Merge pull request #1781 from open-webui/dev

0.1.122

.eslintrc.cjs

@@ -4,6 +4,7 @@ module.exports = {
 		'eslint:recommended',
 		'plugin:@typescript-eslint/recommended',
 		'plugin:svelte/recommended',
+		'plugin:cypress/recommended',
 		'prettier'
 	],
 	parser: '@typescript-eslint/parser',

.github/pull_request_template.md

@@ -2,14 +2,16 @@
 
 - [ ] **Description:** Briefly describe the changes in this pull request.
 - [ ] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description.
-- [ ] **Documentation:** Have you updated relevant documentation?
+- [ ] **Documentation:** Have you updated relevant documentation [Open WebUI Docs](https://github.com/open-webui/docs), or other documentation sources?
 - [ ] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation?
+- [ ] **Testing:** Have you written and run sufficient tests for the changes?
+- [ ] **Code Review:** Have you self-reviewed your code and addressed any coding standard issues?
 
 ---
 
 ## Description
 
-[Insert a brief description of the changes made in this pull request]
+[Insert a brief description of the changes made in this pull request, including any relevant motivation and impact.]
 
 ---
 
@@ -17,16 +19,32 @@
 
 ### Added
 
-- [List any new features or additions]
+- [List any new features, functionalities, or additions]
 
 ### Fixed
 
-- [List any fixes or corrections]
+- [List any fixes, corrections, or bug fixes]
 
 ### Changed
 
-- [List any changes or updates]
+- [List any changes, updates, refactorings, or optimizations]
 
 ### Removed
 
-- [List any removed features or files]
+- [List any removed features, files, or deprecated functionalities]
+
+### Security
+
+- [List any new or updated security-related changes, including vulnerability fixes]
+
+### Breaking Changes
+
+- [List any breaking changes affecting compatibility or functionality]
+
+---
+
+### Additional Information
+
+- [Insert any additional context, notes, or explanations for the changes]
+
+- [Reference any related issues, commits, or other relevant information]

.github/workflows/integration-test.yml

@@ -0,0 +1,55 @@
+name: Integration Test
+
+on:
+  push:
+    branches:
+      - main
+      - dev
+  pull_request:
+    branches:
+      - main
+      - dev
+
+jobs:
+  cypress-run:
+    name: Run Cypress Integration Tests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Build and run Compose Stack
+        run: |
+          docker compose up --detach --build
+
+      - name: Preload Ollama model
+        run: |
+          docker exec ollama ollama pull qwen:0.5b-chat-v1.5-q2_K
+
+      - name: Cypress run
+        uses: cypress-io/github-action@v6
+        with:
+          browser: chrome
+          wait-on: 'http://localhost:3000'
+          config: baseUrl=http://localhost:3000
+
+      - uses: actions/upload-artifact@v4
+        if: always()
+        name: Upload Cypress videos
+        with:
+          name: cypress-videos
+          path: cypress/videos
+          if-no-files-found: ignore
+
+      - name: Extract Compose logs
+        if: always()
+        run: |
+          docker compose logs > compose-logs.txt
+
+      - uses: actions/upload-artifact@v4
+        if: always()
+        name: Upload Compose logs
+        with:
+          name: compose-logs
+          path: compose-logs.txt
+          if-no-files-found: ignore

.gitignore

@@ -297,4 +297,8 @@ dist
 .yarn/unplugged
 .yarn/build-state.yml
 .yarn/install-state.gz
-.pnp.*
+.pnp.*
+
+# cypress artifacts
+cypress/videos
+cypress/screenshots

CHANGELOG.md

@@ -5,6 +5,30 @@ 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).
 
