclude_none=True).encode())
+    log.debug(
+        "form_data.model_dump_json(exclude_none=True).encode(): {0} ".format(
+            form_data.model_dump_json(exclude_none=True).encode()
+        )
+    )

    def get_request():
        nonlocal form_data
@@ -733,7 +875,7 @@ async def generate_chat_completion(
                        if request_id in REQUEST_POOL:
                            yield chunk
                        else:
-                            print("User: canceled request")
+                            log.warning("User: canceled request")
                            break
                finally:
                    if hasattr(r, "close"):
@@ -756,7 +898,7 @@ async def generate_chat_completion(
                headers=dict(r.headers),
            )
        except Exception as e:
-            print(e)
+            log.exception(e)
            raise e

    try:
@@ -801,8 +943,13 @@ async def generate_openai_chat_completion(
 ):

    if url_idx == None:
-        if form_data.model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[form_data.model]["urls"])
+        model = form_data.model
+
+        if ":" not in model:
+            model = f"{model}:latest"
+
+        if model in app.state.MODELS:
+            url_idx = random.choice(app.state.MODELS[model]["urls"])
        else:
            raise HTTPException(
                status_code=400,
@@ -810,7 +957,7 @@ async def generate_openai_chat_completion(
            )

    url = app.state.OLLAMA_BASE_URLS[url_idx]
-    print(url)
+    log.info(f"url: {url}")

    r = None

@@ -833,7 +980,7 @@ async def generate_openai_chat_completion(
                        if request_id in REQUEST_POOL:
                            yield chunk
                        else:
-                            print("User: canceled request")
+                            log.warning("User: canceled request")
                            break
                finally:
                    if hasattr(r, "close"):
@@ -876,6 +1023,220 @@ async def generate_openai_chat_completion(
        )


+class UrlForm(BaseModel):
+    url: str
+
+
+class UploadBlobForm(BaseModel):
+    filename: str
+
+
+def parse_huggingface_url(hf_url):
+    try:
+        # Parse the URL
+        parsed_url = urlparse(hf_url)
+
+        # Get the path and split it into components
+        path_components = parsed_url.path.split("/")
+
+        # Extract the desired output
+        user_repo = "/".join(path_components[1:3])
+        model_file = path_components[-1]
+
+        return model_file
+    except ValueError:
+        return None
+
+
+async def download_file_stream(
+    ollama_url, file_url, file_path, file_name, chunk_size=1024 * 1024
+):
+    done = False
+
+    if os.path.exists(file_path):
+        current_size = os.path.getsize(file_path)
+    else:
+        current_size = 0
+
+    headers = {"Range": f"bytes={current_size}-"} if current_size > 0 else {}
+
+    timeout = aiohttp.ClientTimeout(total=600)  # Set the timeout
+
+    async with aiohttp.ClientSession(timeout=timeout) as session:
+        async with session.get(file_url, headers=headers) as response:
+            total_size = int(response.headers.get("content-length", 0)) + current_size
+
+            with open(file_path, "ab+") as file:
+                async for data in response.content.iter_chunked(chunk_size):
+                    current_size += len(data)
+                    file.write(data)
+
+                    done = current_size == total_size
+                    progress = round((current_size / total_size) * 100, 2)
+
+                    yield f'data: {{"progress": {progress}, "completed": {current_size}, "total": {total_size}}}\n\n'
+
+                if done:
+                    file.seek(0)
+                    hashed = calculate_sha256(file)
+                    file.seek(0)
+
+                    url = f"{ollama_url}/api/blobs/sha256:{hashed}"
+                    response = requests.post(url, data=file)
+
+                    if response.ok:
+                        res = {
+                            "done": done,
+                            "blob": f"sha256:{hashed}",
+                            "name": file_name,
+                        }
+                        os.remove(file_path)
+
+                        yield f"data: {json.dumps(res)}\n\n"
+                    else:
+                        raise "Ollama: Could not create blob, Please try again."
+
+
+# def number_generator():
+#     for i in range(1, 101):
+#         yield f"data: {i}\n"
+
+
+# url = "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q2_K.gguf"
+@app.post("/models/download")
+@app.post("/models/download/{url_idx}")
+async def download_model(
+    form_data: UrlForm,
+    url_idx: Optional[int] = None,
+):
+
+    allowed_hosts = ["https://huggingface.co/", "https://github.com/"]
+
+    if not any(form_data.url.startswith(host) for host in allowed_hosts):
+        raise HTTPException(
+            status_code=400,
+            detail="Invalid file_url. Only URLs from allowed hosts are permitted.",
+        )
+
+    if url_idx == None:
+        url_idx = 0
+    url = app.state.OLLAMA_BASE_URLS[url_idx]
+
+    file_name = parse_huggingface_url(form_data.url)
+
+    if file_name:
+        file_path = f"{UPLOAD_DIR}/{file_name}"
+
+        return StreamingResponse(
+            download_file_stream(url, form_data.url, file_path, file_name),
+        )
+    else:
+        return None
+
+
+@app.post("/models/upload")
+@app.post("/models/upload/{url_idx}")
+def upload_model(file: UploadFile = File(...), url_idx: Optional[int] = None):
+    if url_idx == None:
+        url_idx = 0
+    ollama_url = app.state.OLLAMA_BASE_URLS[url_idx]
+
+    file_path = f"{UPLOAD_DIR}/{file.filename}"
+
+    # Save file in chunks
+    with open(file_path, "wb+") as f:
+        for chunk in file.file:
+            f.write(chunk)
+
+    def file_process_stream():
+        nonlocal ollama_url
+        total_size = os.path.getsize(file_path)
+        chunk_size = 1024 * 1024
+        try:
+            with open(file_path, "rb") as f:
+                total = 0
+                done = False
+
+                while not done:
+                    chunk = f.read(chunk_size)
+                    if not chunk:
+                        done = True
+                        continue
+
+                    total += len(chunk)
+                    progress = round((total / total_size) * 100, 2)
+
+                    res = {
+                        "progress": progress,
+                        "total": total_size,
+                        "completed": total,
+                    }
+                    yield f"data: {json.dumps(res)}\n\n"
+
+                if done:
+                    f.seek(0)
+                    hashed = calculate_sha256(f)
+                    f.seek(0)
+
+                    url = f"{ollama_url}/api/blobs/sha256:{hashed}"
+                    response = requests.post(url, data=f)
+
+                    if response.ok:
+                        res = {
+                            "done": done,
+                            "blob": f"sha256:{hashed}",
+                            "name": file.filename,
+                        }
+                        os.remove(file_path)
+                        yield f"data: {json.dumps(res)}\n\n"
+                    else:
+                        raise Exception(
+                            "Ollama: Could not create blob, Please try again."
+                        )
+
+        except Exception as e:
+            res = {"error": str(e)}
+            yield f"data: {json.dumps(res)}\n\n"
+
+    return StreamingResponse(file_process_stream(), media_type="text/event-stream")
+
+
+# async def upload_model(file: UploadFile = File(), url_idx: Optional[int] = None):
+#     if url_idx == None:
+#         url_idx = 0
+#     url = app.state.OLLAMA_BASE_URLS[url_idx]
+
+#     file_location = os.path.join(UPLOAD_DIR, file.filename)
+#     total_size = file.size
+
+#     async def file_upload_generator(file):
+#         print(file)
+#         try:
+#             async with aiofiles.open(file_location, "wb") as f:
+#                 completed_size = 0
+#                 while True:
+#                     chunk = await file.read(1024*1024)
+#                     if not chunk:
+#                         break
+#                     await f.write(chunk)
+#                     completed_size += len(chunk)
+#                     progress = (completed_size / total_size) * 100
+
+#                     print(progress)
+#                     yield f'data: {json.dumps({"status": "uploading", "percentage": progress, "total": total_size, "completed": completed_size, "done": False})}\n'
+#         except Exception as e:
+#             print(e)
+#             yield f"data: {json.dumps({'status': 'error', 'message': str(e)})}\n"
+#         finally:
+#             await file.close()
+#             print("done")
+#             yield f'data: {json.dumps({"status": "completed", "percentage": 100, "total": total_size, "completed": completed_size, "done": True})}\n'
+
+#     return StreamingResponse(
+#         file_upload_generator(copy.deepcopy(file)), media_type="text/event-stream"
+#     )
+
+
@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
 async def deprecated_proxy(path: str, request: Request, user=Depends(get_current_user)):
    url = app.state.OLLAMA_BASE_URLS[0]
@@ -926,7 +1287,7 @@ async def deprecated_proxy(path: str, request: Request, user=Depends(get_current
                        if request_id in REQUEST_POOL:
                            yield chunk
                        else:
-                            print("User: canceled request")
+                            log.warning("User: canceled request")
                            break
                finally:
                    if hasattr(r, "close"):
@@ -6,6 +6,7 @@ import requests
 import aiohttp
 import asyncio
 import json
+import logging

 from pydantic import BaseModel

@@ -18,13 +19,23 @@ from utils.utils import (
    get_verified_user,
    get_admin_user,
 )
-from config import OPENAI_API_BASE_URLS, OPENAI_API_KEYS, CACHE_DIR
+from config import (
+    SRC_LOG_LEVELS,
+    OPENAI_API_BASE_URLS,
+    OPENAI_API_KEYS,
+    CACHE_DIR,
+    MODEL_FILTER_ENABLED,
+    MODEL_FILTER_LIST,
+)
 from typing import List, Optional


 import hashlib
 from pathlib import Path

+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["OPENAI"])
+
 app = FastAPI()
 app.add_middleware(
    CORSMiddleware,
@@ -34,6 +45,9 @@ app.add_middleware(
    allow_headers=["*"],
 )

+app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+
 app.state.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS
 app.state.OPENAI_API_KEYS = OPENAI_API_KEYS

@@ -102,6 +116,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
        headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEYS[idx]}"
        headers["Content-Type"] = "application/json"

+        r = None
        try:
            r = requests.post(
                url=f"{app.state.OPENAI_API_BASE_URLS[idx]}/audio/speech",
@@ -124,7 +139,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
            return FileResponse(file_path)

        except Exception as e:
-            print(e)
+            log.exception(e)
            error_detail = "Open WebUI: Server Connection Error"
            if r is not None:
                try:
@@ -134,7 +149,9 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                except:
                    error_detail = f"External: {e}"

-            raise HTTPException(status_code=r.status_code, detail=error_detail)
+            raise HTTPException(
+                status_code=r.status_code if r else 500, detail=error_detail
+            )

    except ValueError:
        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.OPENAI_NOT_FOUND)
@@ -148,7 +165,7 @@ async def fetch_url(url, key):
                return await response.json()
    except Exception as e:
        # Handle connection error here
-        print(f"Connection error: {e}")
+        log.error(f"Connection error: {e}")
        return None


@@ -156,44 +173,72 @@ def merge_models_lists(model_lists):
    merged_list = []

    for idx, models in enumerate(model_lists):
-        merged_list.extend(
-            [
-                {**model, "urlIdx": idx}
-                for model in models
-                if "api.openai.com" not in app.state.OPENAI_API_BASE_URLS[idx]
-                or "gpt" in model["id"]
-            ]
-        )
+        if models is not None and "error" not in models:
+            merged_list.extend(
+                [
+                    {**model, "urlIdx": idx}
+                    for model in models
+                    if "api.openai.com" not in app.state.OPENAI_API_BASE_URLS[idx]
+                    or "gpt" in model["id"]
+                ]
+            )

    return merged_list


 async def get_all_models():
-    print("get_all_models")
-    tasks = [
-        fetch_url(f"{url}/models", app.state.OPENAI_API_KEYS[idx])
-        for idx, url in enumerate(app.state.OPENAI_API_BASE_URLS)
-    ]
-    responses = await asyncio.gather(*tasks)
-    responses = list(filter(lambda x: x is not None and "error" not in x, responses))
-    models = {
-        "data": merge_models_lists(
-            list(map(lambda response: response["data"], responses))
-        )
-    }
-    app.state.MODELS = {model["id"]: model for model in models["data"]}
+    log.info("get_all_models()")

-    return models
+    if len(app.state.OPENAI_API_KEYS) == 1 and app.state.OPENAI_API_KEYS[0] == "":
+        models = {"data": []}
+    else:
+        tasks = [
+            fetch_url(f"{url}/models", app.state.OPENAI_API_KEYS[idx])
+            for idx, url in enumerate(app.state.OPENAI_API_BASE_URLS)
+        ]
+
+        responses = await asyncio.gather(*tasks)
+        models = {
+            "data": merge_models_lists(
+                list(
+                    map(
+                        lambda response: (
+                            response["data"]
+                            if response and "data" in response
+                            else None
+                        ),
+                        responses,
+                    )
+                )
+            )
+        }
+
+        log.info(f"models: {models}")
+        app.state.MODELS = {model["id"]: model for model in models["data"]}
+
+        return models


-# , user=Depends(get_current_user)
@app.get("/models")
@app.get("/models/{url_idx}")
-async def get_models(url_idx: Optional[int] = None):
+async def get_models(url_idx: Optional[int] = None, user=Depends(get_current_user)):
    if url_idx == None:
-        return await get_all_models()
+        models = await get_all_models()
+        if app.state.MODEL_FILTER_ENABLED:
+            if user.role == "user":
+                models["data"] = list(
+                    filter(
+                        lambda model: model["id"] in app.state.MODEL_FILTER_LIST,
+                        models["data"],
+                    )
+                )
+                return models
+        return models
    else:
        url = app.state.OPENAI_API_BASE_URLS[url_idx]
+
+        r = None
+
        try:
            r = requests.request(method="GET", url=f"{url}/models")
            r.raise_for_status()
@@ -206,7 +251,7 @@ async def get_models(url_idx: Optional[int] = None):

            return response_data
        except Exception as e:
-            print(e)
+            log.exception(e)
            error_detail = "Open WebUI: Server Connection Error"
            if r is not None:
                try:
@@ -240,7 +285,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
        if body.get("model") == "gpt-4-vision-preview":
            if "max_tokens" not in body:
                body["max_tokens"] = 4000
-            print("Modified body_dict:", body)
+            log.debug("Modified body_dict:", body)

        # Fix for ChatGPT calls failing because the num_ctx key is in body
        if "num_ctx" in body:
@@ -252,7 +297,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
        # Convert the modified body back to JSON
        body = json.dumps(body)
    except json.JSONDecodeError as e:
-        print("Error loading request body into a dictionary:", e)
+        log.error("Error loading request body into a dictionary:", e)

    url = app.state.OPENAI_API_BASE_URLS[idx]
    key = app.state.OPENAI_API_KEYS[idx]
@@ -266,6 +311,8 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
    headers["Authorization"] = f"Bearer {key}"
    headers["Content-Type"] = "application/json"

+    r = None
+
    try:
        r = requests.request(
            method=request.method,
@@ -288,14 +335,16 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
            response_data = r.json()
            return response_data
    except Exception as e:
-        print(e)
+        log.exception(e)
        error_detail = "Open WebUI: Server Connection Error"
        if r is not None:
            try:
                res = r.json()
                if "error" in res:
-                    error_detail = f"External: {res['error']}"
+                    error_detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
            except:
                error_detail = f"External: {e}"

-        raise HTTPException(status_code=r.status_code, detail=error_detail)
+        raise HTTPException(
+            status_code=r.status_code if r else 500, detail=error_detail
+        )
@@ -8,19 +8,20 @@ from fastapi import (
    Form,
 )
 from fastapi.middleware.cors import CORSMiddleware
-import os, shutil
+import os, shutil, logging, re

 from pathlib import Path
 from typing import List

-from sentence_transformers import SentenceTransformer
 from chromadb.utils import embedding_functions
+from chromadb.utils.batch_utils import create_batches

 from langchain_community.document_loaders import (
    WebBaseLoader,
    TextLoader,
    PyPDFLoader,
    CSVLoader,
+    BSHTMLLoader,
    Docx2txtLoader,
    UnstructuredEPubLoader,
    UnstructuredWordDocumentLoader,
@@ -38,12 +39,23 @@ import uuid
 import json


+from apps.ollama.main import generate_ollama_embeddings, GenerateEmbeddingsForm
+
 from apps.web.models.documents import (
    Documents,
    DocumentForm,
    DocumentResponse,
 )

+from apps.rag.utils import (
+    query_doc,
+    query_embeddings_doc,
+    query_collection,
+    query_embeddings_collection,
+    get_embedding_model_path,
+    generate_openai_embeddings,
+)
+
 from utils.misc import (
    calculate_sha256,
    calculate_sha256_string,
@@ -52,10 +64,15 @@ from utils.misc import (
 )
 from utils.utils import get_current_user, get_admin_user
 from config import (
+    SRC_LOG_LEVELS,
    UPLOAD_DIR,
    DOCS_DIR,
+    RAG_EMBEDDING_ENGINE,
    RAG_EMBEDDING_MODEL,
-    RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+    RAG_EMBEDDING_MODEL_AUTO_UPDATE,
+    RAG_OPENAI_API_BASE_URL,
+    RAG_OPENAI_API_KEY,
+    DEVICE_TYPE,
    CHROMA_CLIENT,
    CHUNK_SIZE,
    CHUNK_OVERLAP,
@@ -64,27 +81,33 @@ from config import (

 from constants import ERROR_MESSAGES

-#
-# if RAG_EMBEDDING_MODEL:
-#    sentence_transformer_ef = SentenceTransformer(
-#        model_name_or_path=RAG_EMBEDDING_MODEL,
-#        cache_folder=RAG_EMBEDDING_MODEL_DIR,
-#        device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
-#    )
-
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])

 app = FastAPI()

+
+app.state.TOP_K = 4
 app.state.CHUNK_SIZE = CHUNK_SIZE
 app.state.CHUNK_OVERLAP = CHUNK_OVERLAP
-app.state.RAG_TEMPLATE = RAG_TEMPLATE
+
+
+app.state.RAG_EMBEDDING_ENGINE = RAG_EMBEDDING_ENGINE
 app.state.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
-app.state.TOP_K = 4
+app.state.RAG_TEMPLATE = RAG_TEMPLATE
+
+app.state.OPENAI_API_BASE_URL = RAG_OPENAI_API_BASE_URL
+app.state.OPENAI_API_KEY = RAG_OPENAI_API_KEY
+
+app.state.PDF_EXTRACT_IMAGES = False
+

 app.state.sentence_transformer_ef = (
    embedding_functions.SentenceTransformerEmbeddingFunction(
-        model_name=app.state.RAG_EMBEDDING_MODEL,
-        device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+        model_name=get_embedding_model_path(
+            app.state.RAG_EMBEDDING_MODEL, RAG_EMBEDDING_MODEL_AUTO_UPDATE
+        ),
+        device=DEVICE_TYPE,
    )
 )

@@ -108,39 +131,6 @@ class StoreWebForm(CollectionNameForm):
    url: str


-def store_data_in_vector_db(data, collection_name, overwrite: bool = False) -> bool:
-    text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=app.state.CHUNK_SIZE, chunk_overlap=app.state.CHUNK_OVERLAP
-    )
-    docs = text_splitter.split_documents(data)
-
-    texts = [doc.page_content for doc in docs]
-    metadatas = [doc.metadata for doc in docs]
-
-    try:
-        if overwrite:
-            for collection in CHROMA_CLIENT.list_collections():
-                if collection_name == collection.name:
-                    print(f"deleting existing collection {collection_name}")
-                    CHROMA_CLIENT.delete_collection(name=collection_name)
-
-        collection = CHROMA_CLIENT.create_collection(
-            name=collection_name,
-            embedding_function=app.state.sentence_transformer_ef,
-        )
-
-        collection.add(
-            documents=texts, metadatas=metadatas, ids=[str(uuid.uuid1()) for _ in texts]
-        )
-        return True
-    except Exception as e:
-        print(e)
-        if e.__class__.__name__ == "UniqueConstraintError":
-            return True
-
-        return False
-
-
@app.get("/")
 async def get_status():
    return {
@@ -148,46 +138,91 @@ async def get_status():
        "chunk_size": app.state.CHUNK_SIZE,
        "chunk_overlap": app.state.CHUNK_OVERLAP,
        "template": app.state.RAG_TEMPLATE,
+        "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
        "embedding_model": app.state.RAG_EMBEDDING_MODEL,
    }


-@app.get("/embedding/model")
-async def get_embedding_model(user=Depends(get_admin_user)):
+@app.get("/embedding")
+async def get_embedding_config(user=Depends(get_admin_user)):
    return {
        "status": True,
+        "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
        "embedding_model": app.state.RAG_EMBEDDING_MODEL,
+        "openai_config": {
+            "url": app.state.OPENAI_API_BASE_URL,
+            "key": app.state.OPENAI_API_KEY,
+        },
    }


+class OpenAIConfigForm(BaseModel):
+    url: str
+    key: str
+
+
 class EmbeddingModelUpdateForm(BaseModel):
+    openai_config: Optional[OpenAIConfigForm] = None
+    embedding_engine: str
    embedding_model: str


-@app.post("/embedding/model/update")
-async def update_embedding_model(
+@app.post("/embedding/update")
+async def update_embedding_config(
    form_data: EmbeddingModelUpdateForm, user=Depends(get_admin_user)
 ):
-    app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
-    app.state.sentence_transformer_ef = (
-        embedding_functions.SentenceTransformerEmbeddingFunction(
-            model_name=app.state.RAG_EMBEDDING_MODEL,
-            device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
-        )
+    log.info(
+        f"Updating embedding model: {app.state.RAG_EMBEDDING_MODEL} to {form_data.embedding_model}"
    )
+    try:
+        app.state.RAG_EMBEDDING_ENGINE = form_data.embedding_engine

+        if app.state.RAG_EMBEDDING_ENGINE in ["ollama", "openai"]:
+            app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
+            app.state.sentence_transformer_ef = None
+
+            if form_data.openai_config != None:
+                app.state.OPENAI_API_BASE_URL = form_data.openai_config.url
+                app.state.OPENAI_API_KEY = form_data.openai_config.key
+        else:
+            sentence_transformer_ef = (
+                embedding_functions.SentenceTransformerEmbeddingFunction(
+                    model_name=get_embedding_model_path(
+                        form_data.embedding_model, True
+                    ),
+                    device=DEVICE_TYPE,
+                )
+            )
+            app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
+            app.state.sentence_transformer_ef = sentence_transformer_ef
+
+        return {
+            "status": True,
+            "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
+            "embedding_model": app.state.RAG_EMBEDDING_MODEL,
+            "openai_config": {
+                "url": app.state.OPENAI_API_BASE_URL,
+                "key": app.state.OPENAI_API_KEY,
+            },
+        }
+
+    except Exception as e:
+        log.exception(f"Problem updating embedding model: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )
+
+
+@app.get("/config")
+async def get_rag_config(user=Depends(get_admin_user)):
    return {
        "status": True,
-        "embedding_model": app.state.RAG_EMBEDDING_MODEL,
-    }
-
-
-@app.get("/chunk")
-async def get_chunk_params(user=Depends(get_admin_user)):
-    return {
-        "status": True,
-        "chunk_size": app.state.CHUNK_SIZE,
-        "chunk_overlap": app.state.CHUNK_OVERLAP,
+        "pdf_extract_images": app.state.PDF_EXTRACT_IMAGES,
+        "chunk": {
+            "chunk_size": app.state.CHUNK_SIZE,
+            "chunk_overlap": app.state.CHUNK_OVERLAP,
+        },
    }


@@ -196,17 +231,24 @@ class ChunkParamUpdateForm(BaseModel):
    chunk_overlap: int


-@app.post("/chunk/update")
-async def update_chunk_params(
-    form_data: ChunkParamUpdateForm, user=Depends(get_admin_user)
-):
-    app.state.CHUNK_SIZE = form_data.chunk_size
-    app.state.CHUNK_OVERLAP = form_data.chunk_overlap
+class ConfigUpdateForm(BaseModel):
+    pdf_extract_images: bool
+    chunk: ChunkParamUpdateForm
+
+
+@app.post("/config/update")
+async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_user)):
+    app.state.PDF_EXTRACT_IMAGES = form_data.pdf_extract_images
+    app.state.CHUNK_SIZE = form_data.chunk.chunk_size
+    app.state.CHUNK_OVERLAP = form_data.chunk.chunk_overlap

    return {
        "status": True,
-        "chunk_size": app.state.CHUNK_SIZE,
-        "chunk_overlap": app.state.CHUNK_OVERLAP,
+        "pdf_extract_images": app.state.PDF_EXTRACT_IMAGES,
+        "chunk": {
+            "chunk_size": app.state.CHUNK_SIZE,
+            "chunk_overlap": app.state.CHUNK_OVERLAP,
+        },
    }


@@ -248,23 +290,45 @@ class QueryDocForm(BaseModel):


@app.post("/query/doc")
-def query_doc(
+def query_doc_handler(
    form_data: QueryDocForm,
    user=Depends(get_current_user),
 ):
+
    try:
-        # if you use docker use the model from the environment variable
-        collection = CHROMA_CLIENT.get_collection(
-            name=form_data.collection_name,
-            embedding_function=app.state.sentence_transformer_ef,
-        )
-        result = collection.query(
-            query_texts=[form_data.query],
-            n_results=form_data.k if form_data.k else app.state.TOP_K,
-        )
-        return result
+        if app.state.RAG_EMBEDDING_ENGINE == "":
+            return query_doc(
+                collection_name=form_data.collection_name,
+                query=form_data.query,
+                k=form_data.k if form_data.k else app.state.TOP_K,
+                embedding_function=app.state.sentence_transformer_ef,
+            )
+        else:
+            if app.state.RAG_EMBEDDING_ENGINE == "ollama":
+                query_embeddings = generate_ollama_embeddings(
+                    GenerateEmbeddingsForm(
+                        **{
+                            "model": app.state.RAG_EMBEDDING_MODEL,
+                            "prompt": form_data.query,
+                        }
+                    )
+                )
+            elif app.state.RAG_EMBEDDING_ENGINE == "openai":
+                query_embeddings = generate_openai_embeddings(
+                    model=app.state.RAG_EMBEDDING_MODEL,
+                    text=form_data.query,
+                    key=app.state.OPENAI_API_KEY,
+                    url=app.state.OPENAI_API_BASE_URL,
+                )
+
+            return query_embeddings_doc(
+                collection_name=form_data.collection_name,
+                query_embeddings=query_embeddings,
+                k=form_data.k if form_data.k else app.state.TOP_K,
+            )
+
    except Exception as e:
-        print(e)
+        log.exception(e)
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
            detail=ERROR_MESSAGES.DEFAULT(e),
@@ -277,77 +341,50 @@ class QueryCollectionsForm(BaseModel):
    k: Optional[int] = None


-def merge_and_sort_query_results(query_results, k):
-    # Initialize lists to store combined data
-    combined_ids = []
-    combined_distances = []
-    combined_metadatas = []
-    combined_documents = []
-
-    # Combine data from each dictionary
-    for data in query_results:
-        combined_ids.extend(data["ids"][0])
-        combined_distances.extend(data["distances"][0])
-        combined_metadatas.extend(data["metadatas"][0])
-        combined_documents.extend(data["documents"][0])
-
-    # Create a list of tuples (distance, id, metadata, document)
-    combined = list(
-        zip(combined_distances, combined_ids, combined_metadatas, combined_documents)
-    )
-
-    # Sort the list based on distances
-    combined.sort(key=lambda x: x[0])
-
-    # Unzip the sorted list
-    sorted_distances, sorted_ids, sorted_metadatas, sorted_documents = zip(*combined)
-
-    # Slicing the lists to include only k elements
-    sorted_distances = list(sorted_distances)[:k]
-    sorted_ids = list(sorted_ids)[:k]
-    sorted_metadatas = list(sorted_metadatas)[:k]
-    sorted_documents = list(sorted_documents)[:k]
-
-    # Create the output dictionary
-    merged_query_results = {
-        "ids": [sorted_ids],
-        "distances": [sorted_distances],
-        "metadatas": [sorted_metadatas],
-        "documents": [sorted_documents],
-        "embeddings": None,
-        "uris": None,
-        "data": None,
-    }
-
-    return merged_query_results
-
-
@app.post("/query/collection")
-def query_collection(
+def query_collection_handler(
    form_data: QueryCollectionsForm,
    user=Depends(get_current_user),
 ):
-    results = []
-
-    for collection_name in form_data.collection_names:
-        try:
-            # if you use docker use the model from the environment variable
-            collection = CHROMA_CLIENT.get_collection(
-                name=collection_name,
+    try:
+        if app.state.RAG_EMBEDDING_ENGINE == "":
+            return query_collection(
+                collection_names=form_data.collection_names,
+                query=form_data.query,
+                k=form_data.k if form_data.k else app.state.TOP_K,
                embedding_function=app.state.sentence_transformer_ef,
            )
+        else:

-            result = collection.query(
-                query_texts=[form_data.query],
-                n_results=form_data.k if form_data.k else app.state.TOP_K,
+            if app.state.RAG_EMBEDDING_ENGINE == "ollama":
+                query_embeddings = generate_ollama_embeddings(
+                    GenerateEmbeddingsForm(
+                        **{
+                            "model": app.state.RAG_EMBEDDING_MODEL,
+                            "prompt": form_data.query,
+                        }
+                    )
+                )
+            elif app.state.RAG_EMBEDDING_ENGINE == "openai":
+                query_embeddings = generate_openai_embeddings(
+                    model=app.state.RAG_EMBEDDING_MODEL,
+                    text=form_data.query,
+                    key=app.state.OPENAI_API_KEY,
+                    url=app.state.OPENAI_API_BASE_URL,
+                )
+
+            return query_embeddings_collection(
+                collection_names=form_data.collection_names,
+                query_embeddings=query_embeddings,
+                k=form_data.k if form_data.k else app.state.TOP_K,
            )
-            results.append(result)
-        except:
-            pass

-    return merge_and_sort_query_results(
-        results, form_data.k if form_data.k else app.state.TOP_K
-    )
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )


@app.post("/web")
@@ -368,13 +405,111 @@ def store_web(form_data: StoreWebForm, user=Depends(get_current_user)):
            "filename": form_data.url,
        }
    except Exception as e:
-        print(e)
+        log.exception(e)
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
            detail=ERROR_MESSAGES.DEFAULT(e),
        )


+def store_data_in_vector_db(data, collection_name, overwrite: bool = False) -> bool:
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=app.state.CHUNK_SIZE,
+        chunk_overlap=app.state.CHUNK_OVERLAP,
+        add_start_index=True,
+    )
+
+    docs = text_splitter.split_documents(data)
+
+    if len(docs) > 0:
+        log.info(f"store_data_in_vector_db {docs}")
+        return store_docs_in_vector_db(docs, collection_name, overwrite), None
+    else:
+        raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
+
+
+def store_text_in_vector_db(
+    text, metadata, collection_name, overwrite: bool = False
+) -> bool:
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=app.state.CHUNK_SIZE,
+        chunk_overlap=app.state.CHUNK_OVERLAP,
+        add_start_index=True,
+    )
+    docs = text_splitter.create_documents([text], metadatas=[metadata])
+    return store_docs_in_vector_db(docs, collection_name, overwrite)
+
+
+def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> bool:
+    log.info(f"store_docs_in_vector_db {docs} {collection_name}")
+
+    texts = [doc.page_content for doc in docs]
+    metadatas = [doc.metadata for doc in docs]
+
+    try:
+        if overwrite:
+            for collection in CHROMA_CLIENT.list_collections():
+                if collection_name == collection.name:
+                    log.info(f"deleting existing collection {collection_name}")
+                    CHROMA_CLIENT.delete_collection(name=collection_name)
+
+        if app.state.RAG_EMBEDDING_ENGINE == "":
+
+            collection = CHROMA_CLIENT.create_collection(
+                name=collection_name,
+                embedding_function=app.state.sentence_transformer_ef,
+            )
+
+            for batch in create_batches(
+                api=CHROMA_CLIENT,
+                ids=[str(uuid.uuid1()) for _ in texts],
+                metadatas=metadatas,
+                documents=texts,
+            ):
+                collection.add(*batch)
+
+        else:
+            collection = CHROMA_CLIENT.create_collection(name=collection_name)
+
+            if app.state.RAG_EMBEDDING_ENGINE == "ollama":
+                embeddings = [
+                    generate_ollama_embeddings(
+                        GenerateEmbeddingsForm(
+                            **{"model": app.state.RAG_EMBEDDING_MODEL, "prompt": text}
+                        )
+                    )
+                    for text in texts
+                ]
+            elif app.state.RAG_EMBEDDING_ENGINE == "openai":
+                embeddings = [
+                    generate_openai_embeddings(
+                        model=app.state.RAG_EMBEDDING_MODEL,
+                        text=text,
+                        key=app.state.OPENAI_API_KEY,
+                        url=app.state.OPENAI_API_BASE_URL,
+                    )
+                    for text in texts
+                ]
+
+            for batch in create_batches(
+                api=CHROMA_CLIENT,
+                ids=[str(uuid.uuid1()) for _ in texts],
+                metadatas=metadatas,
+                embeddings=embeddings,
+                documents=texts,
+            ):
+                collection.add(*batch)
+
+        return True
+    except Exception as e:
+        log.exception(e)
+        if e.__class__.__name__ == "UniqueConstraintError":
+            return True
+
+        return False
+
+
 def get_loader(filename: str, file_content_type: str, file_path: str):
    file_ext = filename.split(".")[-1].lower()
    known_type = True
@@ -425,13 +560,15 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
    ]

    if file_ext == "pdf":
-        loader = PyPDFLoader(file_path, extract_images=True)
+        loader = PyPDFLoader(file_path, extract_images=app.state.PDF_EXTRACT_IMAGES)
    elif file_ext == "csv":
        loader = CSVLoader(file_path)
    elif file_ext == "rst":
        loader = UnstructuredRSTLoader(file_path, mode="elements")
    elif file_ext == "xml":
        loader = UnstructuredXMLLoader(file_path)
+    elif file_ext in ["htm", "html"]:
+        loader = BSHTMLLoader(file_path, open_encoding="unicode_escape")
    elif file_ext == "md":
        loader = UnstructuredMarkdownLoader(file_path)
    elif file_content_type == "application/epub+zip":
@@ -450,9 +587,9 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
    elif file_ext in known_source_ext or (
        file_content_type and file_content_type.find("text/") >= 0
    ):
-        loader = TextLoader(file_path)
+        loader = TextLoader(file_path, autodetect_encoding=True)
    else:
-        loader = TextLoader(file_path)
+        loader = TextLoader(file_path, autodetect_encoding=True)
        known_type = False

    return loader, known_type
@@ -466,10 +603,13 @@ def store_doc(
 ):
    # "https://www.gutenberg.org/files/1727/1727-h/1727-h.htm"

-    print(file.content_type)
+    log.info(f"file.content_type: {file.content_type}")
    try:
-        filename = file.filename
+        unsanitized_filename = file.filename
+        filename = os.path.basename(unsanitized_filename)
+
        file_path = f"{UPLOAD_DIR}/{filename}"
+
        contents = file.file.read()
        with open(file_path, "wb") as f:
            f.write(contents)
@@ -480,24 +620,26 @@ def store_doc(
            collection_name = calculate_sha256(f)[:63]
        f.close()

-        loader, known_type = get_loader(file.filename, file.content_type, file_path)
+        loader, known_type = get_loader(filename, file.content_type, file_path)
        data = loader.load()
-        result = store_data_in_vector_db(data, collection_name)

-        if result:
-            return {
-                "status": True,
-                "collection_name": collection_name,
-                "filename": filename,
-                "known_type": known_type,
-            }
-        else:
+        try:
+            result = store_data_in_vector_db(data, collection_name)
+
+            if result:
+                return {
+                    "status": True,
+                    "collection_name": collection_name,
+                    "filename": filename,
+                    "known_type": known_type,
+                }
+        except Exception as e:
            raise HTTPException(
                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=ERROR_MESSAGES.DEFAULT(),
+                detail=e,
            )
    except Exception as e:
-        print(e)
+        log.exception(e)
        if "No pandoc was found" in str(e):
            raise HTTPException(
                status_code=status.HTTP_400_BAD_REQUEST,
@@ -510,6 +652,37 @@ def store_doc(
            )


+class TextRAGForm(BaseModel):
+    name: str
+    content: str
+    collection_name: Optional[str] = None
+
+
+@app.post("/text")
+def store_text(
+    form_data: TextRAGForm,
+    user=Depends(get_current_user),
+):
+
+    collection_name = form_data.collection_name
+    if collection_name == None:
+        collection_name = calculate_sha256_string(form_data.content)
+
+    result = store_text_in_vector_db(
+        form_data.content,
+        metadata={"name": form_data.name, "created_by": user.id},
+        collection_name=collection_name,
+    )
+
+    if result:
+        return {"status": True, "collection_name": collection_name}
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=ERROR_MESSAGES.DEFAULT(),
+        )
+
+
@app.get("/scan")
 def scan_docs_dir(user=Depends(get_admin_user)):
    for path in Path(DOCS_DIR).rglob("./**/*"):
@@ -528,41 +701,45 @@ def scan_docs_dir(user=Depends(get_admin_user)):
                )
                data = loader.load()

-                result = store_data_in_vector_db(data, collection_name)
+                try:
+                    result = store_data_in_vector_db(data, collection_name)

-                if result:
-                    sanitized_filename = sanitize_filename(filename)
-                    doc = Documents.get_doc_by_name(sanitized_filename)
+                    if result:
+                        sanitized_filename = sanitize_filename(filename)
+                        doc = Documents.get_doc_by_name(sanitized_filename)

-                    if doc == None:
-                        doc = Documents.insert_new_doc(
-                            user.id,
-                            DocumentForm(
-                                **{
-                                    "name": sanitized_filename,
-                                    "title": filename,
-                                    "collection_name": collection_name,
-                                    "filename": filename,
-                                    "content": (
-                                        json.dumps(
-                                            {
-                                                "tags": list(
-                                                    map(
-                                                        lambda name: {"name": name},
-                                                        tags,
+                        if doc == None:
+                            doc = Documents.insert_new_doc(
+                                user.id,
+                                DocumentForm(
+                                    **{
+                                        "name": sanitized_filename,
+                                        "title": filename,
+                                        "collection_name": collection_name,
+                                        "filename": filename,
+                                        "content": (
+                                            json.dumps(
+                                                {
+                                                    "tags": list(
+                                                        map(
+                                                            lambda name: {"name": name},
+                                                            tags,
+                                                        )
                                                    )
-                                                )
-                                            }
-                                        )
-                                        if len(tags)
-                                        else "{}"
-                                    ),
-                                }
-                            ),
-                        )
+                                                }
+                                            )
+                                            if len(tags)
+                                            else "{}"
+                                        ),
+                                    }
+                                ),
+                            )
+                except Exception as e:
+                    log.exception(e)
+                    pass

        except Exception as e:
-            print(e)
+            log.exception(e)

    return True

@@ -583,11 +760,11 @@ def reset(user=Depends(get_admin_user)) -> bool:
            elif os.path.isdir(file_path):
                shutil.rmtree(file_path)
        except Exception as e:
-            print("Failed to delete %s. Reason: %s" % (file_path, e))
+            log.error("Failed to delete %s. Reason: %s" % (file_path, e))

    try:
        CHROMA_CLIENT.reset()
    except Exception as e:
-        print(e)
+        log.exception(e)

    return True
@@ -0,0 +1,346 @@
+import os
+import re
+import logging
+from typing import List
+import requests
+
+
+from huggingface_hub import snapshot_download
+from apps.ollama.main import generate_ollama_embeddings, GenerateEmbeddingsForm
+
+
+from config import SRC_LOG_LEVELS, CHROMA_CLIENT
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def query_doc(collection_name: str, query: str, k: int, embedding_function):
+    try:
+        # if you use docker use the model from the environment variable
+        collection = CHROMA_CLIENT.get_collection(
+            name=collection_name,
+            embedding_function=embedding_function,
+        )
+        result = collection.query(
+            query_texts=[query],
+            n_results=k,
+        )
+        return result
+    except Exception as e:
+        raise e
+
+
+def query_embeddings_doc(collection_name: str, query_embeddings, k: int):
+    try:
+        # if you use docker use the model from the environment variable
+        log.info(f"query_embeddings_doc {query_embeddings}")
+        collection = CHROMA_CLIENT.get_collection(
+            name=collection_name,
+        )
+        result = collection.query(
+            query_embeddings=[query_embeddings],
+            n_results=k,
+        )
+
+        log.info(f"query_embeddings_doc:result {result}")
+        return result
+    except Exception as e:
+        raise e
+
+
+def merge_and_sort_query_results(query_results, k):
+    # Initialize lists to store combined data
+    combined_ids = []
+    combined_distances = []
+    combined_metadatas = []
+    combined_documents = []
+
+    # Combine data from each dictionary
+    for data in query_results:
+        combined_ids.extend(data["ids"][0])
+        combined_distances.extend(data["distances"][0])
+        combined_metadatas.extend(data["metadatas"][0])
+        combined_documents.extend(data["documents"][0])
+
+    # Create a list of tuples (distance, id, metadata, document)
+    combined = list(
+        zip(combined_distances, combined_ids, combined_metadatas, combined_documents)
+    )
+
+    # Sort the list based on distances
+    combined.sort(key=lambda x: x[0])
+
+    # Unzip the sorted list
+    sorted_distances, sorted_ids, sorted_metadatas, sorted_documents = zip(*combined)
+
+    # Slicing the lists to include only k elements
+    sorted_distances = list(sorted_distances)[:k]
+    sorted_ids = list(sorted_ids)[:k]
+    sorted_metadatas = list(sorted_metadatas)[:k]
+    sorted_documents = list(sorted_documents)[:k]
+
+    # Create the output dictionary
+    merged_query_results = {
+        "ids": [sorted_ids],
+        "distances": [sorted_distances],
+        "metadatas": [sorted_metadatas],
+        "documents": [sorted_documents],
+        "embeddings": None,
+        "uris": None,
+        "data": None,
+    }
+
+    return merged_query_results
+
+
+def query_collection(
+    collection_names: List[str], query: str, k: int, embedding_function
+):
+
+    results = []
+
+    for collection_name in collection_names:
+        try:
+            # if you use docker use the model from the environment variable
+            collection = CHROMA_CLIENT.get_collection(
+                name=collection_name,
+                embedding_function=embedding_function,
+            )
+
+            result = collection.query(
+                query_texts=[query],
+                n_results=k,
+            )
+            results.append(result)
+        except:
+            pass
+
+    return merge_and_sort_query_results(results, k)
+
+
+def query_embeddings_collection(collection_names: List[str], query_embeddings, k: int):
+
+    results = []
+    log.info(f"query_embeddings_collection {query_embeddings}")
+
+    for collection_name in collection_names:
+        try:
+            collection = CHROMA_CLIENT.get_collection(name=collection_name)
+
+            result = collection.query(
+                query_embeddings=[query_embeddings],
+                n_results=k,
+            )
+            results.append(result)
+        except:
+            pass
+
+    return merge_and_sort_query_results(results, k)
+
+
+def rag_template(template: str, context: str, query: str):
+    template = template.replace("[context]", context)
+    template = template.replace("[query]", query)
+    return template
+
+
+def rag_messages(
+    docs,
+    messages,
+    template,
+    k,
+    embedding_engine,
+    embedding_model,
+    embedding_function,
+    openai_key,
+    openai_url,
+):
+    log.debug(
+        f"docs: {docs} {messages} {embedding_engine} {embedding_model} {embedding_function} {openai_key} {openai_url}"
+    )
+
+    last_user_message_idx = None
+    for i in range(len(messages) - 1, -1, -1):
+        if messages[i]["role"] == "user":
+            last_user_message_idx = i
+            break
+
+    user_message = messages[last_user_message_idx]
+
+    if isinstance(user_message["content"], list):
+        # Handle list content input
+        content_type = "list"
+        query = ""
+        for content_item in user_message["content"]:
+            if content_item["type"] == "text":
+                query = content_item["text"]
+                break
+    elif isinstance(user_message["content"], str):
+        # Handle text content input
+        content_type = "text"
+        query = user_message["content"]
+    else:
+        # Fallback in case the input does not match expected types
+        content_type = None
+        query = ""
+
+    relevant_contexts = []
+
+    for doc in docs:
+        context = None
+
+        try:
+
+            if doc["type"] == "text":
+                context = doc["content"]
+            else:
+                if embedding_engine == "":
+                    if doc["type"] == "collection":
+                        context = query_collection(
+                            collection_names=doc["collection_names"],
+                            query=query,
+                            k=k,
+                            embedding_function=embedding_function,
+                        )
+                    else:
+                        context = query_doc(
+                            collection_name=doc["collection_name"],
+                            query=query,
+                            k=k,
+                            embedding_function=embedding_function,
+                        )
+
+                else:
+                    if embedding_engine == "ollama":
+                        query_embeddings = generate_ollama_embeddings(
+                            GenerateEmbeddingsForm(
+                                **{
+                                    "model": embedding_model,
+                                    "prompt": query,
+                                }
+                            )
+                        )
+                    elif embedding_engine == "openai":
+                        query_embeddings = generate_openai_embeddings(
+                            model=embedding_model,
+                            text=query,
+                            key=openai_key,
+                            url=openai_url,
+                        )
+
+                    if doc["type"] == "collection":
+                        context = query_embeddings_collection(
+                            collection_names=doc["collection_names"],
+                            query_embeddings=query_embeddings,
+                            k=k,
+                        )
+                    else:
+                        context = query_embeddings_doc(
+                            collection_name=doc["collection_name"],
+                            query_embeddings=query_embeddings,
+                            k=k,
+                        )
+
+        except Exception as e:
+            log.exception(e)
+            context = None
+
+        relevant_contexts.append(context)
+
+    log.debug(f"relevant_contexts: {relevant_contexts}")
+
+    context_string = ""
+    for context in relevant_contexts:
+        if context:
+            context_string += " ".join(context["documents"][0]) + "\n"
+
+    ra_content = rag_template(
+        template=template,
+        context=context_string,
+        query=query,
+    )
+
+    if content_type == "list":
+        new_content = []
+        for content_item in user_message["content"]:
+            if content_item["type"] == "text":
+                # Update the text item's content with ra_content
+                new_content.append({"type": "text", "text": ra_content})
+            else:
+                # Keep other types of content as they are
+                new_content.append(content_item)
+        new_user_message = {**user_message, "content": new_content}
+    else:
+        new_user_message = {
+            **user_message,
+            "content": ra_content,
+        }
+
+    messages[last_user_message_idx] = new_user_message
+
+    return messages
+
+
+def get_embedding_model_path(
+    embedding_model: str, update_embedding_model: bool = False
+):
+    # Construct huggingface_hub kwargs with local_files_only to return the snapshot path
+    cache_dir = os.getenv("SENTENCE_TRANSFORMERS_HOME")
+
+    local_files_only = not update_embedding_model
+
+    snapshot_kwargs = {
+        "cache_dir": cache_dir,
+        "local_files_only": local_files_only,
+    }
+
+    log.debug(f"embedding_model: {embedding_model}")
+    log.debug(f"snapshot_kwargs: {snapshot_kwargs}")
+
+    # Inspiration from upstream sentence_transformers
+    if (
+        os.path.exists(embedding_model)
+        or ("\\" in embedding_model or embedding_model.count("/") > 1)
+        and local_files_only
+    ):
+        # If fully qualified path exists, return input, else set repo_id
+        return embedding_model
+    elif "/" not in embedding_model:
+        # Set valid repo_id for model short-name
+        embedding_model = "sentence-transformers" + "/" + embedding_model
+
+    snapshot_kwargs["repo_id"] = embedding_model
+
+    # Attempt to query the huggingface_hub library to determine the local path and/or to update
+    try:
+        embedding_model_repo_path = snapshot_download(**snapshot_kwargs)
+        log.debug(f"embedding_model_repo_path: {embedding_model_repo_path}")
+        return embedding_model_repo_path
+    except Exception as e:
+        log.exception(f"Cannot determine embedding model snapshot path: {e}")
+        return embedding_model
+
+
+def generate_openai_embeddings(
+    model: str, text: str, key: str, url: str = "https://api.openai.com/v1"
+):
+    try:
+        r = requests.post(
+            f"{url}/embeddings",
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {key}",
+            },
+            json={"input": text, "model": model},
+        )
+        r.raise_for_status()
+        data = r.json()
+        if "data" in data:
+            return data["data"][0]["embedding"]
+        else:
+            raise "Something went wrong :/"
+    except Exception as e:
+        print(e)
+        return None
@@ -1,16 +1,22 @@
 from peewee import *
-from config import DATA_DIR
+from peewee_migrate import Router
+from config import SRC_LOG_LEVELS, DATA_DIR
 import os
+import logging

+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["DB"])

 # Check if the file exists
 if os.path.exists(f"{DATA_DIR}/ollama.db"):
    # Rename the file
    os.rename(f"{DATA_DIR}/ollama.db", f"{DATA_DIR}/webui.db")
-    print("File renamed successfully.")
+    log.info("File renamed successfully.")
 else:
    pass


 DB = SqliteDatabase(f"{DATA_DIR}/webui.db")
-DB.connect()
+router = Router(DB, migrate_dir="apps/web/internal/migrations", logger=log)
+router.run()
+DB.connect(reuse_if_open=True)
@@ -0,0 +1,149 @@
+"""Peewee migrations -- 001_initial_schema.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    @migrator.create_model
+    class Auth(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        email = pw.CharField(max_length=255)
+        password = pw.CharField(max_length=255)
+        active = pw.BooleanField()
+
+        class Meta:
+            table_name = "auth"
+
+    @migrator.create_model
+    class Chat(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        user_id = pw.CharField(max_length=255)
+        title = pw.CharField()
+        chat = pw.TextField()
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "chat"
+
+    @migrator.create_model
+    class ChatIdTag(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        tag_name = pw.CharField(max_length=255)
+        chat_id = pw.CharField(max_length=255)
+        user_id = pw.CharField(max_length=255)
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "chatidtag"
+
+    @migrator.create_model
+    class Document(pw.Model):
+        id = pw.AutoField()
+        collection_name = pw.CharField(max_length=255, unique=True)
+        name = pw.CharField(max_length=255, unique=True)
+        title = pw.CharField()
+        filename = pw.CharField()
+        content = pw.TextField(null=True)
+        user_id = pw.CharField(max_length=255)
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "document"
+
+    @migrator.create_model
+    class Modelfile(pw.Model):
+        id = pw.AutoField()
+        tag_name = pw.CharField(max_length=255, unique=True)
+        user_id = pw.CharField(max_length=255)
+        modelfile = pw.TextField()
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "modelfile"
+
+    @migrator.create_model
+    class Prompt(pw.Model):
+        id = pw.AutoField()
+        command = pw.CharField(max_length=255, unique=True)
+        user_id = pw.CharField(max_length=255)
+        title = pw.CharField()
+        content = pw.TextField()
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "prompt"
+
+    @migrator.create_model
+    class Tag(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        name = pw.CharField(max_length=255)
+        user_id = pw.CharField(max_length=255)
+        data = pw.TextField(null=True)
+
+        class Meta:
+            table_name = "tag"
+
+    @migrator.create_model
+    class User(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        name = pw.CharField(max_length=255)
+        email = pw.CharField(max_length=255)
+        role = pw.CharField(max_length=255)
+        profile_image_url = pw.CharField(max_length=255)
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "user"
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    migrator.remove_model("user")
+
+    migrator.remove_model("tag")
+
+    migrator.remove_model("prompt")
+
+    migrator.remove_model("modelfile")
+
+    migrator.remove_model("document")
+
+    migrator.remove_model("chatidtag")
+
+    migrator.remove_model("chat")
+
+    migrator.remove_model("auth")
@@ -0,0 +1,48 @@
+"""Peewee migrations -- 002_add_local_sharing.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    migrator.add_fields(
+        "chat", share_id=pw.CharField(max_length=255, null=True, unique=True)
+    )
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    migrator.remove_fields("chat", "share_id")
@@ -0,0 +1,48 @@
+"""Peewee migrations -- 002_add_local_sharing.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    migrator.add_fields(
+        "user", api_key=pw.CharField(max_length=255, null=True, unique=True)
+    )
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    migrator.remove_fields("user", "api_key")
@@ -0,0 +1,46 @@
+"""Peewee migrations -- 002_add_local_sharing.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    migrator.add_fields("chat", archived=pw.BooleanField(default=False))
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    migrator.remove_fields("chat", "archived")
@@ -0,0 +1,77 @@
+"""Peewee migrations -- 002_add_local_sharing.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    # Adding fields created_at and updated_at to the 'chat' table
+    migrator.add_fields(
+        "chat",
+        created_at=pw.DateTimeField(null=True),  # Allow null for transition
+        updated_at=pw.DateTimeField(null=True),  # Allow null for transition
+    )
+
+    # Populate the new fields from an existing 'timestamp' field
+    migrator.sql(
+        "UPDATE chat SET created_at = timestamp, updated_at = timestamp WHERE timestamp IS NOT NULL"
+    )
+
+    # Now that the data has been copied, remove the original 'timestamp' field
+    migrator.remove_fields("chat", "timestamp")
+
+    # Update the fields to be not null now that they are populated
+    migrator.change_fields(
+        "chat",
+        created_at=pw.DateTimeField(null=False),
+        updated_at=pw.DateTimeField(null=False),
+    )
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    # Recreate the timestamp field initially allowing null values for safe transition
+    migrator.add_fields("chat", timestamp=pw.DateTimeField(null=True))
+
+    # Copy the earliest created_at date back into the new timestamp field
+    # This assumes created_at was originally a copy of timestamp
+    migrator.sql("UPDATE chat SET timestamp = created_at")
+
+    # Remove the created_at and updated_at fields
+    migrator.remove_fields("chat", "created_at", "updated_at")
+
+    # Finally, alter the timestamp field to not allow nulls if that was the original setting
+    migrator.change_fields("chat", timestamp=pw.DateTimeField(null=False))
@@ -0,0 +1,21 @@
+# Database Migrations
+
+This directory contains all the database migrations for the web app.
+Migrations are done using the [`peewee-migrate`](https://github.com/klen/peewee_migrate) library.
+
+Migrations are automatically ran at app startup.
+
+## Creating a migration
+
+Have you made a change to the schema of an existing model?
+You will need to create a migration file to ensure that existing databases are updated for backwards compatibility.
+
+1. Have a database file (`webui.db`) that has the old schema prior to any of your changes.
+2. Make your changes to the models.
+3. From the `backend` directory, run the following command:
+   ```bash
+   pw_migrate create --auto --auto-source apps.web.models --database sqlite:///${SQLITE_DB} --directory apps/web/internal/migrations ${MIGRATION_NAME}
+   ```
+   - `$SQLITE_DB` should be the path to the database file.
+   - `$MIGRATION_NAME` should be a descriptive name for the migration.
+4. The migration file will be created in the `apps/web/internal/migrations` directory.
@@ -19,6 +19,8 @@ from config import (
    DEFAULT_USER_ROLE,
    ENABLE_SIGNUP,
    USER_PERMISSIONS,
+    WEBHOOK_URL,
+    WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
 )

 app = FastAPI()
@@ -32,7 +34,8 @@ app.state.DEFAULT_MODELS = DEFAULT_MODELS
 app.state.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
 app.state.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
 app.state.USER_PERMISSIONS = USER_PERMISSIONS
-
+app.state.WEBHOOK_URL = WEBHOOK_URL
+app.state.AUTH_TRUSTED_EMAIL_HEADER = WEBUI_AUTH_TRUSTED_EMAIL_HEADER

 app.add_middleware(
    CORSMiddleware,
@@ -2,6 +2,7 @@ from pydantic import BaseModel
 from typing import List, Union, Optional
 import time
 import uuid
+import logging
 from peewee import *

 from apps.web.models.users import UserModel, Users
@@ -9,6 +10,11 @@ from utils.utils import verify_password

 from apps.web.internal.db import DB

+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 ####################
 # DB MODEL
 ####################
@@ -41,6 +47,10 @@ class Token(BaseModel):
    token_type: str


+class ApiKey(BaseModel):
+    api_key: Optional[str] = None
+
+
 class UserResponse(BaseModel):
    id: str
    email: str
@@ -76,6 +86,7 @@ class SignupForm(BaseModel):
    name: str
    email: str
    password: str
+    profile_image_url: Optional[str] = "/user.png"


 class AuthsTable:
@@ -84,9 +95,14 @@ class AuthsTable:
        self.db.create_tables([Auth])

    def insert_new_auth(
-        self, email: str, password: str, name: str, role: str = "pending"
+        self,
+        email: str,
+        password: str,
+        name: str,
+        profile_image_url: str = "/user.png",
+        role: str = "pending",
    ) -> Optional[UserModel]:
-        print("insert_new_auth")
+        log.info("insert_new_auth")

        id = str(uuid.uuid4())

@@ -95,7 +111,7 @@ class AuthsTable:
        )
        result = Auth.create(**auth.model_dump())

-        user = Users.insert_new_user(id, name, email, role)
+        user = Users.insert_new_user(id, name, email, profile_image_url, role)

        if result and user:
            return user
@@ -103,7 +119,7 @@ class AuthsTable:
            return None

    def authenticate_user(self, email: str, password: str) -> Optional[UserModel]:
-        print("authenticate_user", email)
+        log.info(f"authenticate_user: {email}")
        try:
            auth = Auth.get(Auth.email == email, Auth.active == True)
            if auth:
@@ -117,6 +133,28 @@ class AuthsTable:
        except:
            return None

+    def authenticate_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
+        log.info(f"authenticate_user_by_api_key: {api_key}")
+        # if no api_key, return None
+        if not api_key:
+            return None
+
+        try:
+            user = Users.get_user_by_api_key(api_key)
+            return user if user else None
+        except:
+            return False
+
+    def authenticate_user_by_trusted_header(self, email: str) -> Optional[UserModel]:
+        log.info(f"authenticate_user_by_trusted_header: {email}")
+        try:
+            auth = Auth.get(Auth.email == email, Auth.active == True)
+            if auth:
+                user = Users.get_user_by_id(auth.id)
+                return user
+        except:
+            return None
+
    def update_user_password_by_id(self, id: str, new_password: str) -> bool:
        try:
            query = Auth.update(password=new_password).where(Auth.id == id)
@@ -19,7 +19,12 @@ class Chat(Model):
    user_id = CharField()
    title = CharField()
    chat = TextField()  # Save Chat JSON as Text
-    timestamp = DateField()
+
+    created_at = DateTimeField()
+    updated_at = DateTimeField()
+
+    share_id = CharField(null=True, unique=True)
+    archived = BooleanField(default=False)

    class Meta:
        database = DB
@@ -30,7 +35,12 @@ class ChatModel(BaseModel):
    user_id: str
    title: str
    chat: str
-    timestamp: int  # timestamp in epoch
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+    share_id: Optional[str] = None
+    archived: bool = False


 ####################
@@ -51,12 +61,17 @@ class ChatResponse(BaseModel):
    user_id: str
    title: str
    chat: dict
-    timestamp: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+    created_at: int  # timestamp in epoch
+    share_id: Optional[str] = None  # id of the chat to be shared
+    archived: bool


 class ChatTitleIdResponse(BaseModel):
    id: str
    title: str
+    updated_at: int
+    created_at: int


 class ChatTable:
@@ -74,7 +89,8 @@ class ChatTable:
                    form_data.chat["title"] if "title" in form_data.chat else "New Chat"
                ),
                "chat": json.dumps(form_data.chat),
-                "timestamp": int(time.time()),
+                "created_at": int(time.time()),
+                "updated_at": int(time.time()),
            }
        )