+## [0.1.122] - 2024-04-27
+
+### Added
+
+- **🌟 Enhanced RAG Pipeline**: Now with hybrid searching via 'BM25', reranking powered by 'CrossEncoder', and configurable relevance score thresholds.
+- **🛢️ External Database Support**: Seamlessly connect to custom SQLite or Postgres databases using the 'DATABASE_URL' environment variable.
+- **🌐 Remote ChromaDB Support**: Introducing the capability to connect to remote ChromaDB servers.
+- **👨‍💼 Improved Admin Panel**: Admins can now conveniently check users' chat lists and last active status directly from the admin panel.
+- **🎨 Splash Screen**: Introducing a loading splash screen for a smoother user experience.
+- **🌍 Language Support Expansion**: Added support for Bangla (bn-BD), along with enhancements to Chinese, Spanish, and Ukrainian translations.
+- **💻 Improved LaTeX Rendering Performance**: Enjoy faster rendering times for LaTeX equations.
+- **🔧 More Environment Variables**: Explore additional environment variables in our documentation (https://docs.openwebui.com), including the 'ENABLE_LITELLM' option to manage memory usage.
+
+### Fixed
+
+- **🔧 Ollama Compatibility**: Resolved errors occurring when Ollama server version isn't an integer, such as SHA builds or RCs.
+- **🐛 Various OpenAI API Issues**: Addressed several issues related to the OpenAI API.
+- **🛑 Stop Sequence Issue**: Fixed the problem where the stop sequence with a backslash '\' was not functioning.
+- **🔤 Font Fallback**: Corrected font fallback issue.
+
+### Changed
+
+- **⌨️ Prompt Input Behavior on Mobile**: Enter key prompt submission disabled on mobile devices for improved user experience.
+
 ## [0.1.121] - 2024-04-24
 
 ### Fixed

Dockerfile

@@ -8,8 +8,9 @@ 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 (sentence-transformers/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.
+# IMPORTANT: If you change the embedding model (sentence-transformers/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=sentence-transformers/all-MiniLM-L6-v2
+ARG USE_RERANKING_MODEL=""
 
 ######## WebUI frontend ########
 FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
@@ -30,6 +31,7 @@ ARG USE_CUDA
 ARG USE_OLLAMA
 ARG USE_CUDA_VER
 ARG USE_EMBEDDING_MODEL
+ARG USE_RERANKING_MODEL
 
 ## Basis ##
 ENV ENV=prod \
@@ -38,7 +40,8 @@ ENV ENV=prod \
     USE_OLLAMA_DOCKER=${USE_OLLAMA} \
     USE_CUDA_DOCKER=${USE_CUDA} \
     USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
-    USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL}
+    USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL} \
+    USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL}
 
 ## Basis URL Config ##
 ENV OLLAMA_BASE_URL="/ollama" \
@@ -62,8 +65,11 @@ ENV WHISPER_MODEL="base" \
 
 ## RAG Embedding model settings ##
 ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
-    RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models" \
+    RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
     SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
+
+## Hugging Face download cache ##
+ENV HF_HOME="/app/backend/data/cache/embedding/models"
 #### Other models ##########################################################
 
 WORKDIR /app/backend

Makefile

@@ -1,27 +1,33 @@
+
+ifneq ($(shell which docker-compose 2>/dev/null),)
+    DOCKER_COMPOSE := docker-compose
+else
+    DOCKER_COMPOSE := docker compose
+endif
+
 install:
-	@docker-compose up -d
+	$(DOCKER_COMPOSE) up -d
 
 remove:
 	@chmod +x confirm_remove.sh
 	@./confirm_remove.sh
 
-
 start:
-	@docker-compose start
+	$(DOCKER_COMPOSE) start
 startAndBuild: 
-	docker-compose up -d --build
+	$(DOCKER_COMPOSE) up -d --build
 
 stop:
-	@docker-compose stop
+	$(DOCKER_COMPOSE) stop
 
 update:
 	# Calls the LLM update script
 	chmod +x update_ollama_models.sh
 	@./update_ollama_models.sh
 	@git pull
-	@docker-compose down
+	$(DOCKER_COMPOSE) down
 	# Make sure the ollama-webui container is stopped before rebuilding
 	@docker stop open-webui || true
-	@docker-compose up --build -d
-	@docker-compose start
+	$(DOCKER_COMPOSE) up --build -d
+	$(DOCKER_COMPOSE) start
 