@@ -86,7 +102,7 @@ class ChatTable:
            query = Chat.update(
                chat=json.dumps(chat),
                title=chat["title"] if "title" in chat else "New Chat",
-                timestamp=int(time.time()),
+                updated_at=int(time.time()),
            ).where(Chat.id == id)
            query.execute()

@@ -95,12 +111,64 @@ class ChatTable:
        except:
            return None

-    def update_chat_by_id(self, id: str, chat: dict) -> Optional[ChatModel]:
+    def insert_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
+        # Get the existing chat to share
+        chat = Chat.get(Chat.id == chat_id)
+        # Check if the chat is already shared
+        if chat.share_id:
+            return self.get_chat_by_id_and_user_id(chat.share_id, "shared")
+        # Create a new chat with the same data, but with a new ID
+        shared_chat = ChatModel(
+            **{
+                "id": str(uuid.uuid4()),
+                "user_id": f"shared-{chat_id}",
+                "title": chat.title,
+                "chat": chat.chat,
+                "created_at": chat.created_at,
+                "updated_at": int(time.time()),
+            }
+        )
+        shared_result = Chat.create(**shared_chat.model_dump())
+        # Update the original chat with the share_id
+        result = (
+            Chat.update(share_id=shared_chat.id).where(Chat.id == chat_id).execute()
+        )
+
+        return shared_chat if (shared_result and result) else None
+
+    def update_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
+        try:
+            print("update_shared_chat_by_id")
+            chat = Chat.get(Chat.id == chat_id)
+            print(chat)
+
+            query = Chat.update(
+                title=chat.title,
+                chat=chat.chat,
+            ).where(Chat.id == chat.share_id)
+
+            query.execute()
+
+            chat = Chat.get(Chat.id == chat.share_id)
+            return ChatModel(**model_to_dict(chat))
+        except:
+            return None
+
+    def delete_shared_chat_by_chat_id(self, chat_id: str) -> bool:
+        try:
+            query = Chat.delete().where(Chat.user_id == f"shared-{chat_id}")
+            query.execute()  # Remove the rows, return number of rows removed.
+
+            return True
+        except:
+            return False
+
+    def update_chat_share_id_by_id(
+        self, id: str, share_id: Optional[str]
+    ) -> Optional[ChatModel]:
        try:
            query = Chat.update(
-                chat=json.dumps(chat),
-                title=chat["title"] if "title" in chat else "New Chat",
-                timestamp=int(time.time()),
+                share_id=share_id,
            ).where(Chat.id == id)
            query.execute()

@@ -109,14 +177,42 @@ class ChatTable:
        except:
            return None

+    def toggle_chat_archive_by_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            chat = self.get_chat_by_id(id)
+            query = Chat.update(
+                archived=(not chat.archived),
+            ).where(Chat.id == id)
+
+            query.execute()
+
+            chat = Chat.get(Chat.id == id)
+            return ChatModel(**model_to_dict(chat))
+        except:
+            return None
+
+    def get_archived_chat_lists_by_user_id(
+        self, user_id: str, skip: int = 0, limit: int = 50
+    ) -> List[ChatModel]:
+        return [
+            ChatModel(**model_to_dict(chat))
+            for chat in Chat.select()
+            .where(Chat.archived == True)
+            .where(Chat.user_id == user_id)
+            .order_by(Chat.updated_at.desc())
+            # .limit(limit)
+            # .offset(skip)
+        ]
+
    def get_chat_lists_by_user_id(
        self, user_id: str, skip: int = 0, limit: int = 50
    ) -> List[ChatModel]:
        return [
            ChatModel(**model_to_dict(chat))
            for chat in Chat.select()
+            .where(Chat.archived == False)
            .where(Chat.user_id == user_id)
-            .order_by(Chat.timestamp.desc())
+            .order_by(Chat.updated_at.desc())
            # .limit(limit)
            # .offset(skip)
        ]
@@ -127,14 +223,15 @@ class ChatTable:
        return [
            ChatModel(**model_to_dict(chat))
            for chat in Chat.select()
+            .where(Chat.archived == False)
            .where(Chat.id.in_(chat_ids))
-            .order_by(Chat.timestamp.desc())
+            .order_by(Chat.updated_at.desc())
        ]

    def get_all_chats(self) -> List[ChatModel]:
        return [
            ChatModel(**model_to_dict(chat))
-            for chat in Chat.select().order_by(Chat.timestamp.desc())
+            for chat in Chat.select().order_by(Chat.updated_at.desc())
        ]

    def get_all_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
@@ -142,9 +239,28 @@ class ChatTable:
            ChatModel(**model_to_dict(chat))
            for chat in Chat.select()
            .where(Chat.user_id == user_id)
-            .order_by(Chat.timestamp.desc())
+            .order_by(Chat.updated_at.desc())
        ]

+    def get_chat_by_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            chat = Chat.get(Chat.id == id)
+            return ChatModel(**model_to_dict(chat))
+        except:
+            return None
+
+    def get_chat_by_share_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            chat = Chat.get(Chat.share_id == id)
+
+            if chat:
+                chat = Chat.get(Chat.id == id)
+                return ChatModel(**model_to_dict(chat))
+            else:
+                return None
+        except:
+            return None
+
    def get_chat_by_id_and_user_id(self, id: str, user_id: str) -> Optional[ChatModel]:
        try:
            chat = Chat.get(Chat.id == id, Chat.user_id == user_id)
@@ -163,12 +279,15 @@ class ChatTable:
            query = Chat.delete().where((Chat.id == id) & (Chat.user_id == user_id))
            query.execute()  # Remove the rows, return number of rows removed.

-            return True
+            return True and self.delete_shared_chat_by_chat_id(id)
        except:
            return False

    def delete_chats_by_user_id(self, user_id: str) -> bool:
        try:
+
+            self.delete_shared_chats_by_user_id(user_id)
+
            query = Chat.delete().where(Chat.user_id == user_id)
            query.execute()  # Remove the rows, return number of rows removed.

@@ -176,5 +295,19 @@ class ChatTable:
        except:
            return False

+    def delete_shared_chats_by_user_id(self, user_id: str) -> bool:
+        try:
+            shared_chat_ids = [
+                f"shared-{chat.id}"
+                for chat in Chat.select().where(Chat.user_id == user_id)
+            ]
+
+            query = Chat.delete().where(Chat.user_id << shared_chat_ids)
+            query.execute()  # Remove the rows, return number of rows removed.
+
+            return True
+        except:
+            return False
+

 Chats = ChatTable(DB)
@@ -3,6 +3,7 @@ from peewee import *
 from playhouse.shortcuts import model_to_dict
 from typing import List, Union, Optional
 import time
+import logging

 from utils.utils import decode_token
 from utils.misc import get_gravatar_url
@@ -11,6 +12,11 @@ from apps.web.internal.db import DB

 import json

+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 ####################
 # Documents DB Schema
 ####################
@@ -118,7 +124,7 @@ class DocumentsTable:
            doc = Document.get(Document.name == form_data.name)
            return DocumentModel(**model_to_dict(doc))
        except Exception as e:
-            print(e)
+            log.exception(e)
            return None

    def update_doc_content_by_name(
@@ -138,7 +144,7 @@ class DocumentsTable:
            doc = Document.get(Document.name == name)
            return DocumentModel(**model_to_dict(doc))
        except Exception as e:
-            print(e)
+            log.exception(e)
            return None

    def delete_doc_by_name(self, name: str) -> bool:
@@ -64,8 +64,8 @@ class ModelfilesTable:
        self.db.create_tables([Modelfile])

    def insert_new_modelfile(
-            self, user_id: str,
-            form_data: ModelfileForm) -> Optional[ModelfileModel]:
+        self, user_id: str, form_data: ModelfileForm
+    ) -> Optional[ModelfileModel]:
        if "tagName" in form_data.modelfile:
            modelfile = ModelfileModel(
                **{
@@ -73,7 +73,8 @@ class ModelfilesTable:
                    "tag_name": form_data.modelfile["tagName"],
                    "modelfile": json.dumps(form_data.modelfile),
                    "timestamp": int(time.time()),
-                })
+                }
+            )

            try:
                result = Modelfile.create(**modelfile.model_dump())
@@ -87,29 +88,28 @@ class ModelfilesTable:
        else:
            return None

-    def get_modelfile_by_tag_name(self,
-                                  tag_name: str) -> Optional[ModelfileModel]:
+    def get_modelfile_by_tag_name(self, tag_name: str) -> Optional[ModelfileModel]:
        try:
            modelfile = Modelfile.get(Modelfile.tag_name == tag_name)
            return ModelfileModel(**model_to_dict(modelfile))
        except:
            return None

-    def get_modelfiles(self,
-                       skip: int = 0,
-                       limit: int = 50) -> List[ModelfileResponse]:
+    def get_modelfiles(self, skip: int = 0, limit: int = 50) -> List[ModelfileResponse]:
        return [
            ModelfileResponse(
                **{
                    **model_to_dict(modelfile),
-                    "modelfile":
-                    json.loads(modelfile.modelfile),
-                }) for modelfile in Modelfile.select()
+                    "modelfile": json.loads(modelfile.modelfile),
+                }
+            )
+            for modelfile in Modelfile.select()
            # .limit(limit).offset(skip)
        ]

    def update_modelfile_by_tag_name(
-            self, tag_name: str, modelfile: dict) -> Optional[ModelfileModel]:
+        self, tag_name: str, modelfile: dict
+    ) -> Optional[ModelfileModel]:
        try:
            query = Modelfile.update(
                modelfile=json.dumps(modelfile),
@@ -52,8 +52,9 @@ class PromptsTable:
        self.db = db
        self.db.create_tables([Prompt])

-    def insert_new_prompt(self, user_id: str,
-                          form_data: PromptForm) -> Optional[PromptModel]:
+    def insert_new_prompt(
+        self, user_id: str, form_data: PromptForm
+    ) -> Optional[PromptModel]:
        prompt = PromptModel(
            **{
                "user_id": user_id,
@@ -61,7 +62,8 @@ class PromptsTable:
                "title": form_data.title,
                "content": form_data.content,
                "timestamp": int(time.time()),
-            })
+            }
+        )

        try:
            result = Prompt.create(**prompt.model_dump())
@@ -81,13 +83,14 @@ class PromptsTable:

    def get_prompts(self) -> List[PromptModel]:
        return [
-            PromptModel(**model_to_dict(prompt)) for prompt in Prompt.select()
+            PromptModel(**model_to_dict(prompt))
+            for prompt in Prompt.select()
            # .limit(limit).offset(skip)
        ]

    def update_prompt_by_command(
-            self, command: str,
-            form_data: PromptForm) -> Optional[PromptModel]:
+        self, command: str, form_data: PromptForm
+    ) -> Optional[PromptModel]:
        try:
            query = Prompt.update(
                title=form_data.title,
@@ -6,9 +6,15 @@ from playhouse.shortcuts import model_to_dict
 import json
 import uuid
 import time
+import logging

 from apps.web.internal.db import DB

+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 ####################
 # Tag DB Schema
 ####################
@@ -173,7 +179,7 @@ class TagTable:
                (ChatIdTag.tag_name == tag_name) & (ChatIdTag.user_id == user_id)
            )
            res = query.execute()  # Remove the rows, return number of rows removed.
-            print(res)
+            log.debug(f"res: {res}")

            tag_count = self.count_chat_ids_by_tag_name_and_user_id(tag_name, user_id)
            if tag_count == 0:
@@ -185,7 +191,7 @@ class TagTable:

            return True
        except Exception as e:
-            print("delete_tag", e)
+            log.error(f"delete_tag: {e}")
            return False

    def delete_tag_by_tag_name_and_chat_id_and_user_id(
@@ -198,7 +204,7 @@ class TagTable:
                & (ChatIdTag.user_id == user_id)
            )
            res = query.execute()  # Remove the rows, return number of rows removed.
-            print(res)
+            log.debug(f"res: {res}")

            tag_count = self.count_chat_ids_by_tag_name_and_user_id(tag_name, user_id)
            if tag_count == 0:
@@ -210,7 +216,7 @@ class TagTable:

            return True
        except Exception as e:
-            print("delete_tag", e)
+            log.error(f"delete_tag: {e}")
            return False

    def delete_tags_by_chat_id_and_user_id(self, chat_id: str, user_id: str) -> bool:
@@ -20,6 +20,7 @@ class User(Model):
    role = CharField()
    profile_image_url = CharField()
    timestamp = DateField()
+    api_key = CharField(null=True, unique=True)

    class Meta:
        database = DB
@@ -30,8 +31,9 @@ class UserModel(BaseModel):
    name: str
    email: str
    role: str = "pending"
-    profile_image_url: str = "/user.png"
+    profile_image_url: str
    timestamp: int  # timestamp in epoch
+    api_key: Optional[str] = None


 ####################
@@ -57,7 +59,12 @@ class UsersTable:
        self.db.create_tables([User])

    def insert_new_user(
-        self, id: str, name: str, email: str, role: str = "pending"
+        self,
+        id: str,
+        name: str,
+        email: str,
+        profile_image_url: str = "/user.png",
+        role: str = "pending",
    ) -> Optional[UserModel]:
        user = UserModel(
            **{
@@ -65,7 +72,7 @@ class UsersTable:
                "name": name,
                "email": email,
                "role": role,
-                "profile_image_url": "/user.png",
+                "profile_image_url": profile_image_url,
                "timestamp": int(time.time()),
            }
        )
@@ -82,6 +89,13 @@ class UsersTable:
        except:
            return None

+    def get_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
+        try:
+            user = User.get(User.api_key == api_key)
+            return UserModel(**model_to_dict(user))
+        except:
+            return None
+
    def get_user_by_email(self, email: str) -> Optional[UserModel]:
        try:
            user = User.get(User.email == email)
@@ -149,5 +163,21 @@ class UsersTable:
        except:
            return False

+    def update_user_api_key_by_id(self, id: str, api_key: str) -> str:
+        try:
+            query = User.update(api_key=api_key).where(User.id == id)
+            result = query.execute()
+
+            return True if result == 1 else False
+        except:
+            return False
+
+    def get_user_api_key_by_id(self, id: str) -> Optional[str]:
+        try:
+            user = User.get(User.id == id)
+            return user.api_key
+        except:
+            return None
+

 Users = UsersTable(DB)
@@ -1,13 +1,10 @@
-from fastapi import Response, Request
-from fastapi import Depends, FastAPI, HTTPException, status
-from datetime import datetime, timedelta
-from typing import List, Union
+from fastapi import Request
+from fastapi import Depends, HTTPException, status

-from fastapi import APIRouter, status
+from fastapi import APIRouter
 from pydantic import BaseModel
-import time
-import uuid
 import re
+import uuid

 from apps.web.models.auths import (
    SigninForm,
@@ -17,6 +14,7 @@ from apps.web.models.auths import (
    UserResponse,
    SigninResponse,
    Auths,
+    ApiKey,
 )
 from apps.web.models.users import Users

@@ -25,9 +23,12 @@ from utils.utils import (
    get_current_user,
    get_admin_user,
    create_token,
+    create_api_key,
 )
 from utils.misc import parse_duration, validate_email_format
-from constants import ERROR_MESSAGES
+from utils.webhook import post_webhook
+from constants import ERROR_MESSAGES, WEBHOOK_MESSAGES
+from config import WEBUI_AUTH_TRUSTED_EMAIL_HEADER

 router = APIRouter()

@@ -78,6 +79,8 @@ async def update_profile(
 async def update_password(
    form_data: UpdatePasswordForm, session_user=Depends(get_current_user)
 ):
+    if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
+        raise HTTPException(400, detail=ERROR_MESSAGES.ACTION_PROHIBITED)
    if session_user:
        user = Auths.authenticate_user(session_user.email, form_data.password)

@@ -97,7 +100,22 @@ async def update_password(

@router.post("/signin", response_model=SigninResponse)
 async def signin(request: Request, form_data: SigninForm):
-    user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
+    if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
+        if WEBUI_AUTH_TRUSTED_EMAIL_HEADER not in request.headers:
+            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_TRUSTED_HEADER)
+
+        trusted_email = request.headers[WEBUI_AUTH_TRUSTED_EMAIL_HEADER].lower()
+        if not Users.get_user_by_email(trusted_email.lower()):
+            await signup(
+                request,
+                SignupForm(
+                    email=trusted_email, password=str(uuid.uuid4()), name=trusted_email
+                ),
+            )
+        user = Auths.authenticate_user_by_trusted_header(trusted_email)
+    else:
+        user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
+
    if user:
        token = create_token(
            data={"id": user.id},
@@ -145,7 +163,11 @@ async def signup(request: Request, form_data: SignupForm):
        )
        hashed = get_password_hash(form_data.password)
        user = Auths.insert_new_auth(
-            form_data.email.lower(), hashed, form_data.name, role
+            form_data.email.lower(),
+            hashed,
+            form_data.name,
+            form_data.profile_image_url,
+            role,
        )

        if user:
@@ -155,6 +177,17 @@ async def signup(request: Request, form_data: SignupForm):
            )
            # response.set_cookie(key='token', value=token, httponly=True)

+            if request.app.state.WEBHOOK_URL:
+                post_webhook(
+                    request.app.state.WEBHOOK_URL,
+                    WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
+                    {
+                        "action": "signup",
+                        "message": WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
+                        "user": user.model_dump_json(exclude_none=True),
+                    },
+                )
+
            return {
                "token": token,
                "token_type": "Bearer",
@@ -237,3 +270,40 @@ async def update_token_expires_duration(
        return request.app.state.JWT_EXPIRES_IN
    else:
        return request.app.state.JWT_EXPIRES_IN
+
+
+############################
+# API Key
+############################
+
+
+# create api key
+@router.post("/api_key", response_model=ApiKey)
+async def create_api_key_(user=Depends(get_current_user)):
+    api_key = create_api_key()
+    success = Users.update_user_api_key_by_id(user.id, api_key)
+    if success:
+        return {
+            "api_key": api_key,
+        }
+    else:
+        raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_API_KEY_ERROR)
+
+
+# delete api key
+@router.delete("/api_key", response_model=bool)
+async def delete_api_key(user=Depends(get_current_user)):
+    success = Users.update_user_api_key_by_id(user.id, None)
+    return success
+
+
+# get api key
+@router.get("/api_key", response_model=ApiKey)
+async def get_api_key(user=Depends(get_current_user)):
+    api_key = Users.get_user_api_key_by_id(user.id)
+    if api_key:
+        return {
+            "api_key": api_key,
+        }
+    else:
+        raise HTTPException(404, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
@@ -5,6 +5,7 @@ from utils.utils import get_current_user, get_admin_user
 from fastapi import APIRouter
 from pydantic import BaseModel
 import json
+import logging

 from apps.web.models.users import Users
 from apps.web.models.chats import (
@@ -27,6 +28,11 @@ from apps.web.models.tags import (

 from constants import ERROR_MESSAGES

+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 router = APIRouter()

 ############################
@@ -41,6 +47,18 @@ async def get_user_chats(
    return Chats.get_chat_lists_by_user_id(user.id, skip, limit)


+############################
+# GetArchivedChats
+############################
+
+
+@router.get("/archived", response_model=List[ChatTitleIdResponse])
+async def get_archived_user_chats(
+    user=Depends(get_current_user), skip: int = 0, limit: int = 50
+):
+    return Chats.get_archived_chat_lists_by_user_id(user.id, skip, limit)
+
+
 ############################
 # GetAllChats
 ############################
@@ -78,7 +96,7 @@ async def create_new_chat(form_data: ChatForm, user=Depends(get_current_user)):
        chat = Chats.insert_new_chat(user.id, form_data)
        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
    except Exception as e:
-        print(e)
+        log.exception(e)
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
        )
@@ -95,7 +113,7 @@ async def get_all_tags(user=Depends(get_current_user)):
        tags = Tags.get_tags_by_user_id(user.id)
        return tags
    except Exception as e:
-        print(e)
+        log.exception(e)
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
        )
@@ -183,6 +201,103 @@ async def delete_chat_by_id(request: Request, id: str, user=Depends(get_current_
    return result


+############################
+# ArchiveChat
+############################
+
+
+@router.get("/{id}/archive", response_model=Optional[ChatResponse])
+async def archive_chat_by_id(id: str, user=Depends(get_current_user)):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        chat = Chats.toggle_chat_archive_by_id(id)
+        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
+############################
+# ShareChatById
+############################
+
+
+@router.post("/{id}/share", response_model=Optional[ChatResponse])
+async def share_chat_by_id(id: str, user=Depends(get_current_user)):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        if chat.share_id:
+            shared_chat = Chats.update_shared_chat_by_chat_id(chat.id)
+            return ChatResponse(
+                **{**shared_chat.model_dump(), "chat": json.loads(shared_chat.chat)}
+            )
+
+        shared_chat = Chats.insert_shared_chat_by_chat_id(chat.id)
+        if not shared_chat:
+            raise HTTPException(
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                detail=ERROR_MESSAGES.DEFAULT(),
+            )
+
+        return ChatResponse(
+            **{**shared_chat.model_dump(), "chat": json.loads(shared_chat.chat)}
+        )
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+
+############################
+# DeletedSharedChatById
+############################
+
+
+@router.delete("/{id}/share", response_model=Optional[bool])
+async def delete_shared_chat_by_id(id: str, user=Depends(get_current_user)):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        if not chat.share_id:
+            return False
+
+        result = Chats.delete_shared_chat_by_chat_id(id)
+        update_result = Chats.update_chat_share_id_by_id(id, None)
+
+        return result and update_result != None
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+
+############################
+# GetSharedChatById
+############################
+
+
+@router.get("/share/{share_id}", response_model=Optional[ChatResponse])
+async def get_shared_chat_by_id(share_id: str, user=Depends(get_current_user)):
+    if user.role == "pending":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
+    if user.role == "user":
+        chat = Chats.get_chat_by_share_id(share_id)
+    elif user.role == "admin":
+        chat = Chats.get_chat_by_id(share_id)
+
+    if chat:
+        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
+
 ############################
 # GetChatTagsById
 ############################
@@ -10,7 +10,12 @@ import uuid

 from apps.web.models.users import Users

-from utils.utils import get_password_hash, get_current_user, get_admin_user, create_token
+from utils.utils import (
+    get_password_hash,
+    get_current_user,
+    get_admin_user,
+    create_token,
+)
 from utils.misc import get_gravatar_url, validate_email_format
 from constants import ERROR_MESSAGES

@@ -43,7 +48,6 @@ async def set_global_default_models(
    return request.app.state.DEFAULT_MODELS


-
@router.post("/default/suggestions", response_model=List[PromptSuggestion])
 async def set_global_default_suggestions(
    request: Request,
@@ -24,9 +24,9 @@ router = APIRouter()


@router.get("/", response_model=List[ModelfileResponse])
-async def get_modelfiles(skip: int = 0,
-                         limit: int = 50,
-                         user=Depends(get_current_user)):
+async def get_modelfiles(
+    skip: int = 0, limit: int = 50, user=Depends(get_current_user)
+):
    return Modelfiles.get_modelfiles(skip, limit)


@@ -36,17 +36,16 @@ async def get_modelfiles(skip: int = 0,


@router.post("/create", response_model=Optional[ModelfileResponse])
-async def create_new_modelfile(form_data: ModelfileForm,
-                               user=Depends(get_admin_user)):
+async def create_new_modelfile(form_data: ModelfileForm, user=Depends(get_admin_user)):
    modelfile = Modelfiles.insert_new_modelfile(user.id, form_data)

    if modelfile:
        return ModelfileResponse(
            **{
                **modelfile.model_dump(),
-                "modelfile":
-                json.loads(modelfile.modelfile),
-            })
+                "modelfile": json.loads(modelfile.modelfile),
+            }
+        )
    else:
        raise HTTPException(
            status_code=status.HTTP_401_UNAUTHORIZED,
@@ -60,17 +59,18 @@ async def create_new_modelfile(form_data: ModelfileForm,


@router.post("/", response_model=Optional[ModelfileResponse])
-async def get_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
-                                    user=Depends(get_current_user)):
+async def get_modelfile_by_tag_name(
+    form_data: ModelfileTagNameForm, user=Depends(get_current_user)
+):
    modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)

    if modelfile:
        return ModelfileResponse(
            **{
                **modelfile.model_dump(),
-                "modelfile":
-                json.loads(modelfile.modelfile),
-            })
+                "modelfile": json.loads(modelfile.modelfile),
+            }
+        )
    else:
        raise HTTPException(
            status_code=status.HTTP_401_UNAUTHORIZED,
@@ -84,8 +84,9 @@ async def get_modelfile_by_tag_name(form_data: ModelfileTagNameForm,


@router.post("/update", response_model=Optional[ModelfileResponse])
-async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,
-                                       user=Depends(get_admin_user)):
+async def update_modelfile_by_tag_name(
+    form_data: ModelfileUpdateForm, user=Depends(get_admin_user)
+):
    modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)
    if modelfile:
        updated_modelfile = {
@@ -94,14 +95,15 @@ async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,
        }

        modelfile = Modelfiles.update_modelfile_by_tag_name(
-            form_data.tag_name, updated_modelfile)
+            form_data.tag_name, updated_modelfile
+        )

        return ModelfileResponse(
            **{
                **modelfile.model_dump(),
-                "modelfile":
-                json.loads(modelfile.modelfile),
-            })
+                "modelfile": json.loads(modelfile.modelfile),
+            }
+        )
    else:
        raise HTTPException(
            status_code=status.HTTP_401_UNAUTHORIZED,
@@ -115,7 +117,8 @@ async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,


@router.delete("/delete", response_model=bool)
-async def delete_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
-                                       user=Depends(get_admin_user)):
+async def delete_modelfile_by_tag_name(
+    form_data: ModelfileTagNameForm, user=Depends(get_admin_user)
+):
    result = Modelfiles.delete_modelfile_by_tag_name(form_data.tag_name)
    return result
@@ -7,6 +7,7 @@ from fastapi import APIRouter
 from pydantic import BaseModel
 import time
 import uuid
+import logging

 from apps.web.models.users import UserModel, UserUpdateForm, UserRoleUpdateForm, Users
 from apps.web.models.auths import Auths
@@ -14,6 +15,11 @@ from apps.web.models.auths import Auths
 from utils.utils import get_current_user, get_password_hash, get_admin_user
 from constants import ERROR_MESSAGES

+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 router = APIRouter()

 ############################
@@ -83,7 +89,7 @@ async def update_user_by_id(

        if form_data.password:
            hashed = get_password_hash(form_data.password)
-            print(hashed)
+            log.debug(f"hashed: {hashed}")
            Auths.update_user_password_by_id(user_id, hashed)

        Auths.update_email_by_id(user_id, form_data.email.lower())
@@ -1,14 +1,11 @@
-from fastapi import APIRouter, UploadFile, File, BackgroundTasks
+from fastapi import APIRouter, UploadFile, File, Response
 from fastapi import Depends, HTTPException, status
 from starlette.responses import StreamingResponse, FileResponse
-
-
 from pydantic import BaseModel

-import requests
-import os
-import aiohttp
-import json
+
+from fpdf import FPDF
+import markdown


 from utils.utils import get_admin_user
@@ -16,160 +13,11 @@ from utils.misc import calculate_sha256, get_gravatar_url

 from config import OLLAMA_BASE_URLS, DATA_DIR, UPLOAD_DIR
 from constants import ERROR_MESSAGES
-
+from typing import List

 router = APIRouter()


-class UploadBlobForm(BaseModel):
-    filename: str
-
-
-from urllib.parse import urlparse
-
-
-def parse_huggingface_url(hf_url):
-    try:
-        # Parse the URL
-        parsed_url = urlparse(hf_url)
-
-        # Get the path and split it into components
-        path_components = parsed_url.path.split("/")
-
-        # Extract the desired output
-        user_repo = "/".join(path_components[1:3])
-        model_file = path_components[-1]
-
-        return model_file
-    except ValueError:
-        return None
-
-
-async def download_file_stream(url, file_path, file_name, chunk_size=1024 * 1024):
-    done = False
-
-    if os.path.exists(file_path):
-        current_size = os.path.getsize(file_path)
-    else:
-        current_size = 0
-
-    headers = {"Range": f"bytes={current_size}-"} if current_size > 0 else {}
-
-    timeout = aiohttp.ClientTimeout(total=600)  # Set the timeout
-
-    async with aiohttp.ClientSession(timeout=timeout) as session:
-        async with session.get(url, headers=headers) as response:
-            total_size = int(response.headers.get("content-length", 0)) + current_size
-
-            with open(file_path, "ab+") as file:
-                async for data in response.content.iter_chunked(chunk_size):
-                    current_size += len(data)
-                    file.write(data)
-
-                    done = current_size == total_size
-                    progress = round((current_size / total_size) * 100, 2)
-                    yield f'data: {{"progress": {progress}, "completed": {current_size}, "total": {total_size}}}\n\n'
-
-                if done:
-                    file.seek(0)
-                    hashed = calculate_sha256(file)
-                    file.seek(0)
-
-                    url = f"{OLLAMA_BASE_URLS[0]}/blobs/sha256:{hashed}"
-                    response = requests.post(url, data=file)
-
-                    if response.ok:
-                        res = {
-                            "done": done,
-                            "blob": f"sha256:{hashed}",
-                            "name": file_name,
-                        }
-                        os.remove(file_path)
-
-                        yield f"data: {json.dumps(res)}\n\n"
-                    else:
-                        raise "Ollama: Could not create blob, Please try again."
-
-
-@router.get("/download")
-async def download(
-    url: str,
-):
-    # url = "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q2_K.gguf"
-    file_name = parse_huggingface_url(url)
-
-    if file_name:
-        file_path = f"{UPLOAD_DIR}/{file_name}"
-
-        return StreamingResponse(
-            download_file_stream(url, file_path, file_name),
-            media_type="text/event-stream",
-        )
-    else:
-        return None
-
-
-@router.post("/upload")
-def upload(file: UploadFile = File(...)):
-    file_path = f"{UPLOAD_DIR}/{file.filename}"
-
-    # Save file in chunks
-    with open(file_path, "wb+") as f:
-        for chunk in file.file:
-            f.write(chunk)
-
-    def file_process_stream():
-        total_size = os.path.getsize(file_path)
-        chunk_size = 1024 * 1024
-        try:
-            with open(file_path, "rb") as f:
-                total = 0
-                done = False
-
-                while not done:
-                    chunk = f.read(chunk_size)
-                    if not chunk:
-                        done = True
-                        continue
-
-                    total += len(chunk)
-                    progress = round((total / total_size) * 100, 2)
-
-                    res = {
-                        "progress": progress,
-                        "total": total_size,
-                        "completed": total,
-                    }
-                    yield f"data: {json.dumps(res)}\n\n"
-
-                if done:
-                    f.seek(0)
-                    hashed = calculate_sha256(f)
-                    f.seek(0)
-
-                    url = f"{OLLAMA_BASE_URLS[0]}/blobs/sha256:{hashed}"
-                    response = requests.post(url, data=f)
-
-                    if response.ok:
-                        res = {
-                            "done": done,
-                            "blob": f"sha256:{hashed}",
-                            "name": file.filename,
-                        }
-                        os.remove(file_path)
-                        yield f"data: {json.dumps(res)}\n\n"
-                    else:
-                        raise Exception(
-                            "Ollama: Could not create blob, Please try again."
-                        )
-
-        except Exception as e:
-            res = {"error": str(e)}
-            yield f"data: {json.dumps(res)}\n\n"
-
-    return StreamingResponse(file_process_stream(), media_type="text/event-stream")
-
-
@router.get("/gravatar")
 async def get_gravatar(
    email: str,
@@ -177,6 +25,70 @@ async def get_gravatar(
    return get_gravatar_url(email)


+class MarkdownForm(BaseModel):
+    md: str
+
+
+@router.post("/markdown")
+async def get_html_from_markdown(
+    form_data: MarkdownForm,
+):
+    return {"html": markdown.markdown(form_data.md)}
+
+
+class ChatForm(BaseModel):
+    title: str
+    messages: List[dict]
+
+
+@router.post("/pdf")
+async def download_chat_as_pdf(
+    form_data: ChatForm,
+):
+    pdf = FPDF()
+    pdf.add_page()
+
+    STATIC_DIR = "./static"
+    FONTS_DIR = f"{STATIC_DIR}/fonts"
+
+    pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
+    pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")
+    pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf")
+    pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf")
+    pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf")
+
+    pdf.set_font("NotoSans", size=12)
+    pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP"])
+
+    pdf.set_auto_page_break(auto=True, margin=15)
+
+    # Adjust the effective page width for multi_cell
+    effective_page_width = (
+        pdf.w - 2 * pdf.l_margin - 10
+    )  # Subtracted an additional 10 for extra padding
+
+    # Add chat messages
+    for message in form_data.messages:
+        role = message["role"]
+        content = message["content"]
+        pdf.set_font("NotoSans", "B", size=14)  # Bold for the role
+        pdf.multi_cell(effective_page_width, 10, f"{role.upper()}", 0, "L")
+        pdf.ln(1)  # Extra space between messages
+
+        pdf.set_font("NotoSans", size=10)  # Regular for content
+        pdf.multi_cell(effective_page_width, 6, content, 0, "L")
+        pdf.ln(1.5)  # Extra space between messages
+
+    # Save the pdf with name .pdf
+    pdf_bytes = pdf.output()
+
+    return Response(
+        content=bytes(pdf_bytes),
+        media_type="application/pdf",
+        headers={"Content-Disposition": f"attachment;filename=chat.pdf"},
+    )
+
+
@router.get("/db/download")
 async def download_db(user=Depends(get_admin_user)):

@@ -1,4 +1,6 @@
 import os
+import sys
+import logging
 import chromadb
 from chromadb import Settings
 from base64 import b64encode
@@ -16,15 +18,60 @@ from secrets import token_bytes
 from constants import ERROR_MESSAGES


+####################################
+# LOGGING
+####################################
+
+log_levels = ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]
+
+GLOBAL_LOG_LEVEL = os.environ.get("GLOBAL_LOG_LEVEL", "").upper()
+if GLOBAL_LOG_LEVEL in log_levels:
+    logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL, force=True)
+else:
+    GLOBAL_LOG_LEVEL = "INFO"
+
+log = logging.getLogger(__name__)
+log.info(f"GLOBAL_LOG_LEVEL: {GLOBAL_LOG_LEVEL}")
+
+log_sources = [
+    "AUDIO",
+    "COMFYUI",
+    "CONFIG",
+    "DB",
+    "IMAGES",
+    "LITELLM",
+    "MAIN",
+    "MODELS",
+    "OLLAMA",
+    "OPENAI",
+    "RAG",
+    "WEBHOOK",
+]
+
+SRC_LOG_LEVELS = {}
+
+for source in log_sources:
+    log_env_var = source + "_LOG_LEVEL"
+    SRC_LOG_LEVELS[source] = os.environ.get(log_env_var, "").upper()
+    if SRC_LOG_LEVELS[source] not in log_levels:
+        SRC_LOG_LEVELS[source] = GLOBAL_LOG_LEVEL
+    log.info(f"{log_env_var}: {SRC_LOG_LEVELS[source]}")
+
+log.setLevel(SRC_LOG_LEVELS["CONFIG"])
+
+####################################
+# Load .env file
+####################################
+
 try:
    from dotenv import load_dotenv, find_dotenv

    load_dotenv(find_dotenv("../.env"))
 except ImportError:
-    print("dotenv not installed, skipping...")
+    log.warning("dotenv not installed, skipping...")

-WEBUI_NAME = "Open WebUI"
-shutil.copyfile("../build/favicon.png", "./static/favicon.png")
+WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
+WEBUI_FAVICON_URL = "https://openwebui.com/favicon.png"

 ####################################
 # ENV (dev,test,prod)
@@ -99,36 +146,6 @@ for version in soup.find_all("h2"):

 CHANGELOG = changelog_json

-
-####################################
-# CUSTOM_NAME
-####################################
-
-CUSTOM_NAME = os.environ.get("CUSTOM_NAME", "")
-if CUSTOM_NAME:
-    try:
-        r = requests.get(f"https://api.openwebui.com/api/v1/custom/{CUSTOM_NAME}")
-        data = r.json()
-        if r.ok:
-            if "logo" in data:
-                url = (
-                    f"https://api.openwebui.com{data['logo']}"
-                    if data["logo"][0] == "/"
-                    else data["logo"]
-                )
-
-                r = requests.get(url, stream=True)
-                if r.status_code == 200:
-                    with open("./static/favicon.png", "wb") as f:
-                        r.raw.decode_content = True
-                        shutil.copyfileobj(r.raw, f)
-
-            WEBUI_NAME = data["name"]
-    except Exception as e:
-        print(e)
-        pass
-
-
 ####################################
 # DATA/FRONTEND BUILD DIR
 ####################################
@@ -142,6 +159,47 @@ try:
 except:
    CONFIG_DATA = {}

+####################################
+# Static DIR
+####################################
+
+STATIC_DIR = str(Path(os.getenv("STATIC_DIR", "./static")).resolve())
+
+shutil.copyfile(f"{FRONTEND_BUILD_DIR}/favicon.png", f"{STATIC_DIR}/favicon.png")
+
+####################################
+# CUSTOM_NAME
+####################################
+
+CUSTOM_NAME = os.environ.get("CUSTOM_NAME", "")
+
+if CUSTOM_NAME:
+    try:
+        r = requests.get(f"https://api.openwebui.com/api/v1/custom/{CUSTOM_NAME}")
+        data = r.json()
+        if r.ok:
+            if "logo" in data:
+                WEBUI_FAVICON_URL = url = (
+                    f"https://api.openwebui.com{data['logo']}"
+                    if data["logo"][0] == "/"
+                    else data["logo"]
+                )
+
+                r = requests.get(url, stream=True)
+                if r.status_code == 200:
+                    with open(f"{STATIC_DIR}/favicon.png", "wb") as f:
+                        r.raw.decode_content = True
+                        shutil.copyfileobj(r.raw, f)
+
+            WEBUI_NAME = data["name"]
+    except Exception as e:
+        log.exception(e)
+        pass
+else:
+    if WEBUI_NAME != "Open WebUI":
+        WEBUI_NAME += " (Open WebUI)"
+
+
 ####################################
 # File Upload DIR
 ####################################
@@ -194,9 +252,9 @@ def create_config_file(file_path):
 LITELLM_CONFIG_PATH = f"{DATA_DIR}/litellm/config.yaml"

 if not os.path.exists(LITELLM_CONFIG_PATH):
-    print("Config file doesn't exist. Creating...")
+    log.info("Config file doesn't exist. Creating...")
    create_config_file(LITELLM_CONFIG_PATH)
-    print("Config file created successfully.")
+    log.info("Config file created successfully.")


 ####################################
@@ -208,11 +266,8 @@ OLLAMA_API_BASE_URL = os.environ.get(
 )

 OLLAMA_BASE_URL = os.environ.get("OLLAMA_BASE_URL", "")
-
-if ENV == "prod":
-    if OLLAMA_BASE_URL == "/ollama":
-        OLLAMA_BASE_URL = "http://host.docker.internal:11434"
-
+K8S_FLAG = os.environ.get("K8S_FLAG", "")
+USE_OLLAMA_DOCKER = os.environ.get("USE_OLLAMA_DOCKER", "false")

 if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
    OLLAMA_BASE_URL = (
@@ -221,6 +276,18 @@ if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
        else OLLAMA_API_BASE_URL
    )

+if ENV == "prod":
+    if OLLAMA_BASE_URL == "/ollama" and not K8S_FLAG:
+        if USE_OLLAMA_DOCKER.lower() == "true":
+            # if you use all-in-one docker container (Open WebUI + Ollama)
+            # with the docker build arg USE_OLLAMA=true (--build-arg="USE_OLLAMA=true") this only works with http://localhost:11434
+            OLLAMA_BASE_URL = "http://localhost:11434"
+        else:
+            OLLAMA_BASE_URL = "http://host.docker.internal:11434"
+    elif K8S_FLAG:
+        OLLAMA_BASE_URL = "http://ollama-service.open-webui.svc.cluster.local:11434"
+
+
 OLLAMA_BASE_URLS = os.environ.get("OLLAMA_BASE_URLS", "")
 OLLAMA_BASE_URLS = OLLAMA_BASE_URLS if OLLAMA_BASE_URLS != "" else OLLAMA_BASE_URL

@@ -234,8 +301,6 @@ OLLAMA_BASE_URLS = [url.strip() for url in OLLAMA_BASE_URLS.split(";")]
 OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "")
 OPENAI_API_BASE_URL = os.environ.get("OPENAI_API_BASE_URL", "")

-if OPENAI_API_KEY == "":
-    OPENAI_API_KEY = "none"

 if OPENAI_API_BASE_URL == "":
    OPENAI_API_BASE_URL = "https://api.openai.com/v1"
@@ -251,7 +316,16 @@ OPENAI_API_BASE_URLS = (
    OPENAI_API_BASE_URLS if OPENAI_API_BASE_URLS != "" else OPENAI_API_BASE_URL
 )

-OPENAI_API_BASE_URLS = [url.strip() for url in OPENAI_API_BASE_URL.split(";")]
+OPENAI_API_BASE_URLS = [
+    url.strip() if url != "" else "https://api.openai.com/v1"
+    for url in OPENAI_API_BASE_URLS.split(";")
+]
+
+OPENAI_API_KEY = ""
+OPENAI_API_KEY = OPENAI_API_KEYS[
+    OPENAI_API_BASE_URLS.index("https://api.openai.com/v1")
+]
+OPENAI_API_BASE_URL = "https://api.openai.com/v1"


 ####################################
@@ -289,8 +363,19 @@ DEFAULT_PROMPT_SUGGESTIONS = (


 DEFAULT_USER_ROLE = os.getenv("DEFAULT_USER_ROLE", "pending")
-USER_PERMISSIONS = {"chat": {"deletion": True}}

+USER_PERMISSIONS_CHAT_DELETION = (
+    os.environ.get("USER_PERMISSIONS_CHAT_DELETION", "True").lower() == "true"
+)
+
+USER_PERMISSIONS = {"chat": {"deletion": USER_PERMISSIONS_CHAT_DELETION}}
+
+
+MODEL_FILTER_ENABLED = os.environ.get("MODEL_FILTER_ENABLED", "False").lower() == "true"
+MODEL_FILTER_LIST = os.environ.get("MODEL_FILTER_LIST", "")
+MODEL_FILTER_LIST = [model.strip() for model in MODEL_FILTER_LIST.split(";")]
+
+WEBHOOK_URL = os.environ.get("WEBHOOK_URL", "")

 ####################################
 # WEBUI_VERSION
@@ -303,6 +388,9 @@ WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.100")
 ####################################

 WEBUI_AUTH = True
+WEBUI_AUTH_TRUSTED_EMAIL_HEADER = os.environ.get(
+    "WEBUI_AUTH_TRUSTED_EMAIL_HEADER", None
+)

 ####################################
 # WEBUI_SECRET_KEY
@@ -324,11 +412,26 @@ if WEBUI_AUTH and WEBUI_SECRET_KEY == "":

 CHROMA_DATA_PATH = f"{DATA_DIR}/vector_db"
 # this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (all-MiniLM-L6-v2)
+
+RAG_EMBEDDING_ENGINE = os.environ.get("RAG_EMBEDDING_ENGINE", "")
+
 RAG_EMBEDDING_MODEL = os.environ.get("RAG_EMBEDDING_MODEL", "all-MiniLM-L6-v2")
-# device type ebbeding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
-RAG_EMBEDDING_MODEL_DEVICE_TYPE = os.environ.get(
-    "RAG_EMBEDDING_MODEL_DEVICE_TYPE", "cpu"
+log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL}"),
+
+RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
+    os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
 )
+
+
+# device type embedding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
+USE_CUDA = os.environ.get("USE_CUDA_DOCKER", "false")
+
+if USE_CUDA.lower() == "true":
+    DEVICE_TYPE = "cuda"
+else:
+    DEVICE_TYPE = "cpu"
+
+
 CHROMA_CLIENT = chromadb.PersistentClient(
    path=CHROMA_DATA_PATH,
    settings=Settings(allow_reset=True, anonymized_telemetry=False),
@@ -351,16 +454,34 @@ And answer according to the language of the user's question.
 Given the context information, answer the query.
 Query: [query]"""

+RAG_OPENAI_API_BASE_URL = os.getenv("RAG_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL)
+RAG_OPENAI_API_KEY = os.getenv("RAG_OPENAI_API_KEY", OPENAI_API_KEY)
+
 ####################################
 # Transcribe
 ####################################

 WHISPER_MODEL = os.getenv("WHISPER_MODEL", "base")
 WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
+WHISPER_MODEL_AUTO_UPDATE = (
+    os.environ.get("WHISPER_MODEL_AUTO_UPDATE", "").lower() == "true"
+)


 ####################################
 # Images
 ####################################

+ENABLE_IMAGE_GENERATION = (
+    os.environ.get("ENABLE_IMAGE_GENERATION", "").lower() == "true"
+)
 AUTOMATIC1111_BASE_URL = os.getenv("AUTOMATIC1111_BASE_URL", "")
+COMFYUI_BASE_URL = os.getenv("COMFYUI_BASE_URL", "")
+
+
+####################################
+# Audio
+####################################
+
+AUDIO_OPENAI_API_BASE_URL = os.getenv("AUDIO_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL)
+AUDIO_OPENAI_API_KEY = os.getenv("AUDIO_OPENAI_API_KEY", OPENAI_API_KEY)
@@ -5,6 +5,13 @@ class MESSAGES(str, Enum):
    DEFAULT = lambda msg="": f"{msg if msg else ''}"


+class WEBHOOK_MESSAGES(str, Enum):
+    DEFAULT = lambda msg="": f"{msg if msg else ''}"
+    USER_SIGNUP = lambda username="": (
+        f"New user signed up: {username}" if username else "New user signed up"
+    )
+
+
 class ERROR_MESSAGES(str, Enum):
    def __str__(self) -> str:
        return super().__str__()
@@ -13,6 +20,7 @@ class ERROR_MESSAGES(str, Enum):
    ENV_VAR_NOT_FOUND = "Required environment variable not found. Terminating now."
    CREATE_USER_ERROR = "Oops! Something went wrong while creating your account. Please try again later. If the issue persists, contact support for assistance."
    DELETE_USER_ERROR = "Oops! Something went wrong. We encountered an issue while trying to delete the user. Please give it another shot."
+    EMAIL_MISMATCH = "Uh-oh! This email does not match the email your provider is registered with. Please check your email and try again."
    EMAIL_TAKEN = "Uh-oh! This email is already registered. Sign in with your existing account or choose another email to start anew."
    USERNAME_TAKEN = (
        "Uh-oh! This username is already registered. Please choose another username."
@@ -29,6 +37,7 @@ class ERROR_MESSAGES(str, Enum):
    INVALID_PASSWORD = (
        "The password provided is incorrect. Please check for typos and try again."
    )
+    INVALID_TRUSTED_HEADER = "Your provider has not provided a trusted header. Please contact your administrator for assistance."
    UNAUTHORIZED = "401 Unauthorized"
    ACCESS_PROHIBITED = "You do not have permission to access this resource. Please contact your administrator for assistance."
    ACTION_PROHIBITED = (
@@ -46,9 +55,13 @@ class ERROR_MESSAGES(str, Enum):

    PANDOC_NOT_INSTALLED = "Pandoc is not installed on the server. Please contact your administrator for assistance."
    INCORRECT_FORMAT = (
-        lambda err="": f"Invalid format. Please use the correct format{err if err else ''}"
+        lambda err="": f"Invalid format. Please use the correct format{err}"
    )
    RATE_LIMIT_EXCEEDED = "API rate limit exceeded"

    MODEL_NOT_FOUND = lambda name="": f"Model '{name}' was not found"
-    OPENAI_NOT_FOUND = lambda name="": f"OpenAI API was not found"
+    OPENAI_NOT_FOUND = lambda name="": "OpenAI API was not found"
+    OLLAMA_NOT_FOUND = "WebUI could not connect to Ollama"
+    CREATE_API_KEY_ERROR = "Oops! Something went wrong while creating your API key. Please try again later. If the issue persists, contact support for assistance."
+
+    EMPTY_CONTENT = "The content provided is empty. Please ensure that there is text or data present before proceeding."
@@ -1,34 +1,24 @@
 {
-    "ui": {
-        "prompt_suggestions": [
-            {
-                "title": [
-                    "Help me study",
-                    "vocabulary for a college entrance exam"
-                ],
-                "content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option."
-            },
-            {
-                "title": [
-                    "Give me ideas",
-                    "for what to do with my kids' art"
-                ],
-                "content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter."
-            },
-            {
-                "title": [
-                    "Tell me a fun fact",
-                    "about the Roman Empire"
-                ],
-                "content": "Tell me a random fun fact about the Roman Empire"
-            },
-            {
-                "title": [
-                    "Show me a code snippet",
-                    "of a website's sticky header"
-                ],
-                "content": "Show me a code snippet of a website's sticky header in CSS and JavaScript."
-            }
-        ]
-    }
-}
+	"version": 0,
+	"ui": {
+		"default_locale": "en-US",
+		"prompt_suggestions": [
+			{
+				"title": ["Help me study", "vocabulary for a college entrance exam"],
+				"content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option."
+			},
+			{
+				"title": ["Give me ideas", "for what to do with my kids' art"],
+				"content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter."
+			},
+			{
+				"title": ["Tell me a fun fact", "about the Roman Empire"],
+				"content": "Tell me a random fun fact about the Roman Empire"
+			},
+			{
+				"title": ["Show me a code snippet", "of a website's sticky header"],
+				"content": "Show me a code snippet of a website's sticky header in CSS and JavaScript."
+			}
+		]
+	}
+}
@@ -4,32 +4,55 @@ import markdown
 import time
 import os
 import sys
+import logging
+import aiohttp
 import requests

 from fastapi import FastAPI, Request, Depends, status
 from fastapi.staticfiles import StaticFiles
 from fastapi import HTTPException
-from fastapi.responses import JSONResponse
 from fastapi.middleware.wsgi import WSGIMiddleware
 from fastapi.middleware.cors import CORSMiddleware
 from starlette.exceptions import HTTPException as StarletteHTTPException
+from starlette.middleware.base import BaseHTTPMiddleware


-from litellm.proxy.proxy_server import ProxyConfig, initialize
-from litellm.proxy.proxy_server import app as litellm_app
-
 from apps.ollama.main import app as ollama_app
 from apps.openai.main import app as openai_app
+
+from apps.litellm.main import app as litellm_app, startup as litellm_app_startup
 from apps.audio.main import app as audio_app
 from apps.images.main import app as images_app
 from apps.rag.main import app as rag_app
 from apps.web.main import app as webui_app

+from pydantic import BaseModel
+from typing import List

-from config import WEBUI_NAME, ENV, VERSION, CHANGELOG, FRONTEND_BUILD_DIR
+
+from utils.utils import get_admin_user
+from apps.rag.utils import rag_messages
+
+from config import (
+    CONFIG_DATA,
+    WEBUI_NAME,
+    ENV,
+    VERSION,
+    CHANGELOG,
+    FRONTEND_BUILD_DIR,
+    CACHE_DIR,
+    STATIC_DIR,
+    MODEL_FILTER_ENABLED,
+    MODEL_FILTER_LIST,
+    GLOBAL_LOG_LEVEL,
+    SRC_LOG_LEVELS,
+    WEBHOOK_URL,
+)
 from constants import ERROR_MESSAGES

-from utils.utils import get_http_authorization_cred, get_current_user
+logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])


 class SPAStaticFiles(StaticFiles):
@@ -43,25 +66,89 @@ class SPAStaticFiles(StaticFiles):
                raise ex


-proxy_config = ProxyConfig()
-
-
-async def config():
-    router, model_list, general_settings = await proxy_config.load_config(
-        router=None, config_file_path="./data/litellm/config.yaml"
-    )
-
-    await initialize(config="./data/litellm/config.yaml", telemetry=False)
-
-
-async def startup():
-    await config()
+print(
+    f"""
+  ___                    __        __   _     _   _ ___ 
+ / _ \ _ __   ___ _ __   \ \      / /__| |__ | | | |_ _|
+| | | | '_ \ / _ \ '_ \   \ \ /\ / / _ \ '_ \| | | || | 
+| |_| | |_) |  __/ | | |   \ V  V /  __/ |_) | |_| || | 
+ \___/| .__/ \___|_| |_|    \_/\_/ \___|_.__/ \___/|___|
+      |_|                                               

+      
+v{VERSION} - building the best open-source AI user interface.      
+https://github.com/open-webui/open-webui
+"""
+)

 app = FastAPI(docs_url="/docs" if ENV == "dev" else None, redoc_url=None)

+app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+
+app.state.WEBHOOK_URL = WEBHOOK_URL
+
 origins = ["*"]

+
+class RAGMiddleware(BaseHTTPMiddleware):
+    async def dispatch(self, request: Request, call_next):
+        if request.method == "POST" and (
+            "/api/chat" in request.url.path or "/chat/completions" in request.url.path
+        ):
+            log.debug(f"request.url.path: {request.url.path}")
+
+            # Read the original request body
+            body = await request.body()
+            # Decode body to string
+            body_str = body.decode("utf-8")
+            # Parse string to JSON
+            data = json.loads(body_str) if body_str else {}
+
+            # Example: Add a new key-value pair or modify existing ones
+            # data["modified"] = True  # Example modification
+            if "docs" in data:
+                data = {**data}
+                data["messages"] = rag_messages(
+                    data["docs"],
+                    data["messages"],
+                    rag_app.state.RAG_TEMPLATE,
+                    rag_app.state.TOP_K,
+                    rag_app.state.RAG_EMBEDDING_ENGINE,
+                    rag_app.state.RAG_EMBEDDING_MODEL,
+                    rag_app.state.sentence_transformer_ef,
+                    rag_app.state.RAG_OPENAI_API_KEY,
+                    rag_app.state.RAG_OPENAI_API_BASE_URL,
+                )
+                del data["docs"]
+
+                log.debug(f"data['messages']: {data['messages']}")
+
+            modified_body_bytes = json.dumps(data).encode("utf-8")
+
+            # Replace the request body with the modified one
+            request._body = modified_body_bytes
+
+            # Set custom header to ensure content-length matches new body length
+            request.headers.__dict__["_list"] = [
+                (b"content-length", str(len(modified_body_bytes)).encode("utf-8")),
+                *[
+                    (k, v)
+                    for k, v in request.headers.raw
+                    if k.lower() != b"content-length"
+                ],
+            ]
+
+        response = await call_next(request)
+        return response
+
+    async def _receive(self, body: bytes):
+        return {"type": "http.request", "body": body, "more_body": False}
+
+
+app.add_middleware(RAGMiddleware)
+
+
 app.add_middleware(
    CORSMiddleware,
    allow_origins=origins,
@@ -71,11 +158,6 @@ app.add_middleware(
 )


-@app.on_event("startup")
-async def on_startup():
-    await startup()
-
-
@app.middleware("http")
 async def check_url(request: Request, call_next):
    start_time = int(time.time())
@@ -86,19 +168,9 @@ async def check_url(request: Request, call_next):
    return response


-@litellm_app.middleware("http")
-async def auth_middleware(request: Request, call_next):
-    auth_header = request.headers.get("Authorization", "")
-
-    if ENV != "dev":
-        try:
-            user = get_current_user(get_http_authorization_cred(auth_header))
-            print(user)
-        except Exception as e:
-            return JSONResponse(status_code=400, content={"detail": str(e)})
-
-    response = await call_next(request)
-    return response
+@app.on_event("startup")
+async def on_startup():
+    await litellm_app_startup()


 app.mount("/api/v1", webui_app)
@@ -114,20 +186,84 @@ app.mount("/rag/api/v1", rag_app)

@app.get("/api/config")
 async def get_app_config():
+    # Checking and Handling the Absence of 'ui' in CONFIG_DATA

+    default_locale = "en-US"
+    if "ui" in CONFIG_DATA:
+        default_locale = CONFIG_DATA["ui"].get("default_locale", "en-US")
+
+    # The Rest of the Function Now Uses the Variables Defined Above
    return {
        "status": True,
        "name": WEBUI_NAME,
        "version": VERSION,
+        "default_locale": default_locale,
        "images": images_app.state.ENABLED,
        "default_models": webui_app.state.DEFAULT_MODELS,
        "default_prompt_suggestions": webui_app.state.DEFAULT_PROMPT_SUGGESTIONS,
+        "trusted_header_auth": bool(webui_app.state.AUTH_TRUSTED_EMAIL_HEADER),
+    }
+
+
+@app.get("/api/config/model/filter")
+async def get_model_filter_config(user=Depends(get_admin_user)):
+    return {
+        "enabled": app.state.MODEL_FILTER_ENABLED,
+        "models": app.state.MODEL_FILTER_LIST,
+    }
+
+
+class ModelFilterConfigForm(BaseModel):
+    enabled: bool
+    models: List[str]
+
+
+@app.post("/api/config/model/filter")
+async def update_model_filter_config(
+    form_data: ModelFilterConfigForm, user=Depends(get_admin_user)
+):
+    app.state.MODEL_FILTER_ENABLED = form_data.enabled
+    app.state.MODEL_FILTER_LIST = form_data.models
+
+    ollama_app.state.MODEL_FILTER_ENABLED = app.state.MODEL_FILTER_ENABLED
+    ollama_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+
+    openai_app.state.MODEL_FILTER_ENABLED = app.state.MODEL_FILTER_ENABLED
+    openai_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+
+    litellm_app.state.MODEL_FILTER_ENABLED = app.state.MODEL_FILTER_ENABLED
+    litellm_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+
+    return {
+        "enabled": app.state.MODEL_FILTER_ENABLED,
+        "models": app.state.MODEL_FILTER_LIST,
+    }
+
+
+@app.get("/api/webhook")
+async def get_webhook_url(user=Depends(get_admin_user)):
+    return {
+        "url": app.state.WEBHOOK_URL,
+    }
+
+
+class UrlForm(BaseModel):
+    url: str
+
+
+@app.post("/api/webhook")
+async def update_webhook_url(form_data: UrlForm, user=Depends(get_admin_user)):
+    app.state.WEBHOOK_URL = form_data.url
+
+    webui_app.state.WEBHOOK_URL = app.state.WEBHOOK_URL
+
+    return {
+        "url": app.state.WEBHOOK_URL,
    }


@app.get("/api/version")
 async def get_app_config():
-
    return {
        "version": VERSION,
    }
@@ -135,29 +271,45 @@ async def get_app_config():

@app.get("/api/changelog")
 async def get_app_changelog():
-    return CHANGELOG
+    return {key: CHANGELOG[key] for idx, key in enumerate(CHANGELOG) if idx < 5}


@app.get("/api/version/updates")
 async def get_app_latest_release_version():
    try:
-        response = requests.get(
-            f"https://api.github.com/repos/open-webui/open-webui/releases/latest"
-        )
-        response.raise_for_status()
-        latest_version = response.json()["tag_name"]
+        async with aiohttp.ClientSession() as session:
+            async with session.get(
+                "https://api.github.com/repos/open-webui/open-webui/releases/latest"
+            ) as response:
+                response.raise_for_status()
+                data = await response.json()
+                latest_version = data["tag_name"]

-        return {"current": VERSION, "latest": latest_version[1:]}
-    except Exception as e:
+                return {"current": VERSION, "latest": latest_version[1:]}
+    except aiohttp.ClientError as e:
        raise HTTPException(
            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
            detail=ERROR_MESSAGES.RATE_LIMIT_EXCEEDED,
        )


-app.mount("/static", StaticFiles(directory="static"), name="static")
+@app.get("/manifest.json")
+async def get_manifest_json():
+    return {
+        "name": WEBUI_NAME,
+        "short_name": WEBUI_NAME,
+        "start_url": "/",
+        "display": "standalone",
+        "background_color": "#343541",
+        "theme_color": "#343541",
+        "orientation": "portrait-primary",
+        "icons": [{"src": "/favicon.png", "type": "image/png", "sizes": "844x884"}],
+    }


+app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
+app.mount("/cache", StaticFiles(directory=CACHE_DIR), name="cache")
+
 app.mount(
    "/",
    SPAStaticFiles(directory=FRONTEND_BUILD_DIR, html=True),
@@ -14,9 +14,13 @@ uuid
 requests
 aiohttp
 peewee
+peewee-migrate
 bcrypt

-litellm
+litellm==1.30.7
+boto3
+
+argon2-cffi
 apscheduler
 google-generativeai

@@ -38,9 +42,12 @@ xlrd
 opencv-python-headless
 rapidocr-onnxruntime

+fpdf2
+
 faster-whisper

 PyJWT
 pyjwt[crypto]

 black
+langfuse
@@ -7,16 +7,26 @@ KEY_FILE=.webui_secret_key

 PORT="${PORT:-8080}"
 if test "$WEBUI_SECRET_KEY $WEBUI_JWT_SECRET_KEY" = " "; then
-  echo No WEBUI_SECRET_KEY provided
+  echo "No WEBUI_SECRET_KEY provided"

  if ! [ -e "$KEY_FILE" ]; then
-    echo Generating WEBUI_SECRET_KEY
+    echo "Generating WEBUI_SECRET_KEY"
    # Generate a random value to use as a WEBUI_SECRET_KEY in case the user didn't provide one.
-    echo $(head -c 12 /dev/random | base64) > $KEY_FILE
+    echo $(head -c 12 /dev/random | base64) > "$KEY_FILE"
  fi

-  echo Loading WEBUI_SECRET_KEY from $KEY_FILE
-  WEBUI_SECRET_KEY=`cat $KEY_FILE`
+  echo "Loading WEBUI_SECRET_KEY from $KEY_FILE"
+  WEBUI_SECRET_KEY=$(cat "$KEY_FILE")
 fi

-WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host 0.0.0.0 --port "$PORT" --forwarded-allow-ips '*'
+if [ "$USE_OLLAMA_DOCKER" = "true" ]; then
+    echo "USE_OLLAMA is set to true, starting ollama serve."
+    ollama serve &
+fi
+
+if [ "$USE_CUDA_DOCKER" = "true" ]; then
+  echo "CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries."
+  export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.11/site-packages/torch/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib"
+fi
+
+WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host 0.0.0.0 --port "$PORT" --forwarded-allow-ips '*'
@@ -1,6 +1,8 @@
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from fastapi import HTTPException, status, Depends
+
 from apps.web.models.users import Users
+
 from pydantic import BaseModel
 from typing import Union, Optional
 from constants import ERROR_MESSAGES
@@ -8,6 +10,7 @@ from passlib.context import CryptContext
 from datetime import datetime, timedelta
 import requests
 import jwt
+import uuid
 import logging
 import config

@@ -58,6 +61,11 @@ def extract_token_from_auth_header(auth_header: str):
    return auth_header[len("Bearer ") :]


+def create_api_key():
+    key = str(uuid.uuid4()).replace("-", "")
+    return f"sk-{key}"
+
+
 def get_http_authorization_cred(auth_header: str):
    try:
        scheme, credentials = auth_header.split(" ")
@@ -69,6 +77,10 @@ def get_http_authorization_cred(auth_header: str):
 def get_current_user(
    auth_token: HTTPAuthorizationCredentials = Depends(bearer_security),
 ):
+    # auth by api key
+    if auth_token.credentials.startswith("sk-"):
+        return get_current_user_by_api_key(auth_token.credentials)
+    # auth by jwt token
    data = decode_token(auth_token.credentials)
    if data != None and "id" in data:
        user = Users.get_user_by_id(data["id"])
@@ -85,6 +97,16 @@ def get_current_user(
        )


+def get_current_user_by_api_key(api_key: str):
+    user = Users.get_user_by_api_key(api_key)
+    if user is None:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.INVALID_TOKEN,
+        )
+    return user
+
+
 def get_verified_user(user=Depends(get_current_user)):
    if user.role not in {"user", "admin"}:
        raise HTTPException(
@@ -0,0 +1,54 @@
+import json
+import requests
+import logging
+
+from config import SRC_LOG_LEVELS, VERSION, WEBUI_FAVICON_URL, WEBUI_NAME
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["WEBHOOK"])
+
+
+def post_webhook(url: str, message: str, event_data: dict) -> bool:
+    try:
+        payload = {}
+
+        # Slack and Google Chat Webhooks
+        if "https://hooks.slack.com" in url or "https://chat.googleapis.com" in url:
+            payload["text"] = message
+        # Discord Webhooks
+        elif "https://discord.com/api/webhooks" in url:
+            payload["content"] = message
+        # Microsoft Teams Webhooks
+        elif "webhook.office.com" in url:
+            action = event_data.get("action", "undefined")
+            facts = [
+                {"name": name, "value": value}
+                for name, value in json.loads(event_data.get("user", {})).items()
+            ]
+            payload = {
+                "@type": "MessageCard",
+                "@context": "http://schema.org/extensions",
+                "themeColor": "0076D7",
+                "summary": message,
+                "sections": [
+                    {
+                        "activityTitle": message,
+                        "activitySubtitle": f"{WEBUI_NAME} ({VERSION}) - {action}",
+                        "activityImage": WEBUI_FAVICON_URL,
+                        "facts": facts,
+                        "markdown": True,
+                    }
+                ],
+            }
+        # Default Payload
+        else:
+            payload = {**event_data}
+
+        log.debug(f"payload: {payload}")
+        r = requests.post(url, json=payload)
+        r.raise_for_status()
+        log.debug(f"r.text: {r.text}")
+        return True
+    except Exception as e:
+        log.exception(e)
+        return False
@@ -0,0 +1,8 @@
+services:
+  ollama:
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    image: ollama/ollama:${OLLAMA_DOCKER_TAG-rocm}
+    environment:
+      - 'HSA_OVERRIDE_GFX_VERSION=${HSA_OVERRIDE_GFX_VERSION-11.0.0}'
@@ -8,7 +8,7 @@ services:
    pull_policy: always
    tty: true
    restart: unless-stopped
-    image: ollama/ollama:latest
+    image: ollama/ollama:${OLLAMA_DOCKER_TAG-latest}

  open-webui:
    build:
@@ -16,7 +16,7 @@ services:
      args:
        OLLAMA_BASE_URL: '/ollama'
      dockerfile: Dockerfile
-    image: ghcr.io/open-webui/open-webui:main
+    image: ghcr.io/open-webui/open-webui:${WEBUI_DOCKER_TAG-main}
    container_name: open-webui
    volumes:
      - open-webui:/app/backend/data
@@ -50,6 +50,18 @@ We welcome pull requests. Before submitting one, please:

 Help us make Open WebUI more accessible by improving documentation, writing tutorials, or creating guides on setting up and optimizing the web UI.

+### 🌐 Translations and Internationalization
+
+Help us make Open WebUI available to a wider audience. In this section, we'll guide you through the process of adding new translations to the project.
+
+We use JSON files to store translations. You can find the existing translation files in the `src/lib/i18n/locales` directory. Each directory corresponds to a specific language, for example, `en-US` for English (US), `fr-FR` for French (France) and so on. You can refer to [ISO 639 Language Codes][http://www.lingoes.net/en/translator/langcode.htm] to find the appropriate code for a specific language.
+
+To add a new language:
+
+- Create a new directory in the `src/lib/i18n/locales` path with the appropriate language code as its name. For instance, if you're adding translations for Spanish (Spain), create a new directory named `es-ES`.
+- Copy the American English translation file(s) (from `en-US` directory in `src/lib/i18n/locale`) to this new directory and update the string values in JSON format according to your language. Make sure to preserve the structure of the JSON object.
+- Add the language code and its respective title to languages file at `src/lib/i18n/locales/languages.json`.
+
 ### 🤔 Questions & Feedback

 Got questions or feedback? Join our [Discord community](https://discord.gg/5rJgQTnV4s) or open an issue. We're here to help!
@@ -0,0 +1,38 @@
+// i18next-parser.config.ts
+import { getLanguages } from './src/lib/i18n/index.ts';
+
+const getLangCodes = async () => {
+	const languages = await getLanguages();
+	return languages.map((l) => l.code);
+};
+
+export default {
+	contextSeparator: '_',
+	createOldCatalogs: false,
+	defaultNamespace: 'translation',
+	defaultValue: '',
+	indentation: 2,
+	keepRemoved: false,
+	keySeparator: false,
+	lexers: {
+		svelte: ['JavascriptLexer'],
+		js: ['JavascriptLexer'],
+		ts: ['JavascriptLexer'],
+
+		default: ['JavascriptLexer']
+	},
+	lineEnding: 'auto',
+	locales: await getLangCodes(),
+	namespaceSeparator: false,
+	output: 'src/lib/i18n/locales/$LOCALE/$NAMESPACE.json',
+	pluralSeparator: '_',
+	input: 'src/**/*.{js,svelte}',
+	sort: true,
+	verbose: true,
+	failOnWarnings: false,
+	failOnUpdate: false,
+	customValueTemplate: null,
+	resetDefaultValueLocale: null,
+	i18nextOptions: null,
+	yamlOptions: null
+};
@@ -7,7 +7,11 @@ ollama
 {{- end -}}

 {{- define "ollama.url" -}}
-{{- printf "http://%s.%s.svc.cluster.local:%d/api" (include "ollama.name" .) (.Release.Namespace) (.Values.ollama.service.port | int) }}
+{{- if .Values.ollama.externalHost }}
+{{- printf .Values.ollama.externalHost }}
+{{- else }}
+{{- printf "http://%s.%s.svc.cluster.local:%d" (include "ollama.name" .) (.Release.Namespace) (.Values.ollama.service.port | int) }}
+{{- end }}
 {{- end }}

 {{- define "chart.name" -}}
@@ -1,3 +1,4 @@
+{{- if not .Values.ollama.externalHost }}
 apiVersion: v1
 kind: Service
 metadata:
@@ -19,3 +20,4 @@ spec:
    port: {{ .port }}
    targetPort: http
 {{- end }}
+{{- end }}
@@ -1,3 +1,4 @@
+{{- if not .Values.ollama.externalHost }}
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
@@ -88,9 +89,10 @@ spec:
      resources:
        requests:
          storage: {{ .Values.ollama.persistence.size | quote }}
-      storageClass: {{ .Values.ollama.persistence.storageClass }}
+      storageClassName: {{ .Values.ollama.persistence.storageClass }}
      {{- with .Values.ollama.persistence.selector }}
      selector:
        {{- toYaml . | nindent 8 }}
      {{- end }}
      {{- end }}
+{{- end }}
@@ -17,7 +17,9 @@ spec:
  resources:
    requests:
      storage: {{ .Values.webui.persistence.size }}
-  storageClass: {{ .Values.webui.persistence.storageClass }}
+  {{- if .Values.webui.persistence.storageClass }}
+  storageClassName: {{ .Values.webui.persistence.storageClass }}
+  {{- end }}
  {{- with .Values.webui.persistence.selector }}
  selector:
    {{- toYaml . | nindent 4 }}
@@ -4,6 +4,9 @@ metadata:
  name: {{ include "open-webui.name" . }}
  labels:
    {{- include "open-webui.labels" . | nindent 4 }}
+    {{- with .Values.webui.service.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
  {{- with .Values.webui.service.annotations }}
  annotations:
    {{- toYaml . | nindent 4 }}
@@ -11,14 +14,16 @@ metadata:
 spec:
  selector:
    {{- include "open-webui.selectorLabels" . | nindent 4 }}
-{{- with .Values.webui.service }}
-  type: {{ .type }}
+  type: {{ .Values.webui.service.type | default "ClusterIP" }}
  ports:
  - protocol: TCP
    name: http
-    port: {{ .port }}
+    port: {{ .Values.webui.service.port }}
    targetPort: http
-    {{- if .nodePort }}
-    nodePort: {{ .nodePort | int }}
+    {{- if .Values.webui.service.nodePort }}
+    nodePort: {{ .Values.webui.service.nodePort | int }}
    {{- end }}
-{{- end }}
+  {{- if .Values.webui.service.loadBalancerClass }}
+  loadBalancerClass: {{ .Values.webui.service.loadBalancerClass | quote }}
+  {{- end }}
+
@@ -1,6 +1,7 @@
 nameOverride: ""

 ollama:
+  externalHost: ""
  annotations: {}
  podAnnotations: {}
  replicaCount: 1
@@ -70,3 +71,5 @@ webui:
    port: 80
    containerPort: 8080
    nodePort: ""
+    labels: {}
+    loadBalancerClass: "" 
@@ -35,4 +35,4 @@ spec:
      volumes:
      - name: webui-volume
        persistentVolumeClaim:
-          claimName: ollama-webui-pvc          
+          claimName: open-webui-pvc          
@@ -2,8 +2,8 @@ apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
  labels:
-    app: ollama-webui
-  name: ollama-webui-pvc
+    app: open-webui
+  name: open-webui-pvc
  namespace: open-webui
 spec:
  accessModes: ["ReadWriteOnce"]
@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.1.110",
+	"version": "0.1.120",
 	"private": true,
 	"scripts": {
 		"dev": "vite dev --host",
@@ -13,7 +13,8 @@
 		"lint:types": "npm run check",
 		"lint:backend": "pylint backend/",
 		"format": "prettier --plugin-search-dir --write '**/*.{js,ts,svelte,css,md,html,json}'",
-		"format:backend": "yapf --recursive backend -p -i"
+		"format:backend": "black . --exclude \"/venv/\"",
+		"i18n:parse": "i18next --config i18next-parser.config.ts && prettier --write 'src/lib/i18n/**/*.{js,json}'"
 	},
 	"devDependencies": {
 		"@sveltejs/adapter-auto": "^2.0.0",
@@ -27,6 +28,7 @@
 		"eslint": "^8.56.0",
 		"eslint-config-prettier": "^8.5.0",
 		"eslint-plugin-svelte": "^2.30.0",
+		"i18next-parser": "^8.13.0",
 		"postcss": "^8.4.31",
 		"prettier": "^2.8.0",
 		"prettier-plugin-svelte": "^2.10.1",
@@ -42,15 +44,20 @@
 	"dependencies": {
 		"@sveltejs/adapter-node": "^1.3.1",
 		"async": "^3.2.5",
+		"bits-ui": "^0.19.7",
 		"dayjs": "^1.11.10",
 		"file-saver": "^2.0.5",
 		"highlight.js": "^11.9.0",
+		"i18next": "^23.10.0",
+		"i18next-browser-languagedetector": "^7.2.0",
+		"i18next-resources-to-backend": "^1.2.0",
 		"idb": "^7.1.1",
 		"js-sha256": "^0.10.1",
+		"jspdf": "^2.5.1",
 		"katex": "^0.16.9",
 		"marked": "^9.1.0",
 		"svelte-sonner": "^0.3.19",
 		"tippy.js": "^6.3.7",
 		"uuid": "^9.0.1"
 	}
-}
+}
@@ -78,3 +78,7 @@ select {
 	/* for Chrome */
 	-webkit-appearance: none;
 }
+
+.katex-mathml {
+	display: none;
+}
@@ -3,23 +3,44 @@
 	<head>
 		<meta charset="utf-8" />
 		<link rel="icon" href="%sveltekit.assets%/favicon.png" />
-		<link rel="manifest" href="%sveltekit.assets%/manifest.json" />
+		<link rel="manifest" href="%sveltekit.assets%/manifest.json" crossorigin="use-credentials" />
 		<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1" />
 		<meta name="robots" content="noindex,nofollow" />
 		<script>
 			// On page load or when changing themes, best to add inline in `head` to avoid FOUC
-			if (
-				localStorage.theme === 'light' ||
-				(!('theme' in localStorage) && window.matchMedia('(prefers-color-scheme: light)').matches)
-			) {
-				document.documentElement.classList.add('light');
-			} else if (localStorage.theme) {
-				localStorage.theme.split(' ').forEach((e) => {
-					document.documentElement.classList.add(e);
+			(() => {
+				if (localStorage?.theme && localStorage?.theme.includes('oled')) {
+					document.documentElement.style.setProperty('--color-gray-900', '#000000');
+					document.documentElement.style.setProperty('--color-gray-950', '#000000');
+					document.documentElement.classList.add('dark');
+				} else if (
+					localStorage.theme === 'light' ||
+					(!('theme' in localStorage) && window.matchMedia('(prefers-color-scheme: light)').matches)
+				) {
+					document.documentElement.classList.add('light');
+				} else if (localStorage.theme && localStorage.theme !== 'system') {
+					localStorage.theme.split(' ').forEach((e) => {
+						document.documentElement.classList.add(e);
+					});
+				} else if (localStorage.theme && localStorage.theme === 'system') {
+					systemTheme = window.matchMedia('(prefers-color-scheme: dark)').matches;
+					document.documentElement.classList.add(systemTheme ? 'dark' : 'light');
+				} else {
+					document.documentElement.classList.add('dark');
+				}
+
+				window.matchMedia('(prefers-color-scheme: dark)').addListener((e) => {
+					if (localStorage.theme === 'system') {
+						if (e.matches) {
+							document.documentElement.classList.add('dark');
+							document.documentElement.classList.remove('light');
+						} else {
+							document.documentElement.classList.add('light');
+							document.documentElement.classList.remove('dark');
+						}
+					}
 				});
-			} else {
-				document.documentElement.classList.add('dark');
-			}
+			})();
 		</script>

 		%sveltekit.head%
@@ -1,11 +1,73 @@
 import { AUDIO_API_BASE_URL } from '$lib/constants';

+export const getAudioConfig = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${AUDIO_API_BASE_URL}/config`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+type OpenAIConfigForm = {
+	url: string;
+	key: string;
+};
+
+export const updateAudioConfig = async (token: string, payload: OpenAIConfigForm) => {
+	let error = null;
+
+	const res = await fetch(`${AUDIO_API_BASE_URL}/config/update`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			...payload
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const transcribeAudio = async (token: string, file: File) => {
 	const data = new FormData();
 	data.append('file', file);

 	let error = null;
-	const res = await fetch(`${AUDIO_API_BASE_URL}/transcribe`, {
+	const res = await fetch(`${AUDIO_API_BASE_URL}/transcriptions`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -29,3 +91,40 @@ export const transcribeAudio = async (token: string, file: File) => {

 	return res;
 };
+
+export const synthesizeOpenAISpeech = async (
+	token: string = '',
+	speaker: string = 'alloy',
+	text: string = ''
+) => {
+	let error = null;
+
+	const res = await fetch(`${AUDIO_API_BASE_URL}/speech`, {
+		method: 'POST',
+		headers: {
+			Authorization: `Bearer ${token}`,
+			'Content-Type': 'application/json'
+		},
+		body: JSON.stringify({
+			model: 'tts-1',
+			input: text,
+			voice: speaker
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res;
+		})
+		.catch((err) => {
+			error = err.detail;
+			console.log(err);
+
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
@@ -58,7 +58,12 @@ export const userSignIn = async (email: string, password: string) => {
 	return res;
 };

-export const userSignUp = async (name: string, email: string, password: string) => {
+export const userSignUp = async (
+	name: string,
+	email: string,
+	password: string,
+	profile_image_url: string
+) => {
 	let error = null;

 	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/signup`, {
@@ -69,7 +74,8 @@ export const userSignUp = async (name: string, email: string, password: string)
 		body: JSON.stringify({
 			name: name,
 			email: email,
-			password: password
+			password: password,
+			profile_image_url: profile_image_url
 		})
 	})
 		.then(async (res) => {
@@ -318,3 +324,78 @@ export const updateJWTExpiresDuration = async (token: string, duration: string)

 	return res;
 };
+
+export const createAPIKey = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+	if (error) {
+		throw error;
+	}
+	return res.api_key;
+};
+
+export const getAPIKey = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+	if (error) {
+		throw error;
+	}
+	return res.api_key;
+};
+
+export const deleteAPIKey = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
+		method: 'DELETE',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+	if (error) {
+		throw error;
+	}
+	return res;
+};
@@ -62,6 +62,37 @@ export const getChatList = async (token: string = '') => {
 	return res;
 };

+export const getArchivedChatList = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/archived`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const getAllChats = async (token: string) => {
 	let error = null;

@@ -218,6 +249,134 @@ export const getChatById = async (token: string, id: string) => {
 	return res;
 };

+export const getChatByShareId = async (token: string, share_id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/share/${share_id}`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const shareChatById = async (token: string, id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/share`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const archiveChatById = async (token: string, id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/archive`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const deleteSharedChatById = async (token: string, id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/share`, {
+		method: 'DELETE',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const updateChatById = async (token: string, id: string, chat: object) => {
 	let error = null;

@@ -1,9 +1,9 @@
 import { IMAGES_API_BASE_URL } from '$lib/constants';

-export const getImageGenerationEnabledStatus = async (token: string = '') => {
+export const getImageGenerationConfig = async (token: string = '') => {
 	let error = null;

-	const res = await fetch(`${IMAGES_API_BASE_URL}/enabled`, {
+	const res = await fetch(`${IMAGES_API_BASE_URL}/config`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -32,10 +32,50 @@ export const getImageGenerationEnabledStatus = async (token: string = '') => {
 	return res;
 };

-export const toggleImageGenerationEnabledStatus = async (token: string = '') => {
+export const updateImageGenerationConfig = async (
+	token: string = '',
+	engine: string,
+	enabled: boolean
+) => {
 	let error = null;

-	const res = await fetch(`${IMAGES_API_BASE_URL}/enabled/toggle`, {
+	const res = await fetch(`${IMAGES_API_BASE_URL}/config/update`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify({
+			engine,
+			enabled
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = 'Server connection failed';
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getOpenAIKey = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${IMAGES_API_BASE_URL}/key`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -61,10 +101,45 @@ export const toggleImageGenerationEnabledStatus = async (token: string = '') =>
 		throw error;
 	}

-	return res;
+	return res.OPENAI_API_KEY;
 };

-export const getAUTOMATIC1111Url = async (token: string = '') => {
+export const updateOpenAIKey = async (token: string = '', key: string) => {
+	let error = null;
+
+	const res = await fetch(`${IMAGES_API_BASE_URL}/key/update`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify({
+			key: key
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = 'Server connection failed';
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.OPENAI_API_KEY;
+};
+
+export const getImageGenerationEngineUrls = async (token: string = '') => {
 	let error = null;

 	const res = await fetch(`${IMAGES_API_BASE_URL}/url`, {
@@ -93,10 +168,10 @@ export const getAUTOMATIC1111Url = async (token: string = '') => {
 		throw error;
 	}

-	return res.AUTOMATIC1111_BASE_URL;
+	return res;
 };

-export const updateAUTOMATIC1111Url = async (token: string = '', url: string) => {
+export const updateImageGenerationEngineUrls = async (token: string = '', urls: object = {}) => {
 	let error = null;

 	const res = await fetch(`${IMAGES_API_BASE_URL}/url/update`, {
@@ -107,7 +182,7 @@ export const updateAUTOMATIC1111Url = async (token: string = '', url: string) =>
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			url: url
+			...urls
 		})
 	})
 		.then(async (res) => {
@@ -128,7 +203,7 @@ export const updateAUTOMATIC1111Url = async (token: string = '', url: string) =>
 		throw error;
 	}

-	return res.AUTOMATIC1111_BASE_URL;
+	return res;
 };

 export const getImageSize = async (token: string = '') => {
@@ -263,7 +338,7 @@ export const updateImageSteps = async (token: string = '', steps: number) => {
 	return res.IMAGE_STEPS;
 };

-export const getDiffusionModels = async (token: string = '') => {
+export const getImageGenerationModels = async (token: string = '') => {
 	let error = null;

 	const res = await fetch(`${IMAGES_API_BASE_URL}/models`, {
@@ -295,7 +370,7 @@ export const getDiffusionModels = async (token: string = '') => {
 	return res;
 };

-export const getDefaultDiffusionModel = async (token: string = '') => {
+export const getDefaultImageGenerationModel = async (token: string = '') => {
 	let error = null;

 	const res = await fetch(`${IMAGES_API_BASE_URL}/models/default`, {
@@ -327,7 +402,7 @@ export const getDefaultDiffusionModel = async (token: string = '') => {
 	return res.model;
 };

-export const updateDefaultDiffusionModel = async (token: string = '', model: string) => {
+export const updateDefaultImageGenerationModel = async (token: string = '', model: string) => {
 	let error = null;

 	const res = await fetch(`${IMAGES_API_BASE_URL}/models/default/update`, {
@@ -77,3 +77,122 @@ export const getVersionUpdates = async () => {

 	return res;
 };
+
+export const getModelFilterConfig = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/config/model/filter`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const updateModelFilterConfig = async (
+	token: string,
+	enabled: boolean,
+	models: string[]
+) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/config/model/filter`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			enabled: enabled,
+			models: models
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getWebhookUrl = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/webhook`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.url;
+};
+
+export const updateWebhookUrl = async (token: string, url: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/webhook`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			url: url
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.url;
+};
@@ -33,7 +33,7 @@ export const getLiteLLMModels = async (token: string = '') => {
 					id: model.id,
 					name: model.name ?? model.id,
 					external: true,
-					source: 'litellm'
+					source: 'LiteLLM'
 				}))
 				.sort((a, b) => {
 					return a.name.localeCompare(b.name);
@@ -77,6 +77,7 @@ type AddLiteLLMModelForm = {
 	api_base: string;
 	api_key: string;
 	rpm: string;
+	max_tokens: string;
 };

 export const addLiteLLMModel = async (token: string = '', payload: AddLiteLLMModelForm) => {
@@ -95,7 +96,8 @@ export const addLiteLLMModel = async (token: string = '', payload: AddLiteLLMMod
 				model: payload.model,
 				...(payload.api_base === '' ? {} : { api_base: payload.api_base }),
 				...(payload.api_key === '' ? {} : { api_key: payload.api_key }),
-				...(isNaN(parseInt(payload.rpm)) ? {} : { rpm: parseInt(payload.rpm) })
+				...(isNaN(parseInt(payload.rpm)) ? {} : { rpm: parseInt(payload.rpm) }),
+				...(payload.max_tokens === '' ? {} : { max_tokens: payload.max_tokens })
 			}
 		})
 	})
@@ -1,4 +1,5 @@
 import { OLLAMA_API_BASE_URL } from '$lib/constants';
+import { promptTemplate } from '$lib/utils';

 export const getOllamaUrls = async (token: string = '') => {
 	let error = null;
@@ -144,7 +145,7 @@ export const generateTitle = async (
 ) => {
 	let error = null;

-	template = template.replace(/{{prompt}}/g, prompt);
+	template = promptTemplate(template, prompt);

 	console.log(template);

@@ -219,6 +220,32 @@ export const generatePrompt = async (token: string = '', model: string, conversa
 	return res;
 };

+export const generateEmbeddings = async (token: string = '', model: string, text: string) => {
+	let error = null;
+
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/embeddings`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			model: model,
+			prompt: text
+		})
+	}).catch((err) => {
+		error = err;
+		return null;
+	});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const generateTextCompletion = async (token: string = '', model: string, text: string) => {
 	let error = null;

@@ -271,7 +298,7 @@ export const generateChatCompletion = async (token: string = '', body: object) =
 	return [res, controller];
 };

-export const cancelChatCompletion = async (token: string = '', requestId: string) => {
+export const cancelOllamaRequest = async (token: string = '', requestId: string) => {
 	let error = null;

 	const res = await fetch(`${OLLAMA_API_BASE_URL}/cancel/${requestId}`, {
@@ -390,6 +417,73 @@ export const pullModel = async (token: string, tagName: string, urlIdx: string |
 	return res;
 };

+export const downloadModel = async (
+	token: string,
+	download_url: string,
+	urlIdx: string | null = null
+) => {
+	let error = null;
+
+	const res = await fetch(
+		`${OLLAMA_API_BASE_URL}/models/download${urlIdx !== null ? `/${urlIdx}` : ''}`,
+		{
+			method: 'POST',
+			headers: {
+				Accept: 'application/json',
+				'Content-Type': 'application/json',
+				Authorization: `Bearer ${token}`
+			},
+			body: JSON.stringify({
+				url: download_url
+			})
+		}
+	).catch((err) => {
+		console.log(err);
+		error = err;
+
+		if ('detail' in err) {
+			error = err.detail;
+		}
+
+		return null;
+	});
+	if (error) {
+		throw error;
+	}
+	return res;
+};
+
+export const uploadModel = async (token: string, file: File, urlIdx: string | null = null) => {
+	let error = null;
+
+	const formData = new FormData();
+	formData.append('file', file);
+
+	const res = await fetch(
+		`${OLLAMA_API_BASE_URL}/models/upload${urlIdx !== null ? `/${urlIdx}` : ''}`,
+		{
+			method: 'POST',
+			headers: {
+				Authorization: `Bearer ${token}`
+			},
+			body: formData
+		}
+	).catch((err) => {
+		console.log(err);
+		error = err;
+
+		if ('detail' in err) {
+			error = err.detail;
+		}
+
+		return null;
+	});
+	if (error) {
+		throw error;
+	}
+	return res;
+};
+
 // export const pullModel = async (token: string, tagName: string) => {
 // 	return await fetch(`${OLLAMA_API_BASE_URL}/pull`, {
 // 		method: 'POST',
@@ -1,4 +1,5 @@
 import { OPENAI_API_BASE_URL } from '$lib/constants';
+import { promptTemplate } from '$lib/utils';

 export const getOpenAIUrls = async (token: string = '') => {
 	let error = null;
@@ -263,3 +264,53 @@ export const synthesizeOpenAISpeech = async (

 	return res;
 };
+
+export const generateTitle = async (
+	token: string = '',
+	template: string,
+	model: string,
+	prompt: string,
+	url: string = OPENAI_API_BASE_URL
+) => {
+	let error = null;
+
+	template = promptTemplate(template, prompt);
+
+	console.log(template);
+
+	const res = await fetch(`${url}/chat/completions`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			model: model,
+			messages: [
+				{
+					role: 'user',
+					content: template
+				}
+			],
+			stream: false
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res?.choices[0]?.message?.content ?? 'New Chat';
+};
@@ -1,9 +1,9 @@
 import { RAG_API_BASE_URL } from '$lib/constants';

-export const getChunkParams = async (token: string) => {
+export const getRAGConfig = async (token: string) => {
 	let error = null;

-	const res = await fetch(`${RAG_API_BASE_URL}/chunk`, {
+	const res = await fetch(`${RAG_API_BASE_URL}/config`, {
 		method: 'GET',
 		headers: {
 			'Content-Type': 'application/json',
@@ -27,18 +27,27 @@ export const getChunkParams = async (token: string) => {
 	return res;
 };

-export const updateChunkParams = async (token: string, size: number, overlap: number) => {
+type ChunkConfigForm = {
+	chunk_size: number;
+	chunk_overlap: number;
+};
+
+type RAGConfigForm = {
+	pdf_extract_images: boolean;
+	chunk: ChunkConfigForm;
+};
+
+export const updateRAGConfig = async (token: string, payload: RAGConfigForm) => {
 	let error = null;

-	const res = await fetch(`${RAG_API_BASE_URL}/chunk/update`, {
+	const res = await fetch(`${RAG_API_BASE_URL}/config/update`, {
 		method: 'POST',
 		headers: {
 			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
-			chunk_size: size,
-			chunk_overlap: overlap
+			...payload
 		})
 	})
 		.then(async (res) => {
@@ -252,7 +261,7 @@ export const queryCollection = async (
 	token: string,
 	collection_names: string,
 	query: string,
-	k: number
+	k: number | null = null
 ) => {
 	let error = null;

@@ -336,3 +345,71 @@ export const resetVectorDB = async (token: string) => {

 	return res;
 };
+
+export const getEmbeddingConfig = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/embedding`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+type OpenAIConfigForm = {
+	key: string;
+	url: string;
+};
+
+type EmbeddingModelUpdateForm = {
+	openai_config?: OpenAIConfigForm;
+	embedding_engine: string;
+	embedding_model: string;
+};
+
+export const updateEmbeddingConfig = async (token: string, payload: EmbeddingModelUpdateForm) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/embedding/update`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			...payload
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
@@ -22,6 +22,57 @@ export const getGravatarUrl = async (email: string) => {
 	return res;
 };

+export const downloadChatAsPDF = async (chat: object) => {
+	let error = null;
+
+	const blob = await fetch(`${WEBUI_API_BASE_URL}/utils/pdf`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json'
+		},
+		body: JSON.stringify({
+			title: chat.title,
+			messages: chat.messages
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.blob();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	return blob;
+};
+
+export const getHTMLFromMarkdown = async (md: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/utils/markdown`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json'
+		},
+		body: JSON.stringify({
+			md: md
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	return res.html;
+};
+
 export const downloadDatabase = async (token: string) => {
 	let error = null;

@@ -1,8 +1,13 @@
+<script>
+	import { getContext } from 'svelte';
+	const i18n = getContext('i18n');
+</script>
+
 <div class="  text-center text-6xl mb-3">📄</div>
-<div class="text-center dark:text-white text-2xl font-semibold z-50">Add Files</div>
+<div class="text-center dark:text-white text-2xl font-semibold z-50">{$i18n.t('Add Files')}</div>

 <slot
 	><div class=" mt-2 text-center text-sm dark:text-gray-200 w-full">
-		Drop any files here to add to the conversation
+		{$i18n.t('Drop any files here to add to the conversation')}
 	</div>
 </slot>
@@ -1,5 +1,5 @@
 <script lang="ts">
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';
 	import { Confetti } from 'svelte-confetti';

 	import { WEBUI_NAME, config } from '$lib/stores';
@@ -9,6 +9,8 @@

 	import Modal from './common/Modal.svelte';

+	const i18n = getContext('i18n');
+
 	export let show = false;

 	let changelog = null;
@@ -23,12 +25,14 @@
 	<div class="px-5 py-4 dark:text-gray-300">
 		<div class="flex justify-between items-start">
 			<div class="text-xl font-bold">
-				What’s New in {$WEBUI_NAME}
+				{$i18n.t('What’s New in')}
+				{$WEBUI_NAME}
 				<Confetti x={[-1, -0.25]} y={[0, 0.5]} />
 			</div>
 			<button
 				class="self-center"
 				on:click={() => {
+					localStorage.version = $config.version;
 					show = false;
 				}}
 			>
@@ -45,7 +49,7 @@
 			</button>
 		</div>
 		<div class="flex items-center mt-1">
-			<div class="text-sm dark:text-gray-200">Release Notes</div>
+			<div class="text-sm dark:text-gray-200">{$i18n.t('Release Notes')}</div>
 			<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-200 dark:bg-gray-700" />
 			<div class="text-sm dark:text-gray-200">
 				v{WEBUI_VERSION}
@@ -108,7 +112,7 @@
 				}}
 				class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
 			>
-				<span class="relative">Okay, Let's Go!</span>
+				<span class="relative">{$i18n.t("Okay, Let's Go!")}</span>
 			</button>
 		</div>
 	</div>
@@ -2,11 +2,12 @@
 	import { toast } from 'svelte-sonner';
 	import dayjs from 'dayjs';
 	import { createEventDispatcher } from 'svelte';
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';

 	import { updateUserById } from '$lib/apis/users';
 	import Modal from '../common/Modal.svelte';

+	const i18n = getContext('i18n');
 	const dispatch = createEventDispatcher();

 	export let show = false;
@@ -42,7 +43,7 @@
 <Modal size="sm" bind:show>
 	<div>
 		<div class=" flex justify-between dark:text-gray-300 px-5 py-4">
-			<div class=" text-lg font-medium self-center">Edit User</div>
+			<div class=" text-lg font-medium self-center">{$i18n.t('Edit User')}</div>
 			<button
 				class="self-center"
 				on:click={() => {
@@ -84,7 +85,8 @@
 							<div class=" self-center capitalize font-semibold">{selectedUser.name}</div>

 							<div class="text-xs text-gray-500">
-								Created at {dayjs(selectedUser.timestamp * 1000).format('MMMM DD, YYYY')}
+								{$i18n.t('Created at')}
+								{dayjs(selectedUser.timestamp * 1000).format($i18n.t('MMMM DD, YYYY'))}
 							</div>
 						</div>
 					</div>
@@ -93,7 +95,7 @@

 					<div class=" flex flex-col space-y-1.5">
 						<div class="flex flex-col w-full">
-							<div class=" mb-1 text-xs text-gray-500">Email</div>
+							<div class=" mb-1 text-xs text-gray-500">{$i18n.t('Email')}</div>

 							<div class="flex-1">
 								<input
@@ -108,7 +110,7 @@
 						</div>

 						<div class="flex flex-col w-full">
-							<div class=" mb-1 text-xs text-gray-500">Name</div>
+							<div class=" mb-1 text-xs text-gray-500">{$i18n.t('Name')}</div>

 							<div class="flex-1">
 								<input
@@ -122,7 +124,7 @@
 						</div>

 						<div class="flex flex-col w-full">
-							<div class=" mb-1 text-xs text-gray-500">New Password</div>
+							<div class=" mb-1 text-xs text-gray-500">{$i18n.t('New Password')}</div>

 							<div class="flex-1">
 								<input
@@ -140,7 +142,7 @@
 							class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
 							type="submit"
 						>
-							Save
+							{$i18n.t('Save')}
 						</button>
 					</div>
 				</form>
@@ -1,6 +1,8 @@
 <script lang="ts">
 	import { downloadDatabase } from '$lib/apis/utils';
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');

 	export let saveHandler: Function;

@@ -17,10 +19,10 @@
 >
 	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
 		<div>
-			<div class=" mb-2 text-sm font-medium">Database</div>
+			<div class=" mb-2 text-sm font-medium">{$i18n.t('Database')}</div>

 			<div class="  flex w-full justify-between">
-				<!-- <div class=" self-center text-xs font-medium">Allow Chat Deletion</div> -->
+				<!-- <div class=" self-center text-xs font-medium">{$i18n.t('Allow Chat Deletion')}</div> -->

 				<button
 					class=" flex rounded-md py-1.5 px-3 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
@@ -46,7 +48,7 @@
 							/>
 						</svg>
 					</div>
-					<div class=" self-center text-sm font-medium">Download Database</div>
+					<div class=" self-center text-sm font-medium">{$i18n.t('Download Database')}</div>
 				</button>
 			</div>
 		</div>
@@ -1,4 +1,5 @@
 <script lang="ts">
+	import { getWebhookUrl, updateWebhookUrl } from '$lib/apis';
 	import {
 		getDefaultUserRole,
 		getJWTExpiresDuration,
@@ -7,13 +8,17 @@
 		updateDefaultUserRole,
 		updateJWTExpiresDuration
 	} from '$lib/apis/auths';
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');

 	export let saveHandler: Function;
 	let signUpEnabled = true;
 	let defaultUserRole = 'pending';
 	let JWTExpiresIn = '';

+	let webhookUrl = '';
+
 	const toggleSignUpEnabled = async () => {
 		signUpEnabled = await toggleSignUpEnabledStatus(localStorage.token);
 	};
@@ -26,27 +31,32 @@
 		JWTExpiresIn = await updateJWTExpiresDuration(localStorage.token, duration);
 	};

+	const updateWebhookUrlHandler = async () => {
+		webhookUrl = await updateWebhookUrl(localStorage.token, webhookUrl);
+	};
+
 	onMount(async () => {
 		signUpEnabled = await getSignUpEnabledStatus(localStorage.token);
 		defaultUserRole = await getDefaultUserRole(localStorage.token);
 		JWTExpiresIn = await getJWTExpiresDuration(localStorage.token);
+		webhookUrl = await getWebhookUrl(localStorage.token);
 	});
 </script>

 <form
 	class="flex flex-col h-full justify-between space-y-3 text-sm"
 	on:submit|preventDefault={() => {
-		// console.log('submit');
 		updateJWTExpiresDurationHandler(JWTExpiresIn);
+		updateWebhookUrlHandler();
 		saveHandler();
 	}}
 >
 	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
 		<div>
-			<div class=" mb-2 text-sm font-medium">General Settings</div>
+			<div class=" mb-2 text-sm font-medium">{$i18n.t('General Settings')}</div>

 			<div class="  flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">Enable New Sign Ups</div>
+				<div class=" self-center text-xs font-medium">{$i18n.t('Enable New Sign Ups')}</div>

 				<button
 					class="p-1 px-3 text-xs flex rounded transition"
@@ -66,7 +76,7 @@
 								d="M11.5 1A3.5 3.5 0 0 0 8 4.5V7H2.5A1.5 1.5 0 0 0 1 8.5v5A1.5 1.5 0 0 0 2.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 9.5 7V4.5a2 2 0 1 1 4 0v1.75a.75.75 0 0 0 1.5 0V4.5A3.5 3.5 0 0 0 11.5 1Z"
 							/>
 						</svg>
-						<span class="ml-2 self-center">Enabled</span>
+						<span class="ml-2 self-center">{$i18n.t('Enabled')}</span>
 					{:else}
 						<svg
 							xmlns="http://www.w3.org/2000/svg"
@@ -81,25 +91,25 @@
 							/>
 						</svg>

-						<span class="ml-2 self-center">Disabled</span>
+						<span class="ml-2 self-center">{$i18n.t('Disabled')}</span>
 					{/if}
 				</button>
 			</div>

 			<div class=" flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">Default User Role</div>
+				<div class=" self-center text-xs font-medium">{$i18n.t('Default User Role')}</div>
 				<div class="flex items-center relative">
 					<select
-						class="w-fit pr-8 rounded py-2 px-2 text-xs bg-transparent outline-none text-right"
+						class="dark:bg-gray-900 w-fit pr-8 rounded py-2 px-2 text-xs bg-transparent outline-none text-right"
 						bind:value={defaultUserRole}
 						placeholder="Select a theme"
 						on:change={(e) => {
 							updateDefaultUserRoleHandler(e.target.value);
 						}}
 					>
-						<option value="pending">Pending</option>
-						<option value="user">User</option>
-						<option value="admin">Admin</option>
+						<option value="pending">{$i18n.t('pending')}</option>
+						<option value="user">{$i18n.t('user')}</option>
+						<option value="admin">{$i18n.t('admin')}</option>
 					</select>
 				</div>
 			</div>
@@ -108,7 +118,24 @@

 			<div class=" w-full justify-between">
 				<div class="flex w-full justify-between">
-					<div class=" self-center text-xs font-medium">JWT Expiration</div>
+					<div class=" self-center text-xs font-medium">{$i18n.t('Webhook URL')}</div>
+				</div>
+
+				<div class="flex mt-2 space-x-2">
+					<input
+						class="w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
+						type="text"
+						placeholder={`https://example.com/webhook`}
+						bind:value={webhookUrl}
+					/>
+				</div>
+			</div>
+
+			<hr class=" dark:border-gray-700 my-3" />
+
+			<div class=" w-full justify-between">
+				<div class="flex w-full justify-between">
+					<div class=" self-center text-xs font-medium">{$i18n.t('JWT Expiration')}</div>
 				</div>

 				<div class="flex mt-2 space-x-2">
@@ -121,8 +148,9 @@
 				</div>

 				<div class="mt-2 text-xs text-gray-400 dark:text-gray-500">
-					Valid time units: <span class=" text-gray-300 font-medium"
-						>'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.</span
+					{$i18n.t('Valid time units:')}
+					<span class=" text-gray-300 font-medium"
+						>{$i18n.t("'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.")}</span
 					>
 				</div>
 			</div>
@@ -134,7 +162,7 @@
 			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
 			type="submit"
 		>
-			Save
+			{$i18n.t('Save')}
 		</button>
 	</div>
 </form>
@@ -1,10 +1,17 @@
 <script lang="ts">
+	import { getModelFilterConfig, updateModelFilterConfig } from '$lib/apis';
 	import { getSignUpEnabledStatus, toggleSignUpEnabledStatus } from '$lib/apis/auths';
 	import { getUserPermissions, updateUserPermissions } from '$lib/apis/users';
-	import { onMount } from 'svelte';
+
+	import { onMount, getContext } from 'svelte';
+	import { models } from '$lib/stores';
+
+	const i18n = getContext('i18n');

 	export let saveHandler: Function;

+	let whitelistEnabled = false;
+	let whitelistModels = [''];
 	let permissions = {
 		chat: {
 			deletion: true
@@ -13,6 +20,13 @@

 	onMount(async () => {
 		permissions = await getUserPermissions(localStorage.token);
+
+		const res = await getModelFilterConfig(localStorage.token);
+		if (res) {
+			whitelistEnabled = res.enabled;
+
+			whitelistModels = res.models.length > 0 ? res.models : [''];
+		}
 	});
 </script>

@@ -21,15 +35,17 @@
 	on:submit|preventDefault={async () => {
 		// console.log('submit');
 		await updateUserPermissions(localStorage.token, permissions);
+
+		await updateModelFilterConfig(localStorage.token, whitelistEnabled, whitelistModels);
 		saveHandler();
 	}}
 >
 	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
 		<div>
-			<div class=" mb-2 text-sm font-medium">User Permissions</div>
+			<div class=" mb-2 text-sm font-medium">{$i18n.t('User Permissions')}</div>

 			<div class="  flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">Allow Chat Deletion</div>
+				<div class=" self-center text-xs font-medium">{$i18n.t('Allow Chat Deletion')}</div>

 				<button
 					class="p-1 px-3 text-xs flex rounded transition"
@@ -49,7 +65,7 @@
 								d="M11.5 1A3.5 3.5 0 0 0 8 4.5V7H2.5A1.5 1.5 0 0 0 1 8.5v5A1.5 1.5 0 0 0 2.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 9.5 7V4.5a2 2 0 1 1 4 0v1.75a.75.75 0 0 0 1.5 0V4.5A3.5 3.5 0 0 0 11.5 1Z"
 							/>
 						</svg>
-						<span class="ml-2 self-center">Allow</span>
+						<span class="ml-2 self-center">{$i18n.t('Allow')}</span>
 					{:else}
 						<svg
 							xmlns="http://www.w3.org/2000/svg"
@@ -64,11 +80,112 @@
 							/>
 						</svg>

-						<span class="ml-2 self-center">Don't Allow</span>
+						<span class="ml-2 self-center">{$i18n.t("Don't Allow")}</span>
 					{/if}
 				</button>
 			</div>
 		</div>
+
+		<hr class=" dark:border-gray-700 my-2" />
+
+		<div class="mt-2 space-y-3 pr-1.5">
+			<div>
+				<div class="mb-2">
+					<div class="flex justify-between items-center text-xs">
+						<div class=" text-sm font-medium">{$i18n.t('Manage Models')}</div>
+					</div>
+				</div>
+
+				<div class=" space-y-3">
+					<div>
+						<div class="flex justify-between items-center text-xs">
+							<div class=" text-xs font-medium">{$i18n.t('Model Whitelisting')}</div>
+
+							<button
+								class=" text-xs font-medium text-gray-500"
+								type="button"
+								on:click={() => {
+									whitelistEnabled = !whitelistEnabled;
+								}}>{whitelistEnabled ? $i18n.t('On') : $i18n.t('Off')}</button
+							>
+						</div>
+					</div>
+
+					{#if whitelistEnabled}
+						<div>
+							<div class=" space-y-1.5">
+								{#each whitelistModels as modelId, modelIdx}
+									<div class="flex w-full">
+										<div class="flex-1 mr-2">
+											<select
+												class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+												bind:value={modelId}
+												placeholder="Select a model"
+											>
+												<option value="" disabled selected>{$i18n.t('Select a model')}</option>
+												{#each $models.filter((model) => model.id) as model}
+													<option value={model.id} class="bg-gray-100 dark:bg-gray-700"
+														>{model.name}</option
+													>
+												{/each}
+											</select>
+										</div>
+
+										{#if modelIdx === 0}
+											<button
+												class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-900 dark:text-white rounded-lg transition"
+												type="button"
+												on:click={() => {
+													if (whitelistModels.at(-1) !== '') {
+														whitelistModels = [...whitelistModels, ''];
+													}
+												}}
+											>
+												<svg
+													xmlns="http://www.w3.org/2000/svg"
+													viewBox="0 0 16 16"
+													fill="currentColor"
+													class="w-4 h-4"
+												>
+													<path
+														d="M8.75 3.75a.75.75 0 0 0-1.5 0v3.5h-3.5a.75.75 0 0 0 0 1.5h3.5v3.5a.75.75 0 0 0 1.5 0v-3.5h3.5a.75.75 0 0 0 0-1.5h-3.5v-3.5Z"
+													/>
+												</svg>
+											</button>
+										{:else}
+											<button
+												class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-900 dark:text-white rounded-lg transition"
+												type="button"
+												on:click={() => {
+													whitelistModels.splice(modelIdx, 1);
+													whitelistModels = whitelistModels;
+												}}
+											>
+												<svg
+													xmlns="http://www.w3.org/2000/svg"
+													viewBox="0 0 16 16"
+													fill="currentColor"
+													class="w-4 h-4"
+												>
+													<path d="M3.75 7.25a.75.75 0 0 0 0 1.5h8.5a.75.75 0 0 0 0-1.5h-8.5Z" />
+												</svg>
+											</button>
+										{/if}
+									</div>
+								{/each}
+							</div>
+
+							<div class="flex justify-end items-center text-xs mt-1.5 text-right">
+								<div class=" text-xs font-medium">
+									{whitelistModels.length}
+									{$i18n.t('Model(s) Whitelisted')}
+								</div>
+							</div>
+						</div>
+					{/if}
+				</div>
+			</div>
+		</div>
 	</div>

 	<div class="flex justify-end pt-3 text-sm font-medium">
@@ -76,7 +193,7 @@
 			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
 			type="submit"
 		>
-			Save
+			{$i18n.t('Save')}
 		</button>
 	</div>
 </form>
@@ -1,10 +1,13 @@
 <script>
+	import { getContext } from 'svelte';
 	import Modal from '../common/Modal.svelte';
 	import Database from './Settings/Database.svelte';

 	import General from './Settings/General.svelte';
 	import Users from './Settings/Users.svelte';

+	const i18n = getContext('i18n');
+
 	export let show = false;

 	let selectedTab = 'general';
@@ -13,7 +16,7 @@
 <Modal bind:show>
 	<div>
 		<div class=" flex justify-between dark:text-gray-300 px-5 py-4">
-			<div class=" text-lg font-medium self-center">Admin Settings</div>
+			<div class=" text-lg font-medium self-center">{$i18n.t('Admin Settings')}</div>
 			<button
 				class="self-center"
 				on:click={() => {
@@ -61,7 +64,7 @@
 							/>
 						</svg>
 					</div>
-					<div class=" self-center">General</div>
+					<div class=" self-center">{$i18n.t('General')}</div>
 				</button>

 				<button
@@ -85,7 +88,7 @@
 							/>
 						</svg>
 					</div>
-					<div class=" self-center">Users</div>
+					<div class=" self-center">{$i18n.t('Users')}</div>
 				</button>

 				<button
@@ -113,7 +116,7 @@
 							/>
 						</svg>
 					</div>
-					<div class=" self-center">Database</div>
+					<div class=" self-center">{$i18n.t('Database')}</div>
 				</button>
 			</div>
 			<div class="flex-1 md:min-h-[380px]">
@@ -1,6 +1,6 @@
 <script lang="ts">
 	import { toast } from 'svelte-sonner';
-	import { onMount, tick } from 'svelte';
+	import { onMount, tick, getContext } from 'svelte';
 	import { settings } from '$lib/stores';
 	import { blobToFile, calculateSHA256, findWordIndices } from '$lib/utils';

@@ -14,12 +14,14 @@
 	import { transcribeAudio } from '$lib/apis/audio';
 	import Tooltip from '../common/Tooltip.svelte';

+	const i18n = getContext('i18n');
+
 	export let submitPrompt: Function;
 	export let stopResponse: Function;

 	export let suggestionPrompts = [];
 	export let autoScroll = true;
-	let chatTextAreaElement:HTMLTextAreaElement
+	let chatTextAreaElement: HTMLTextAreaElement;
 	let filesInputElement;

 	let promptsElement;
@@ -209,11 +211,11 @@
 					// Event triggered when an error occurs
 					speechRecognition.onerror = function (event) {
 						console.log(event);
-						toast.error(`Speech recognition error: ${event.error}`);
+						toast.error($i18n.t(`Speech recognition error: {{error}}`, { error: event.error }));
 						isRecording = false;
 					};
 				} else {
-					toast.error('SpeechRecognition API is not supported in this browser.');
+					toast.error($i18n.t('SpeechRecognition API is not supported in this browser.'));
 				}
 			}
 		}
@@ -293,6 +295,13 @@

 		const dropZone = document.querySelector('body');

+		const handleKeyDown = (event: KeyboardEvent) => {
+			if (event.key === 'Escape') {
+				console.log('Escape');
+				dragged = false;
+			}
+		};
+
 		const onDragOver = (e) => {
 			e.preventDefault();
 			dragged = true;
@@ -319,37 +328,45 @@
 					];
 				};

-				const inputFiles = e.dataTransfer?.files;
+				const inputFiles = Array.from(e.dataTransfer?.files);

 				if (inputFiles && inputFiles.length > 0) {
-					const file = inputFiles[0];
-					console.log(file, file.name.split('.').at(-1));
-					if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
-						reader.readAsDataURL(file);
-					} else if (
-						SUPPORTED_FILE_TYPE.includes(file['type']) ||
-						SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
-					) {
-						uploadDoc(file);
-					} else {
-						toast.error(
-							`Unknown File Type '${file['type']}', but accepting and treating as plain text`
-						);
-						uploadDoc(file);
-					}
+					inputFiles.forEach((file) => {
+						console.log(file, file.name.split('.').at(-1));
+						if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
+							reader.readAsDataURL(file);
+						} else if (
+							SUPPORTED_FILE_TYPE.includes(file['type']) ||
+							SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
+						) {
+							uploadDoc(file);
+						} else {
+							toast.error(
+								$i18n.t(
+									`Unknown File Type '{{file_type}}', but accepting and treating as plain text`,
+									{ file_type: file['type'] }
+								)
+							);
+							uploadDoc(file);
+						}
+					});
 				} else {
-					toast.error(`File not found.`);
+					toast.error($i18n.t(`File not found.`));
 				}
 			}

 			dragged = false;
 		};

+		window.addEventListener('keydown', handleKeyDown);
+
 		dropZone?.addEventListener('dragover', onDragOver);
 		dropZone?.addEventListener('drop', onDrop);
 		dropZone?.addEventListener('dragleave', onDragLeave);

 		return () => {
+			window.removeEventListener('keydown', handleKeyDown);
+
 			dropZone?.removeEventListener('dragover', onDragOver);
 			dropZone?.removeEventListener('drop', onDrop);
 			dropZone?.removeEventListener('dragleave', onDragLeave);
@@ -359,12 +376,12 @@

 {#if dragged}
 	<div
-		class="fixed w-full h-full flex z-50 touch-none pointer-events-none"
+		class="fixed lg:w-[calc(100%-260px)] w-full h-full flex z-50 touch-none pointer-events-none"
 		id="dropzone"
 		role="region"
 		aria-label="Drag and Drop Container"
 	>
-		<div class="absolute rounded-xl w-full h-full backdrop-blur bg-gray-800/40 flex justify-center">
+		<div class="absolute w-full h-full backdrop-blur bg-gray-800/40 flex justify-center">
 			<div class="m-auto pt-64 flex flex-col justify-center">
 				<div class="max-w-md">
 					<AddFilesPlaceholder />
@@ -451,6 +468,7 @@
 					bind:files={inputFiles}
 					type="file"
 					hidden
+					multiple
 					on:change={async () => {
 						let reader = new FileReader();
 						reader.onload = (event) => {
@@ -466,24 +484,29 @@
 						};

 						if (inputFiles && inputFiles.length > 0) {
-							const file = inputFiles[0];
-							if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
-								reader.readAsDataURL(file);
-							} else if (
-								SUPPORTED_FILE_TYPE.includes(file['type']) ||
-								SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
-							) {
-								uploadDoc(file);
-								filesInputElement.value = '';
-							} else {
-								toast.error(
-									`Unknown File Type '${file['type']}', but accepting and treating as plain text`
-								);
-								uploadDoc(file);
-								filesInputElement.value = '';
-							}
+							const _inputFiles = Array.from(inputFiles);
+							_inputFiles.forEach((file) => {
+								if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
+									reader.readAsDataURL(file);
+								} else if (
+									SUPPORTED_FILE_TYPE.includes(file['type']) ||
+									SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
+								) {
+									uploadDoc(file);
+									filesInputElement.value = '';
+								} else {
+									toast.error(
+										$i18n.t(
+											`Unknown File Type '{{file_type}}', but accepting and treating as plain text`,
+											{ file_type: file['type'] }
+										)
+									);
+									uploadDoc(file);
+									filesInputElement.value = '';
+								}
+							});
 						} else {
-							toast.error(`File not found.`);
+							toast.error($i18n.t(`File not found.`));
 						}
 					}}
 				/>
@@ -570,7 +593,7 @@
 													{file.name}
 												</div>

-												<div class=" text-gray-500 text-sm">Document</div>
+												<div class=" text-gray-500 text-sm">{$i18n.t('Document')}</div>
 											</div>
 										</div>
 									{:else if file.type === 'collection'}
@@ -598,7 +621,7 @@
 													{file?.title ?? `#${file.name}`}
 												</div>

-												<div class=" text-gray-500 text-sm">Collection</div>
+												<div class=" text-gray-500 text-sm">{$i18n.t('Collection')}</div>
 											</div>
 										</div>
 									{/if}
@@ -632,7 +655,7 @@
 					<div class=" flex">
 						{#if fileUploadEnabled}
 							<div class=" self-end mb-2 ml-1">
-								<Tooltip content="Upload files">
+								<Tooltip content={$i18n.t('Upload files')}>
 									<button
 										class="bg-gray-50 hover:bg-gray-100 text-gray-800 dark:bg-gray-850 dark:text-white dark:hover:bg-gray-800 transition rounded-full p-1.5"
 										type="button"
@@ -664,8 +687,8 @@
 							placeholder={chatInputPlaceholder !== ''
 								? chatInputPlaceholder
 								: isRecording
-								? 'Listening...'
-								: 'Send a message'}
+								? $i18n.t('Listening...')
+								: $i18n.t('Send a Message')}
 							bind:value={prompt}
 							on:keypress={(e) => {
 								if (e.keyCode == 13 && !e.shiftKey) {
@@ -804,7 +827,7 @@

 						<div class="self-end mb-2 flex space-x-1 mr-1">
 							{#if messages.length == 0 || messages.at(-1).done == true}
-								<Tooltip content="Record voice">
+								<Tooltip content={$i18n.t('Record voice')}>
 									{#if speechRecognitionEnabled}
 										<button
 											id="voice-input-button"
@@ -873,7 +896,7 @@
 									{/if}
 								</Tooltip>

-								<Tooltip content="Send message">
+								<Tooltip content={$i18n.t('Send message')}>
 									<button
 										class="{prompt !== ''
 											? 'bg-black text-white hover:bg-gray-900 dark:bg-white dark:text-black dark:hover:bg-gray-100 '
@@ -919,7 +942,7 @@
 				</form>

 				<div class="mt-1.5 text-xs text-gray-500 text-center">
-					LLMs can make mistakes. Verify important information.
+					{$i18n.t('LLMs can make mistakes. Verify important information.')}
 				</div>
 			</div>
 		</div>
@@ -3,9 +3,11 @@

 	import { documents } from '$lib/stores';
 	import { removeFirstHashWord, isValidHttpUrl } from '$lib/utils';
-	import { tick } from 'svelte';
+	import { tick, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';

+	const i18n = getContext('i18n');
+
 	export let prompt = '';

 	const dispatch = createEventDispatcher();
@@ -117,7 +119,7 @@
 									{doc?.title ?? `#${doc.name}`}
 								</div>

-								<div class=" text-xs text-gray-600 line-clamp-1">Collection</div>
+								<div class=" text-xs text-gray-600 line-clamp-1">{$i18n.t('Collection')}</div>
 							{:else}
 								<div class=" font-medium text-black line-clamp-1">
 									#{doc.name} ({doc.filename})
@@ -140,7 +142,9 @@
 									confirmSelectWeb(url);
 								} else {
 									toast.error(
-										'Oops! Looks like the URL is invalid. Please double-check and try again.'
+										$i18n.t(
+											'Oops! Looks like the URL is invalid. Please double-check and try again.'
+										)
 									);
 								}
 							}}
@@ -149,7 +153,7 @@
 								{prompt.split(' ')?.at(0)?.substring(1)}
 							</div>

-							<div class=" text-xs text-gray-600 line-clamp-1">Web</div>
+							<div class=" text-xs text-gray-600 line-clamp-1">{$i18n.t('Web')}</div>
 						</button>
 					{/if}
 				</div>
@@ -2,9 +2,11 @@
 	import { generatePrompt } from '$lib/apis/ollama';
 	import { models } from '$lib/stores';
 	import { splitStream } from '$lib/utils';
-	import { tick } from 'svelte';
+	import { tick, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';

+	const i18n = getContext('i18n');
+
 	export let prompt = '';
 	export let user = null;

@@ -41,7 +43,7 @@
 		user = JSON.parse(JSON.stringify(model.name));
 		await tick();

-		chatInputPlaceholder = `'${model.name}' is thinking...`;
+		chatInputPlaceholder = $i18n.t('{{modelName}} is thinking...', { modelName: model.name });

 		const chatInputElement = document.getElementById('chat-textarea');

@@ -113,7 +115,9 @@
 					toast.error(error.error);
 				}
 			} else {
-				toast.error(`Uh-oh! There was an issue connecting to Ollama.`);
+				toast.error(
+					$i18n.t('Uh-oh! There was an issue connecting to {{provider}}.', { provider: 'llama' })
+				);
 			}
 		}

@@ -1,9 +1,11 @@
 <script lang="ts">
 	import { prompts } from '$lib/stores';
 	import { findWordIndices } from '$lib/utils';
-	import { tick } from 'svelte';
+	import { tick, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';

+	const i18n = getContext('i18n');
+
 	export let prompt = '';
 	let selectedCommandIdx = 0;
 	let filteredPromptCommands = [];
@@ -29,7 +31,7 @@

 		if (command.content.includes('{{CLIPBOARD}}')) {
 			const clipboardText = await navigator.clipboard.readText().catch((err) => {
-				toast.error('Failed to read clipboard contents');
+				toast.error($i18n.t('Failed to read clipboard contents'));
 				return '{{CLIPBOARD}}';
 			});

@@ -113,8 +115,9 @@
 					</div>

 					<div class="line-clamp-1">
-						Tip: Update multiple variable slots consecutively by pressing the tab key in the chat
-						input after each replacement.
+						{$i18n.t(
+							'Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.'
+						)}
 					</div>
 				</div>
 			</div>
@@ -2,7 +2,7 @@
 	import { v4 as uuidv4 } from 'uuid';

 	import { chats, config, modelfiles, settings, user } from '$lib/stores';
-	import { tick } from 'svelte';
+	import { tick, getContext } from 'svelte';

 	import { toast } from 'svelte-sonner';
 	import { getChatList, updateChatById } from '$lib/apis/chats';
@@ -12,8 +12,12 @@
 	import Placeholder from './Messages/Placeholder.svelte';
 	import Spinner from '../common/Spinner.svelte';
 	import { imageGenerations } from '$lib/apis/images';
+	import { copyToClipboard } from '$lib/utils';
+
+	const i18n = getContext('i18n');

 	export let chatId = '';
+	export let readOnly = false;
 	export let sendPrompt: Function;
 	export let continueGeneration: Function;
 	export let regenerateResponse: Function;
@@ -39,40 +43,11 @@
 		element.scrollTop = element.scrollHeight;
 	};

-	const copyToClipboard = (text) => {
-		if (!navigator.clipboard) {
-			var textArea = document.createElement('textarea');
-			textArea.value = text;
-
-			// Avoid scrolling to bottom
-			textArea.style.top = '0';
-			textArea.style.left = '0';
-			textArea.style.position = 'fixed';
-
-			document.body.appendChild(textArea);
-			textArea.focus();
-			textArea.select();
-
-			try {
-				var successful = document.execCommand('copy');
-				var msg = successful ? 'successful' : 'unsuccessful';
-				console.log('Fallback: Copying text command was ' + msg);
-			} catch (err) {
-				console.error('Fallback: Oops, unable to copy', err);
-			}
-
-			document.body.removeChild(textArea);
-			return;
+	const copyToClipboardWithToast = async (text) => {
+		const res = await copyToClipboard(text);
+		if (res) {
+			toast.success($i18n.t('Copying to clipboard was successful!'));
 		}
-		navigator.clipboard.writeText(text).then(
-			function () {
-				console.log('Async: Copying to clipboard was successful!');
-				toast.success('Copying to clipboard was successful!');
-			},
-			function (err) {
-				console.error('Async: Could not copy text: ', err);
-			}
-		);
 	};

 	const confirmEditMessage = async (messageId, content) => {
@@ -104,12 +79,8 @@
 		await sendPrompt(userPrompt, userMessageId, chatId);
 	};

-	const confirmEditResponseMessage = async (messageId, content) => {
-		history.messages[messageId].originalContent = history.messages[messageId].content;
-		history.messages[messageId].content = content;
-
+	const updateChatMessages = async () => {
 		await tick();
-
 		await updateChatById(localStorage.token, chatId, {
 			messages: messages,
 			history: history
@@ -118,15 +89,20 @@
 		await chats.set(await getChatList(localStorage.token));
 	};

-	const rateMessage = async (messageId, rating) => {
-		history.messages[messageId].rating = rating;
-		await tick();
-		await updateChatById(localStorage.token, chatId, {
-			messages: messages,
-			history: history
-		});
+	const confirmEditResponseMessage = async (messageId, content) => {
+		history.messages[messageId].originalContent = history.messages[messageId].content;
+		history.messages[messageId].content = content;

-		await chats.set(await getChatList(localStorage.token));
+		await updateChatMessages();
+	};
+
+	const rateMessage = async (messageId, rating) => {
+		history.messages[messageId].annotation = {
+			...history.messages[messageId].annotation,
+			rating: rating
+		};
+
+		await updateChatMessages();
 	};

 	const showPreviousMessage = async (message) => {
@@ -315,6 +291,7 @@
 							<UserMessage
 								on:delete={() => messageDeleteHandler(message.id)}
 								user={$user}
+								{readOnly}
 								{message}
 								isFirstMessage={messageIdx === 0}
 								siblings={message.parentId !== null
@@ -325,7 +302,7 @@
 								{confirmEditMessage}
 								{showPreviousMessage}
 								{showNextMessage}
-								{copyToClipboard}
+								copyToClipboard={copyToClipboardWithToast}
 							/>
 						{:else}
 							<ResponseMessage
@@ -333,11 +310,13 @@
 								modelfiles={selectedModelfiles}
 								siblings={history.messages[message.parentId]?.childrenIds ?? []}
 								isLastMessage={messageIdx + 1 === messages.length}
+								{readOnly}
+								{updateChatMessages}
 								{confirmEditResponseMessage}
 								{showPreviousMessage}
 								{showNextMessage}
 								{rateMessage}
-								{copyToClipboard}
+								copyToClipboard={copyToClipboardWithToast}
 								{continueGeneration}
 								{regenerateResponse}
 								on:save={async (e) => {
@@ -1,7 +1,9 @@
 <script lang="ts">
 	import { WEBUI_BASE_URL } from '$lib/constants';
 	import { user } from '$lib/stores';
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');

 	export let models = [];
 	export let modelfiles = [];
@@ -31,7 +33,7 @@
 							<img
 								src={modelfiles[model]?.imageUrl ?? `${WEBUI_BASE_URL}/static/favicon.png`}
 								alt="modelfile"
-								class=" w-14 rounded-full border-[1px] border-gray-200 dark:border-none"
+								class=" size-12 rounded-full border-[1px] border-gray-200 dark:border-none"
 								draggable="false"
 							/>
 						{:else}
@@ -39,7 +41,7 @@
 								src={models.length === 1
 									? `${WEBUI_BASE_URL}/static/favicon.png`
 									: `${WEBUI_BASE_URL}/static/favicon.png`}
-								class=" w-14 rounded-full border-[1px] border-gray-200 dark:border-none"
+								class=" size-12 rounded-full border-[1px] border-gray-200 dark:border-none"
 								alt="logo"
 								draggable="false"
 							/>
@@ -64,9 +66,9 @@
 					</div>
 				{/if}
 			{:else}
-				<div class=" line-clamp-1">Hello, {$user.name}</div>
+				<div class=" line-clamp-1">{$i18n.t('Hello, {{name}}', { name: $user.name })}</div>

-				<div>How can I help you today?</div>
+				<div>{$i18n.t('How can I help you today?')}</div>
 			{/if}
 		</div>
 	</div>
@@ -0,0 +1,129 @@
+<script lang="ts">
+	import { toast } from 'svelte-sonner';
+
+	import { createEventDispatcher, onMount, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');
+
+	const dispatch = createEventDispatcher();
+
+	export let messageId = null;
+	export let show = false;
+	export let message;
+
+	let LIKE_REASONS = [];
+	let DISLIKE_REASONS = [];
+
+	function loadReasons() {
+		LIKE_REASONS = [
+			$i18n.t('Accurate information'),
+			$i18n.t('Followed instructions perfectly'),
+			$i18n.t('Showcased creativity'),
+			$i18n.t('Positive attitude'),
+			$i18n.t('Attention to detail'),
+			$i18n.t('Thorough explanation'),
+			$i18n.t('Other')
+		];
+
+		DISLIKE_REASONS = [
+			$i18n.t("Don't like the style"),
+			$i18n.t('Not factually correct'),
+			$i18n.t("Didn't fully follow instructions"),
+			$i18n.t("Refused when it shouldn't have"),
+			$i18n.t('Being lazy'),
+			$i18n.t('Other')
+		];
+	}
+
+	let reasons = [];
+	let selectedReason = null;
+	let comment = '';
+
+	$: if (message.annotation.rating === 1) {
+		reasons = LIKE_REASONS;
+	} else if (message.annotation.rating === -1) {
+		reasons = DISLIKE_REASONS;
+	}
+
+	onMount(() => {
+		selectedReason = message.annotation.reason;
+		comment = message.annotation.comment;
+		loadReasons();
+	});
+
+	const submitHandler = () => {
+		console.log('submitHandler');
+
+		message.annotation.reason = selectedReason;
+		message.annotation.comment = comment;
+
+		dispatch('submit');
+
+		toast.success($i18n.t('Thanks for your feedback!'));
+		show = false;
+	};
+</script>
+
+<div
+	class=" my-2.5 rounded-xl px-4 py-3 border dark:border-gray-850"
+	id="message-feedback-{messageId}"
+>
+	<div class="flex justify-between items-center">
+		<div class=" text-sm">{$i18n.t('Tell us more:')}</div>
+
+		<button
+			on:click={() => {
+				show = false;
+			}}
+		>
+			<svg
+				xmlns="http://www.w3.org/2000/svg"
+				fill="none"
+				viewBox="0 0 24 24"
+				stroke-width="1.5"
+				stroke="currentColor"
+				class="size-4"
+			>
+				<path stroke-linecap="round" stroke-linejoin="round" d="M6 18 18 6M6 6l12 12" />
+			</svg>
+		</button>
+	</div>
+
+	{#if reasons.length > 0}
+		<div class="flex flex-wrap gap-2 text-sm mt-2.5">
+			{#each reasons as reason}
+				<button
+					class="px-3.5 py-1 border dark:border-gray-850 hover:bg-gray-100 dark:hover:bg-gray-850 {selectedReason ===
+					reason
+						? 'bg-gray-200 dark:bg-gray-800'
+						: ''} transition rounded-lg"
+					on:click={() => {
+						selectedReason = reason;
+					}}
+				>
+					{reason}
+				</button>
+			{/each}
+		</div>
+	{/if}
+
+	<div class="mt-2">
+		<textarea
+			bind:value={comment}
+			class="w-full text-sm px-1 py-2 bg-transparent outline-none resize-none rounded-xl"
+			placeholder={$i18n.t('Feel free to add specific details')}
+			rows="2"
+		/>
+	</div>
+
+	<div class="mt-2 flex justify-end">
+		<button
+			class=" bg-emerald-700 text-white text-sm font-medium rounded-lg px-3.5 py-1.5"
+			on:click={() => {
+				submitHandler();
+			}}
+		>
+			Submit
+		</button>
+	</div>
+</div>
@@ -6,15 +6,23 @@
 	import auto_render from 'katex/dist/contrib/auto-render.mjs';
 	import 'katex/dist/katex.min.css';

+	import { fade } from 'svelte/transition';
 	import { createEventDispatcher } from 'svelte';
-	import { onMount, tick } from 'svelte';
+	import { onMount, tick, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');

 	const dispatch = createEventDispatcher();

 	import { config, settings } from '$lib/stores';
-	import { synthesizeOpenAISpeech } from '$lib/apis/openai';
+	import { synthesizeOpenAISpeech } from '$lib/apis/audio';
 	import { imageGenerations } from '$lib/apis/images';
-	import { extractSentences } from '$lib/utils';
+	import {
+		approximateToHumanReadable,
+		extractSentences,
+		revertSanitizedResponseContent,
+		sanitizeResponseContent
+	} from '$lib/utils';

 	import Name from './Name.svelte';
 	import ProfileImage from './ProfileImage.svelte';
@@ -23,6 +31,7 @@
 	import Image from '$lib/components/common/Image.svelte';
 	import { WEBUI_BASE_URL } from '$lib/constants';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import RateComment from './RateComment.svelte';

 	export let modelfiles = [];
 	export let message;
@@ -30,6 +39,9 @@

 	export let isLastMessage = true;

+	export let readOnly = false;
+
+	export let updateChatMessages: Function;
 	export let confirmEditResponseMessage: Function;
 	export let showPreviousMessage: Function;
 	export let showNextMessage: Function;
@@ -51,7 +63,9 @@
 	let loadingSpeech = false;
 	let generatingImage = false;

-	$: tokens = marked.lexer(message.content);
+	let showRateComment = false;
+
+	$: tokens = marked.lexer(sanitizeResponseContent(message.content));

 	const renderer = new marked.Renderer();

@@ -109,7 +123,10 @@
                    eval_count: ${message.info.eval_count ?? 'N/A'}<br/>
                    eval_duration: ${
 											Math.round(((message.info.eval_duration ?? 0) / 1000000) * 100) / 100 ?? 'N/A'
-										}ms</span>`,
+										}ms<br/>
+                    approximate_total: ${approximateToHumanReadable(
+											message.info.total_duration
+										)}</span>`,
 				allowHTML: true
 			});
 		}
@@ -125,7 +142,7 @@
 				// • auto-render specific keys, e.g.:
 				delimiters: [
 					{ left: '$$', right: '$$', display: false },
-					{ left: '$', right: '$', display: false },
+					{ left: '$ ', right: ' $', display: false },
 					{ left: '\\(', right: '\\)', display: false },
 					{ left: '\\[', right: '\\]', display: false },
 					{ left: '[ ', right: ' ]', display: false }
@@ -159,10 +176,12 @@

 	const toggleSpeakMessage = async () => {
 		if (speaking) {
-			speechSynthesis.cancel();
+			try {
+				speechSynthesis.cancel();

-			sentencesAudio[speakingIdx].pause();
-			sentencesAudio[speakingIdx].currentTime = 0;
+				sentencesAudio[speakingIdx].pause();
+				sentencesAudio[speakingIdx].currentTime = 0;
+			} catch {}

 			speaking = null;
 			speakingIdx = null;
@@ -204,6 +223,10 @@
 						sentence
 					).catch((error) => {
 						toast.error(error);
+
+						speaking = null;
+						loadingSpeech = false;
+
 						return null;
 					});

@@ -213,7 +236,6 @@
 						const audio = new Audio(blobUrl);
 						sentencesAudio[idx] = audio;
 						loadingSpeech = false;
-
 						lastPlayedAudioPromise = lastPlayedAudioPromise.then(() => playAudio(idx));
 					}
 				}
@@ -276,13 +298,15 @@

 	const generateImage = async (message) => {
 		generatingImage = true;
-		const res = await imageGenerations(localStorage.token, message.content);
+		const res = await imageGenerations(localStorage.token, message.content).catch((error) => {
+			toast.error(error);
+		});
 		console.log(res);

 		if (res) {
-			message.files = res.images.map((image) => ({
+			message.files = res.map((image) => ({
 				type: 'image',
-				url: `data:image/png;base64,${image}`
+				url: `${image.url}`
 			}));

 			dispatch('save', message);
@@ -313,7 +337,7 @@

 				{#if message.timestamp}
 					<span class=" invisible group-hover:visible text-gray-400 text-xs font-medium">
-						{dayjs(message.timestamp * 1000).format('DD/MM/YYYY HH:mm')}
+						{dayjs(message.timestamp * 1000).format($i18n.t('DD/MM/YYYY HH:mm'))}
 					</span>
 				{/if}
 			</Name>
@@ -357,7 +381,7 @@
 											editMessageConfirmHandler();
 										}}
 									>
-										Save
+										{$i18n.t('Save')}
 									</button>

 									<button
@@ -366,7 +390,7 @@
 											cancelEditMessage();
 										}}
 									>
-										Cancel
+										{$i18n.t('Cancel')}
 									</button>
 								</div>
 							</div>
@@ -398,8 +422,10 @@
 								{:else}
 									{#each tokens as token}
 										{#if token.type === 'code'}
-											<!-- {token.text} -->
-											<CodeBlock lang={token.lang} code={token.text} />
+											<CodeBlock
+												lang={token.lang}
+												code={revertSanitizedResponseContent(token.text)}
+											/>
 										{:else}
 											{@html marked.parse(token.raw, {
 												...defaults,
@@ -464,31 +490,33 @@
 											</div>
 										{/if}

-										<Tooltip content="Edit" placement="bottom">
-											<button
-												class="{isLastMessage
-													? 'visible'
-													: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition"
-												on:click={() => {
-													editMessageHandler();
-												}}
-											>
-												<svg
-													xmlns="http://www.w3.org/2000/svg"
-													fill="none"
-													viewBox="0 0 24 24"
-													stroke-width="1.5"
-													stroke="currentColor"
-													class="w-4 h-4"
+										{#if !readOnly}
+											<Tooltip content="Edit" placement="bottom">
+												<button
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition"
+													on:click={() => {
+														editMessageHandler();
+													}}
 												>
-													<path
-														stroke-linecap="round"
-														stroke-linejoin="round"
-														d="M16.862 4.487l1.687-1.688a1.875 1.875 0 112.652 2.652L6.832 19.82a4.5 4.5 0 01-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 011.13-1.897L16.863 4.487zm0 0L19.5 7.125"
-													/>
-												</svg>
-											</button>
-										</Tooltip>
+													<svg
+														xmlns="http://www.w3.org/2000/svg"
+														fill="none"
+														viewBox="0 0 24 24"
+														stroke-width="2"
+														stroke="currentColor"
+														class="w-4 h-4"
+													>
+														<path
+															stroke-linecap="round"
+															stroke-linejoin="round"
+															d="M16.862 4.487l1.687-1.688a1.875 1.875 0 112.652 2.652L6.832 19.82a4.5 4.5 0 01-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 011.13-1.897L16.863 4.487zm0 0L19.5 7.125"
+														/>
+													</svg>
+												</button>
+											</Tooltip>
+										{/if}

 										<Tooltip content="Copy" placement="bottom">
 											<button
@@ -503,7 +531,7 @@
 													xmlns="http://www.w3.org/2000/svg"
 													fill="none"
 													viewBox="0 0 24 24"
-													stroke-width="1.5"
+													stroke-width="2"
 													stroke="currentColor"
 													class="w-4 h-4"
 												>
@@ -516,59 +544,76 @@
 											</button>
 										</Tooltip>

-										<Tooltip content="Good Response" placement="bottom">
-											<button
-												class="{isLastMessage
-													? 'visible'
-													: 'invisible group-hover:visible'} p-1 rounded {message.rating === 1
-													? 'bg-gray-100 dark:bg-gray-800'
-													: ''} dark:hover:text-white hover:text-black transition"
-												on:click={() => {
-													rateMessage(message.id, 1);
-												}}
-											>
-												<svg
-													stroke="currentColor"
-													fill="none"
-													stroke-width="2"
-													viewBox="0 0 24 24"
-													stroke-linecap="round"
-													stroke-linejoin="round"
-													class="w-4 h-4"
-													xmlns="http://www.w3.org/2000/svg"
-													><path
-														d="M14 9V5a3 3 0 0 0-3-3l-4 9v11h11.28a2 2 0 0 0 2-1.7l1.38-9a2 2 0 0 0-2-2.3zM7 22H4a2 2 0 0 1-2-2v-7a2 2 0 0 1 2-2h3"
-													/></svg
-												>
-											</button>
-										</Tooltip>
+										{#if !readOnly}
+											<Tooltip content="Good Response" placement="bottom">
+												<button
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded {message?.annotation
+														?.rating === 1
+														? 'bg-gray-100 dark:bg-gray-800'
+														: ''} dark:hover:text-white hover:text-black transition"
+													on:click={() => {
+														rateMessage(message.id, 1);
+														showRateComment = true;

-										<Tooltip content="Bad Response" placement="bottom">
-											<button
-												class="{isLastMessage
-													? 'visible'
-													: 'invisible group-hover:visible'} p-1 rounded {message.rating === -1
-													? 'bg-gray-100 dark:bg-gray-800'
-													: ''} dark:hover:text-white hover:text-black transition"
-												on:click={() => {
-													rateMessage(message.id, -1);
-												}}
-											>
-												<svg
-													stroke="currentColor"
-													fill="none"
-													stroke-width="2"
-													viewBox="0 0 24 24"
-													stroke-linecap="round"
-													stroke-linejoin="round"
-													class="w-4 h-4"
-													xmlns="http://www.w3.org/2000/svg"
-													><path
-														d="M10 15v4a3 3 0 0 0 3 3l4-9V2H5.72a2 2 0 0 0-2 1.7l-1.38 9a2 2 0 0 0 2 2.3zm7-13h2.67A2.31 2.31 0 0 1 22 4v7a2.31 2.31 0 0 1-2.33 2H17"
-													/></svg
+														window.setTimeout(() => {
+															document
+																.getElementById(`message-feedback-${message.id}`)
+																?.scrollIntoView();
+														}, 0);
+													}}
 												>
-											</button>
-										</Tooltip>
+													<svg
+														stroke="currentColor"
+														fill="none"
+														stroke-width="2"
+														viewBox="0 0 24 24"
+														stroke-linecap="round"
+														stroke-linejoin="round"
+														class="w-4 h-4"
+														xmlns="http://www.w3.org/2000/svg"
+														><path
+															d="M14 9V5a3 3 0 0 0-3-3l-4 9v11h11.28a2 2 0 0 0 2-1.7l1.38-9a2 2 0 0 0-2-2.3zM7 22H4a2 2 0 0 1-2-2v-7a2 2 0 0 1 2-2h3"
+														/></svg
+													>
+												</button>
+											</Tooltip>
+
+											<Tooltip content="Bad Response" placement="bottom">
+												<button
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded {message?.annotation
+														?.rating === -1
+														? 'bg-gray-100 dark:bg-gray-800'
+														: ''} dark:hover:text-white hover:text-black transition"
+													on:click={() => {
+														rateMessage(message.id, -1);
+														showRateComment = true;
+														window.setTimeout(() => {
+															document
+																.getElementById(`message-feedback-${message.id}`)
+																?.scrollIntoView();
+														}, 0);
+													}}
+												>
+													<svg
+														stroke="currentColor"
+														fill="none"
+														stroke-width="2"
+														viewBox="0 0 24 24"
+														stroke-linecap="round"
+														stroke-linejoin="round"
+														class="w-4 h-4"
+														xmlns="http://www.w3.org/2000/svg"
+														><path
+															d="M10 15v4a3 3 0 0 0 3 3l4-9V2H5.72a2 2 0 0 0-2 1.7l-1.38 9a2 2 0 0 0 2 2.3zm7-13h2.67A2.31 2.31 0 0 1 22 4v7a2.31 2.31 0 0 1-2.33 2H17"
+														/></svg
+													>
+												</button>
+											</Tooltip>
+										{/if}

 										<Tooltip content="Read Aloud" placement="bottom">
 											<button
@@ -622,7 +667,7 @@
 														xmlns="http://www.w3.org/2000/svg"
 														fill="none"
 														viewBox="0 0 24 24"
-														stroke-width="1.5"
+														stroke-width="2"
 														stroke="currentColor"
 														class="w-4 h-4"
 													>
@@ -637,7 +682,7 @@
 														xmlns="http://www.w3.org/2000/svg"
 														fill="none"
 														viewBox="0 0 24 24"
-														stroke-width="1.5"
+														stroke-width="2"
 														stroke="currentColor"
 														class="w-4 h-4"
 													>
@@ -651,7 +696,7 @@
 											</button>
 										</Tooltip>

-										{#if $config.images}
+										{#if $config.images && !readOnly}
 											<Tooltip content="Generate Image" placement="bottom">
 												<button
 													class="{isLastMessage
@@ -703,7 +748,7 @@
 															xmlns="http://www.w3.org/2000/svg"
 															fill="none"
 															viewBox="0 0 24 24"
-															stroke-width="1.5"
+															stroke-width="2"
 															stroke="currentColor"
 															class="w-4 h-4"
 														>
@@ -733,7 +778,7 @@
 														xmlns="http://www.w3.org/2000/svg"
 														fill="none"
 														viewBox="0 0 24 24"
-														stroke-width="1.5"
+														stroke-width="2"
 														stroke="currentColor"
 														class="w-4 h-4"
 													>
@@ -747,7 +792,7 @@
 											</Tooltip>
 										{/if}

-										{#if isLastMessage}
+										{#if isLastMessage && !readOnly}
 											<Tooltip content="Continue Response" placement="bottom">
 												<button
 													type="button"
@@ -762,7 +807,7 @@
 														xmlns="http://www.w3.org/2000/svg"
 														fill="none"
 														viewBox="0 0 24 24"
-														stroke-width="1.5"
+														stroke-width="2"
 														stroke="currentColor"
 														class="w-4 h-4"
 													>
@@ -792,7 +837,7 @@
 														xmlns="http://www.w3.org/2000/svg"
 														fill="none"
 														viewBox="0 0 24 24"
-														stroke-width="1.5"
+														stroke-width="2"
 														stroke="currentColor"
 														class="w-4 h-4"
 													>
@@ -807,6 +852,17 @@
 										{/if}
 									</div>
 								{/if}
+
+								{#if showRateComment}
+									<RateComment
+										messageId={message.id}
+										bind:show={showRateComment}
+										bind:message
+										on:submit={() => {
+											updateChatMessages();
+										}}
+									/>
+								{/if}
 							</div>
 						{/if}
 					</div>
@@ -1,18 +1,21 @@
 <script lang="ts">
 	import dayjs from 'dayjs';

-	import { tick, createEventDispatcher } from 'svelte';
+	import { tick, createEventDispatcher, getContext } from 'svelte';
 	import Name from './Name.svelte';
 	import ProfileImage from './ProfileImage.svelte';
 	import { modelfiles, settings } from '$lib/stores';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';

+	const i18n = getContext('i18n');
+
 	const dispatch = createEventDispatcher();

 	export let user;
 	export let message;
 	export let siblings;
 	export let isFirstMessage: boolean;
+	export let readOnly: boolean;

 	export let confirmEditMessage: Function;
 	export let showPreviousMessage: Function;
@@ -65,17 +68,18 @@
 					{#if $modelfiles.map((modelfile) => modelfile.tagName).includes(message.user)}
 						{$modelfiles.find((modelfile) => modelfile.tagName === message.user)?.title}
 					{:else}
-						You <span class=" text-gray-500 text-sm font-medium">{message?.user ?? ''}</span>
+						{$i18n.t('You')}
+						<span class=" text-gray-500 text-sm font-medium">{message?.user ?? ''}</span>
 					{/if}
 				{:else if $settings.showUsername}
 					{user.name}
 				{:else}
-					You
+					{$i18n.t('You')}
 				{/if}

 				{#if message.timestamp}
 					<span class=" invisible group-hover:visible text-gray-400 text-xs font-medium">
-						{dayjs(message.timestamp * 1000).format('DD/MM/YYYY HH:mm')}
+						{dayjs(message.timestamp * 1000).format($i18n.t('DD/MM/YYYY HH:mm'))}
 					</span>
 				{/if}
 			</Name>
@@ -123,7 +127,7 @@
 											{file.name}
 										</div>

-										<div class=" text-gray-500 text-sm">Document</div>
+										<div class=" text-gray-500 text-sm">{$i18n.t('Document')}</div>
 									</div>
 								</button>
 							{:else if file.type === 'collection'}
@@ -152,7 +156,7 @@
 											{file?.title ?? `#${file.name}`}
 										</div>

-										<div class=" text-gray-500 text-sm">Collection</div>
+										<div class=" text-gray-500 text-sm">{$i18n.t('Collection')}</div>
 									</div>
 								</button>
 							{/if}
@@ -172,25 +176,39 @@
 							e.target.style.height = '';
 							e.target.style.height = `${e.target.scrollHeight}px`;
 						}}
+						on:keydown={(e) => {
+							if (e.key === 'Escape') {
+								document.getElementById('close-edit-message-button')?.click();
+							}
+
+							const isCmdOrCtrlPressed = e.metaKey || e.ctrlKey;
+							const isEnterPressed = e.key === 'Enter';
+
+							if (isCmdOrCtrlPressed && isEnterPressed) {
+								document.getElementById('save-edit-message-button')?.click();
+							}
+						}}
 					/>

 					<div class=" mt-2 mb-1 flex justify-center space-x-2 text-sm font-medium">
 						<button
+							id="save-edit-message-button"
 							class="px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded-lg"
 							on:click={() => {
 								editMessageConfirmHandler();
 							}}
 						>
-							Save & Submit
+							{$i18n.t('Save & Submit')}
 						</button>

 						<button
+							id="close-edit-message-button"
 							class=" px-4 py-2 hover:bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 text-gray-700 dark:text-gray-100 transition outline outline-1 outline-gray-200 dark:outline-gray-600 rounded-lg"
 							on:click={() => {
 								cancelEditMessage();
 							}}
 						>
-							Cancel
+							{$i18n.t('Cancel')}
 						</button>
 					</div>
 				</div>
@@ -247,29 +265,31 @@
 							</div>
 						{/if}

-						<Tooltip content="Edit" placement="bottom">
-							<button
-								class="invisible group-hover:visible p-1 rounded dark:hover:text-white hover:text-black transition edit-user-message-button"
-								on:click={() => {
-									editMessageHandler();
-								}}
-							>
-								<svg
-									xmlns="http://www.w3.org/2000/svg"
-									fill="none"
-									viewBox="0 0 24 24"
-									stroke-width="1.5"
-									stroke="currentColor"
-									class="w-4 h-4"
+						{#if !readOnly}
+							<Tooltip content="Edit" placement="bottom">
+								<button
+									class="invisible group-hover:visible p-1 rounded dark:hover:text-white hover:text-black transition edit-user-message-button"
+									on:click={() => {
+										editMessageHandler();
+									}}
 								>
-									<path
-										stroke-linecap="round"
-										stroke-linejoin="round"
-										d="M16.862 4.487l1.687-1.688a1.875 1.875 0 112.652 2.652L6.832 19.82a4.5 4.5 0 01-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 011.13-1.897L16.863 4.487zm0 0L19.5 7.125"
-									/>
-								</svg>
-							</button>
-						</Tooltip>
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										fill="none"
+										viewBox="0 0 24 24"
+										stroke-width="2"
+										stroke="currentColor"
+										class="w-4 h-4"
+									>
+										<path
+											stroke-linecap="round"
+											stroke-linejoin="round"
+											d="M16.862 4.487l1.687-1.688a1.875 1.875 0 112.652 2.652L6.832 19.82a4.5 4.5 0 01-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 011.13-1.897L16.863 4.487zm0 0L19.5 7.125"
+										/>
+									</svg>
+								</button>
+							</Tooltip>
+						{/if}

 						<Tooltip content="Copy" placement="bottom">
 							<button
@@ -282,7 +302,7 @@
 									xmlns="http://www.w3.org/2000/svg"
 									fill="none"
 									viewBox="0 0 24 24"
-									stroke-width="1.5"
+									stroke-width="2"
 									stroke="currentColor"
 									class="w-4 h-4"
 								>
@@ -295,7 +315,7 @@
 							</button>
 						</Tooltip>

-						{#if !isFirstMessage}
+						{#if !isFirstMessage && !readOnly}
 							<Tooltip content="Delete" placement="bottom">
 								<button
 									class="invisible group-hover:visible p-1 rounded dark:hover:text-white hover:text-black transition"
@@ -307,7 +327,7 @@
 										xmlns="http://www.w3.org/2000/svg"
 										fill="none"
 										viewBox="0 0 24 24"
-										stroke-width="1.5"
+										stroke-width="2"
 										stroke="currentColor"
 										class="w-4 h-4"
 									>
@@ -1,8 +1,14 @@
 <script lang="ts">
+	import { Collapsible } from 'bits-ui';
+
 	import { setDefaultModels } from '$lib/apis/configs';
 	import { models, showSettings, settings, user } from '$lib/stores';
-	import { onMount, tick } from 'svelte';
+	import { onMount, tick, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';
+	import Selector from './ModelSelector/Selector.svelte';
+	import Tooltip from '../common/Tooltip.svelte';
+
+	const i18n = getContext('i18n');

 	export let selectedModels = [''];
 	export let disabled = false;
@@ -10,7 +16,7 @@
 	const saveDefaultModel = async () => {
 		const hasEmptyModel = selectedModels.filter((it) => it === '');
 		if (hasEmptyModel.length) {
-			toast.error('Choose a model before saving...');
+			toast.error($i18n.t('Choose a model before saving...'));
 			return;
 		}
 		settings.set({ ...$settings, models: selectedModels });
@@ -20,7 +26,7 @@
 			console.log('setting default models globally');
 			await setDefaultModels(localStorage.token, selectedModels.join(','));
 		}
-		toast.success('Default model updated');
+		toast.success($i18n.t('Default model updated'));
 	};

 	$: if (selectedModels.length > 0 && $models.length > 0) {
@@ -30,108 +36,76 @@
 	}
 </script>

-<div class="flex flex-col my-2">
+<div class="flex flex-col mt-0.5 w-full">
 	{#each selectedModels as selectedModel, selectedModelIdx}
-		<div class="flex">
-			<select
-				id="models"
-				class="outline-none bg-transparent text-lg font-semibold rounded-lg block w-full placeholder-gray-400"
-				bind:value={selectedModel}
-				{disabled}
-			>
-				<option class=" text-gray-700" value="" selected disabled>Select a model</option>
+		<div class="flex w-full">
+			<div class="overflow-hidden w-full">
+				<div class="mr-0.5 max-w-full">
+					<Selector
+						placeholder={$i18n.t('Select a model')}
+						items={$models
+							.filter((model) => model.name !== 'hr')
+							.map((model) => ({
+								value: model.id,
+								label: model.name,
+								info: model
+							}))}
+						bind:value={selectedModel}
+					/>
+				</div>
+			</div>

-				{#each $models as model}
-					{#if model.name === 'hr'}
-						<hr />
-					{:else}
-						<option value={model.id} class="text-gray-700 text-lg"
-							>{model.name +
-								`${model.size ? ` (${(model.size / 1024 ** 3).toFixed(1)}GB)` : ''}`}</option
+			{#if selectedModelIdx === 0}
+				<div class="  self-center mr-2 disabled:text-gray-600 disabled:hover:text-gray-600">
+					<Tooltip content="Add Model">
+						<button
+							class=" "
+							{disabled}
+							on:click={() => {
+								selectedModels = [...selectedModels, ''];
+							}}
 						>
-					{/if}
-				{/each}
-			</select>
-
-			{#if selectedModelIdx === 0}
-				<button
-					class="  self-center {selectedModelIdx === 0
-						? 'mr-3'
-						: 'mr-7'} disabled:text-gray-600 disabled:hover:text-gray-600"
-					{disabled}
-					on:click={() => {
-						selectedModels = [...selectedModels, ''];
-					}}
-				>
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						fill="none"
-						viewBox="0 0 24 24"
-						stroke-width="1.5"
-						stroke="currentColor"
-						class="w-4 h-4"
-					>
-						<path stroke-linecap="round" stroke-linejoin="round" d="M12 6v12m6-6H6" />
-					</svg>
-				</button>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								fill="none"
+								viewBox="0 0 24 24"
+								stroke-width="1.5"
+								stroke="currentColor"
+								class="w-4 h-4"
+							>
+								<path stroke-linecap="round" stroke-linejoin="round" d="M12 6v12m6-6H6" />
+							</svg>
+						</button>
+					</Tooltip>
+				</div>
 			{:else}
-				<button
-					class="  self-center disabled:text-gray-600 disabled:hover:text-gray-600 {selectedModelIdx ===
-					0
-						? 'mr-3'
-						: 'mr-7'}"
-					{disabled}
-					on:click={() => {
-						selectedModels.splice(selectedModelIdx, 1);
-						selectedModels = selectedModels;
-					}}
-				>
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						fill="none"
-						viewBox="0 0 24 24"
-						stroke-width="1.5"
-						stroke="currentColor"
-						class="w-4 h-4"
-					>
-						<path stroke-linecap="round" stroke-linejoin="round" d="M19.5 12h-15" />
-					</svg>
-				</button>
-			{/if}
-
-			{#if selectedModelIdx === 0}
-				<button
-					class=" self-center dark:hover:text-gray-300"
-					id="open-settings-button"
-					on:click={async () => {
-						await showSettings.set(!$showSettings);
-					}}
-				>
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						fill="none"
-						viewBox="0 0 24 24"
-						stroke-width="1.5"
-						stroke="currentColor"
-						class="w-4 h-4"
-					>
-						<path
-							stroke-linecap="round"
-							stroke-linejoin="round"
-							d="M10.343 3.94c.09-.542.56-.94 1.11-.94h1.093c.55 0 1.02.398 1.11.94l.149.894c.07.424.384.764.78.93.398.164.855.142 1.205-.108l.737-.527a1.125 1.125 0 011.45.12l.773.774c.39.389.44 1.002.12 1.45l-.527.737c-.25.35-.272.806-.107 1.204.165.397.505.71.93.78l.893.15c.543.09.94.56.94 1.109v1.094c0 .55-.397 1.02-.94 1.11l-.893.149c-.425.07-.765.383-.93.78-.165.398-.143.854.107 1.204l.527.738c.32.447.269 1.06-.12 1.45l-.774.773a1.125 1.125 0 01-1.449.12l-.738-.527c-.35-.25-.806-.272-1.203-.107-.397.165-.71.505-.781.929l-.149.894c-.09.542-.56.94-1.11.94h-1.094c-.55 0-1.019-.398-1.11-.94l-.148-.894c-.071-.424-.384-.764-.781-.93-.398-.164-.854-.142-1.204.108l-.738.527c-.447.32-1.06.269-1.45-.12l-.773-.774a1.125 1.125 0 01-.12-1.45l.527-.737c.25-.35.273-.806.108-1.204-.165-.397-.505-.71-.93-.78l-.894-.15c-.542-.09-.94-.56-.94-1.109v-1.094c0-.55.398-1.02.94-1.11l.894-.149c.424-.07.765-.383.93-.78.165-.398.143-.854-.107-1.204l-.527-.738a1.125 1.125 0 01.12-1.45l.773-.773a1.125 1.125 0 011.45-.12l.737.527c.35.25.807.272 1.204.107.397-.165.71-.505.78-.929l.15-.894z"
-						/>
-						<path
-							stroke-linecap="round"
-							stroke-linejoin="round"
-							d="M15 12a3 3 0 11-6 0 3 3 0 016 0z"
-						/>
-					</svg>
-				</button>
+				<div class="  self-center disabled:text-gray-600 disabled:hover:text-gray-600 mr-2">
+					<Tooltip content="Remove Model">
+						<button
+							{disabled}
+							on:click={() => {
+								selectedModels.splice(selectedModelIdx, 1);
+								selectedModels = selectedModels;
+							}}
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								fill="none"
+								viewBox="0 0 24 24"
+								stroke-width="1.5"
+								stroke="currentColor"
+								class="w-4 h-4"
+							>
+								<path stroke-linecap="round" stroke-linejoin="round" d="M19.5 12h-15" />
+							</svg>
+						</button>
+					</Tooltip>
+				</div>
 			{/if}
 		</div>
 	{/each}
 </div>

-<div class="text-left mt-1.5 text-xs text-gray-500">
-	<button on:click={saveDefaultModel}> Set as default</button>
+<div class="text-left mt-0.5 ml-1 text-[0.7rem] text-gray-500">
+	<button on:click={saveDefaultModel}> {$i18n.t('Set as default')}</button>
 </div>
@@ -0,0 +1,389 @@
+<script lang="ts">
+	import { Select } from 'bits-ui';
+
+	import { flyAndScale } from '$lib/utils/transitions';
+	import { createEventDispatcher, onMount, getContext, tick } from 'svelte';
+
+	import ChevronDown from '$lib/components/icons/ChevronDown.svelte';
+	import Check from '$lib/components/icons/Check.svelte';
+	import Search from '$lib/components/icons/Search.svelte';
+
+	import { cancelOllamaRequest, deleteModel, getOllamaVersion, pullModel } from '$lib/apis/ollama';
+
+	import { user, MODEL_DOWNLOAD_POOL, models } from '$lib/stores';
+	import { toast } from 'svelte-sonner';
+	import { capitalizeFirstLetter, getModels, splitStream } from '$lib/utils';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+
+	const i18n = getContext('i18n');
+	const dispatch = createEventDispatcher();
+
+	export let value = '';
+	export let placeholder = 'Select a model';
+	export let searchEnabled = true;
+	export let searchPlaceholder = 'Search a model';
+
+	export let items = [{ value: 'mango', label: 'Mango' }];
+
+	let searchValue = '';
+	let ollamaVersion = null;
+
+	$: filteredItems = searchValue
+		? items.filter((item) => item.value.includes(searchValue.toLowerCase()))
+		: items;
+
+	const pullModelHandler = async () => {
+		const sanitizedModelTag = searchValue.trim().replace(/^ollama\s+(run|pull)\s+/, '');
+
+		console.log($MODEL_DOWNLOAD_POOL);
+		if ($MODEL_DOWNLOAD_POOL[sanitizedModelTag]) {
+			toast.error(
+				$i18n.t(`Model '{{modelTag}}' is already in queue for downloading.`, {
+					modelTag: sanitizedModelTag
+				})
+			);
+			return;
+		}
+		if (Object.keys($MODEL_DOWNLOAD_POOL).length === 3) {
+			toast.error(
+				$i18n.t('Maximum of 3 models can be downloaded simultaneously. Please try again later.')
+			);
+			return;
+		}
+
+		const res = await pullModel(localStorage.token, sanitizedModelTag, '0').catch((error) => {
+			toast.error(error);
+			return null;
+		});
+
+		if (res) {
+			const reader = res.body
+				.pipeThrough(new TextDecoderStream())
+				.pipeThrough(splitStream('\n'))
+				.getReader();
+
+			while (true) {
+				try {
+					const { value, done } = await reader.read();
+					if (done) break;
+
+					let lines = value.split('\n');
+
+					for (const line of lines) {
+						if (line !== '') {
+							let data = JSON.parse(line);
+							console.log(data);
+							if (data.error) {
+								throw data.error;
+							}
+							if (data.detail) {
+								throw data.detail;
+							}
+
+							if (data.id) {
+								MODEL_DOWNLOAD_POOL.set({
+									...$MODEL_DOWNLOAD_POOL,
+									[sanitizedModelTag]: {
+										...$MODEL_DOWNLOAD_POOL[sanitizedModelTag],
+										requestId: data.id,
+										reader,
+										done: false
+									}
+								});
+								console.log(data);
+							}
+
+							if (data.status) {
+								if (data.digest) {
+									let downloadProgress = 0;
+									if (data.completed) {
+										downloadProgress = Math.round((data.completed / data.total) * 1000) / 10;
+									} else {
+										downloadProgress = 100;
+									}
+
+									MODEL_DOWNLOAD_POOL.set({
+										...$MODEL_DOWNLOAD_POOL,
+										[sanitizedModelTag]: {
+											...$MODEL_DOWNLOAD_POOL[sanitizedModelTag],
+											pullProgress: downloadProgress,
+											digest: data.digest
+										}
+									});
+								} else {
+									toast.success(data.status);
+
+									MODEL_DOWNLOAD_POOL.set({
+										...$MODEL_DOWNLOAD_POOL,
+										[sanitizedModelTag]: {
+											...$MODEL_DOWNLOAD_POOL[sanitizedModelTag],
+											done: data.status === 'success'
+										}
+									});
+								}
+							}
+						}
+					}
+				} catch (error) {
+					console.log(error);
+					if (typeof error !== 'string') {
+						error = error.message;
+					}
+
+					toast.error(error);
+					// opts.callback({ success: false, error, modelName: opts.modelName });
+				}
+			}
+
+			if ($MODEL_DOWNLOAD_POOL[sanitizedModelTag].done) {
+				toast.success(
+					$i18n.t(`Model '{{modelName}}' has been successfully downloaded.`, {
+						modelName: sanitizedModelTag
+					})
+				);
+
+				models.set(await getModels(localStorage.token));
+			} else {
+				toast.error('Download canceled');
+			}
+
+			delete $MODEL_DOWNLOAD_POOL[sanitizedModelTag];
+
+			MODEL_DOWNLOAD_POOL.set({
+				...$MODEL_DOWNLOAD_POOL
+			});
+		}
+	};
+
+	onMount(async () => {
+		ollamaVersion = await getOllamaVersion(localStorage.token).catch((error) => false);
+	});
+
+	const cancelModelPullHandler = async (model: string) => {
+		const { reader, requestId } = $MODEL_DOWNLOAD_POOL[model];
+		if (reader) {
+			await reader.cancel();
+
+			await cancelOllamaRequest(localStorage.token, requestId);
+			delete $MODEL_DOWNLOAD_POOL[model];
+			MODEL_DOWNLOAD_POOL.set({
+				...$MODEL_DOWNLOAD_POOL
+			});
+			await deleteModel(localStorage.token, model);
+			toast.success(`${model} download has been canceled`);
+		}
+	};
+</script>
+
+<Select.Root
+	{items}
+	onOpenChange={async () => {
+		searchValue = '';
+		window.setTimeout(() => document.getElementById('model-search-input')?.focus(), 0);
+	}}
+	selected={items.find((item) => item.value === value) ?? ''}
+	onSelectedChange={(selectedItem) => {
+		value = selectedItem.value;
+	}}
+>
+	<Select.Trigger class="relative w-full" aria-label={placeholder}>
+		<Select.Value
+			class="flex text-left px-0.5 outline-none bg-transparent truncate text-lg font-semibold placeholder-gray-400  focus:outline-none"
+			{placeholder}
+		/>
+		<ChevronDown className="absolute end-2 top-1/2 -translate-y-[45%] size-3.5" strokeWidth="2.5" />
+	</Select.Trigger>
+	<Select.Content
+		class=" z-40 w-full rounded-lg  bg-white dark:bg-gray-900 dark:text-white shadow-lg border border-gray-300/30 dark:border-gray-700/50  outline-none"
+		transition={flyAndScale}
+		sideOffset={4}
+	>
+		<slot>
+			{#if searchEnabled}
+				<div class="flex items-center gap-2.5 px-5 mt-3.5 mb-3">
+					<Search className="size-4" strokeWidth="2.5" />
+
+					<input
+						id="model-search-input"
+						bind:value={searchValue}
+						class="w-full text-sm bg-transparent outline-none"
+						placeholder={searchPlaceholder}
+					/>
+				</div>
+
+				<hr class="border-gray-100 dark:border-gray-800" />
+			{/if}
+
+			<div class="px-3 my-2 max-h-72 overflow-y-auto">
+				{#each filteredItems as item}
+					<Select.Item
+						class="flex w-full font-medium line-clamp-1 select-none items-center rounded-button py-2 pl-3 pr-1.5 text-sm  text-gray-700 dark:text-gray-100  outline-none transition-all duration-75 hover:bg-gray-100 dark:hover:bg-gray-850 rounded-lg cursor-pointer data-[highlighted]:bg-muted"
+						value={item.value}
+						label={item.label}
+					>
+						<div class="flex items-center gap-2">
+							<div class="line-clamp-1">
+								{item.label}
+
+								<span class=" text-xs font-medium text-gray-600 dark:text-gray-400"
+									>{item.info?.details?.parameter_size ?? ''}</span
+								>
+							</div>
+
+							<!-- {JSON.stringify(item.info)} -->
+
+							{#if item.info.external}
+								<Tooltip content={item.info?.source ?? 'External'}>
+									<div class=" mr-2">
+										<svg
+											xmlns="http://www.w3.org/2000/svg"
+											viewBox="0 0 16 16"
+											fill="currentColor"
+											class="size-3"
+										>
+											<path
+												fill-rule="evenodd"
+												d="M8.914 6.025a.75.75 0 0 1 1.06 0 3.5 3.5 0 0 1 0 4.95l-2 2a3.5 3.5 0 0 1-5.396-4.402.75.75 0 0 1 1.251.827 2 2 0 0 0 3.085 2.514l2-2a2 2 0 0 0 0-2.828.75.75 0 0 1 0-1.06Z"
+												clip-rule="evenodd"
+											/>
+											<path
+												fill-rule="evenodd"
+												d="M7.086 9.975a.75.75 0 0 1-1.06 0 3.5 3.5 0 0 1 0-4.95l2-2a3.5 3.5 0 0 1 5.396 4.402.75.75 0 0 1-1.251-.827 2 2 0 0 0-3.085-2.514l-2 2a2 2 0 0 0 0 2.828.75.75 0 0 1 0 1.06Z"
+												clip-rule="evenodd"
+											/>
+										</svg>
+									</div>
+								</Tooltip>
+							{:else}
+								<Tooltip
+									content={`${
+										item.info?.details?.quantization_level
+											? item.info?.details?.quantization_level + ' '
+											: ''
+									}${item.info.size ? `(${(item.info.size / 1024 ** 3).toFixed(1)}GB)` : ''}`}
+								>
+									<div class=" mr-2">
+										<svg
+											xmlns="http://www.w3.org/2000/svg"
+											fill="none"
+											viewBox="0 0 24 24"
+											stroke-width="1.5"
+											stroke="currentColor"
+											class="w-4 h-4"
+										>
+											<path
+												stroke-linecap="round"
+												stroke-linejoin="round"
+												d="m11.25 11.25.041-.02a.75.75 0 0 1 1.063.852l-.708 2.836a.75.75 0 0 0 1.063.853l.041-.021M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Zm-9-3.75h.008v.008H12V8.25Z"
+											/>
+										</svg>
+									</div>
+								</Tooltip>
+							{/if}
+						</div>
+
+						{#if value === item.value}
+							<div class="ml-auto">
+								<Check />
+							</div>
+						{/if}
+					</Select.Item>
+				{:else}
+					<div>
+						<div class="block px-3 py-2 text-sm text-gray-700 dark:text-gray-100">
+							No results found
+						</div>
+					</div>
+				{/each}
+
+				{#if !(searchValue.trim() in $MODEL_DOWNLOAD_POOL) && searchValue && ollamaVersion && $user.role === 'admin'}
+					<button
+						class="flex w-full font-medium line-clamp-1 select-none items-center rounded-button py-2 pl-3 pr-1.5 text-sm text-gray-700 dark:text-gray-100 outline-none transition-all duration-75 hover:bg-gray-100 dark:hover:bg-gray-850 rounded-lg cursor-pointer data-[highlighted]:bg-muted"
+						on:click={() => {
+							pullModelHandler();
+						}}
+					>
+						Pull "{searchValue}" from Ollama.com
+					</button>
+				{/if}
+
+				{#each Object.keys($MODEL_DOWNLOAD_POOL) as model}
+					<div
+						class="flex w-full justify-between font-medium select-none rounded-button py-2 pl-3 pr-1.5 text-sm text-gray-700 dark:text-gray-100 outline-none transition-all duration-75 rounded-lg cursor-pointer data-[highlighted]:bg-muted"
+					>
+						<div class="flex">
+							<div class="-ml-2 mr-2.5 translate-y-0.5">
+								<svg
+									class="size-4"
+									viewBox="0 0 24 24"
+									fill="currentColor"
+									xmlns="http://www.w3.org/2000/svg"
+									><style>
+										.spinner_ajPY {
+											transform-origin: center;
+											animation: spinner_AtaB 0.75s infinite linear;
+										}
+										@keyframes spinner_AtaB {
+											100% {
+												transform: rotate(360deg);
+											}
+										}
+									</style><path
+										d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
+										opacity=".25"
+									/><path
+										d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
+										class="spinner_ajPY"
+									/></svg
+								>
+							</div>
+
+							<div class="flex flex-col self-start">
+								<div class="line-clamp-1">
+									Downloading "{model}" {'pullProgress' in $MODEL_DOWNLOAD_POOL[model]
+										? `(${$MODEL_DOWNLOAD_POOL[model].pullProgress}%)`
+										: ''}
+								</div>
+
+								{#if 'digest' in $MODEL_DOWNLOAD_POOL[model] && $MODEL_DOWNLOAD_POOL[model].digest}
+									<div class="-mt-1 h-fit text-[0.7rem] dark:text-gray-500 line-clamp-1">
+										{$MODEL_DOWNLOAD_POOL[model].digest}
+									</div>
+								{/if}
+							</div>
+						</div>
+
+						<div class="mr-2 translate-y-0.5">
+							<Tooltip content="Cancel">
+								<button
+									class="text-gray-800 dark:text-gray-100"
+									on:click={() => {
+										cancelModelPullHandler(model);
+									}}
+								>
+									<svg
+										class="w-4 h-4 text-gray-800 dark:text-white"
+										aria-hidden="true"
+										xmlns="http://www.w3.org/2000/svg"
+										width="24"
+										height="24"
+										fill="currentColor"
+										viewBox="0 0 24 24"
+									>
+										<path
+											stroke="currentColor"
+											stroke-linecap="round"
+											stroke-linejoin="round"
+											stroke-width="2"
+											d="M6 18 17.94 6M18 18 6.06 6"
+										/>
+									</svg>
+								</button>
+							</Tooltip>
+						</div>
+					</div>
+				{/each}
+			</div>
+		</slot>
+	</Select.Content>
+</Select.Root>
@@ -4,7 +4,11 @@
 	import { WEBUI_VERSION } from '$lib/constants';
 	import { WEBUI_NAME, config, showChangelog } from '$lib/stores';
 	import { compareVersion } from '$lib/utils';
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';
+
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+
+	const i18n = getContext('i18n');

 	let ollamaVersion = '';

@@ -43,23 +47,26 @@
 		<div>
 			<div class=" mb-2.5 text-sm font-medium flex space-x-2 items-center">
 				<div>
-					{$WEBUI_NAME} Version
+					{$WEBUI_NAME}
+					{$i18n.t('Version')}
 				</div>
 			</div>
 			<div class="flex w-full justify-between items-center">
 				<div class="flex flex-col text-xs text-gray-700 dark:text-gray-200">
-					<div>
-						v{WEBUI_VERSION}
+					<div class="flex gap-1">
+						<Tooltip content={WEBUI_VERSION === '0.1.117' ? "🪖 We're just getting started." : ''}>
+							v{WEBUI_VERSION}
+						</Tooltip>

 						<a
 							href="https://github.com/open-webui/open-webui/releases/tag/v{version.latest}"
 							target="_blank"
 						>
 							{updateAvailable === null
-								? 'Checking for updates...'
+								? $i18n.t('Checking for updates...')
 								: updateAvailable
-								? `(v${version.latest} available!)`
-								: '(latest)'}
+								? `(v${version.latest} ${$i18n.t('available!')})`
+								: $i18n.t('(latest)')}
 						</a>
 					</div>

@@ -69,7 +76,7 @@
 							showChangelog.set(true);
 						}}
 					>
-						<div>See what's new</div>
+						<div>{$i18n.t("See what's new")}</div>
 					</button>
 				</div>

@@ -79,7 +86,7 @@
 						checkForVersionUpdates();
 					}}
 				>
-					Check for updates
+					{$i18n.t('Check for updates')}
 				</button>
 			</div>
 		</div>
@@ -88,7 +95,7 @@
 			<hr class=" dark:border-gray-700" />

 			<div>
-				<div class=" mb-2.5 text-sm font-medium">Ollama Version</div>
+				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Ollama Version')}</div>
 				<div class="flex w-full">
 					<div class="flex-1 text-xs text-gray-700 dark:text-gray-200">
 						{ollamaVersion ?? 'N/A'}
@@ -123,7 +130,10 @@
 		</div>

 		<div class="mt-2 text-xs text-gray-400 dark:text-gray-500">
-			Created by <a
+			{#if !$WEBUI_NAME.includes('Open WebUI')}
+				<span class=" text-gray-500 dark:text-gray-300 font-medium">{$WEBUI_NAME}</span> -
+			{/if}{$i18n.t('Created by')}
+			<a
 				class=" text-gray-500 dark:text-gray-300 font-medium"
 				href="https://github.com/tjbck"
 				target="_blank">Timothy J. Baek</a
--- a/Show More
+++ b/Show More