backend/apps/images/main.py

@@ -32,11 +32,15 @@ import logging
 from config import (
     SRC_LOG_LEVELS,
     CACHE_DIR,
+    IMAGE_GENERATION_ENGINE,
     ENABLE_IMAGE_GENERATION,
     AUTOMATIC1111_BASE_URL,
     COMFYUI_BASE_URL,
     IMAGES_OPENAI_API_BASE_URL,
     IMAGES_OPENAI_API_KEY,
+    IMAGE_GENERATION_MODEL,
+    IMAGE_SIZE,
+    IMAGE_STEPS,
 )
 
 
@@ -55,21 +59,21 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-app.state.ENGINE = ""
+app.state.ENGINE = IMAGE_GENERATION_ENGINE
 app.state.ENABLED = ENABLE_IMAGE_GENERATION
 
 app.state.OPENAI_API_BASE_URL = IMAGES_OPENAI_API_BASE_URL
 app.state.OPENAI_API_KEY = IMAGES_OPENAI_API_KEY
 
-app.state.MODEL = ""
+app.state.MODEL = IMAGE_GENERATION_MODEL
 
 
 app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
 app.state.COMFYUI_BASE_URL = COMFYUI_BASE_URL
 
 
-app.state.IMAGE_SIZE = "512x512"
-app.state.IMAGE_STEPS = 50
+app.state.IMAGE_SIZE = IMAGE_SIZE
+app.state.IMAGE_STEPS = IMAGE_STEPS
 
 
 @app.get("/config")

backend/apps/litellm/main.py

@@ -21,12 +21,15 @@ from utils.utils import get_verified_user, get_current_user, get_admin_user
 from config import SRC_LOG_LEVELS, ENV
 from constants import MESSAGES
 
+import os
+
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["LITELLM"])
 
 
 from config import (
-    MODEL_FILTER_ENABLED,
+    ENABLE_LITELLM,
+    ENABLE_MODEL_FILTER,
     MODEL_FILTER_LIST,
     DATA_DIR,
     LITELLM_PROXY_PORT,
@@ -57,11 +60,20 @@ LITELLM_CONFIG_DIR = f"{DATA_DIR}/litellm/config.yaml"
 with open(LITELLM_CONFIG_DIR, "r") as file:
     litellm_config = yaml.safe_load(file)
 
+
+app.state.ENABLE = ENABLE_LITELLM
 app.state.CONFIG = litellm_config
 
 # Global variable to store the subprocess reference
 background_process = None
 
+CONFLICT_ENV_VARS = [
+    # Uvicorn uses PORT, so LiteLLM might use it as well
+    "PORT",
+    # LiteLLM uses DATABASE_URL for Prisma connections
+    "DATABASE_URL",
+]
+
 
 async def run_background_process(command):
     global background_process
@@ -70,9 +82,11 @@ async def run_background_process(command):
     try:
         # Log the command to be executed
         log.info(f"Executing command: {command}")
+        # Filter environment variables known to conflict with litellm
+        env = {k: v for k, v in os.environ.items() if k not in CONFLICT_ENV_VARS}
         # Execute the command and create a subprocess
         process = await asyncio.create_subprocess_exec(
-            *command, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+            *command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=env
         )
         background_process = process
         log.info("Subprocess started successfully.")
@@ -130,7 +144,7 @@ async def startup_event():
     asyncio.create_task(start_litellm_background())
 
 
-app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
 app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
 
 
@@ -198,49 +212,56 @@ async def update_config(form_data: LiteLLMConfigForm, user=Depends(get_admin_use
 @app.get("/models")
 @app.get("/v1/models")
 async def get_models(user=Depends(get_current_user)):
-    while not background_process:
-        await asyncio.sleep(0.1)
 
-    url = f"http://localhost:{LITELLM_PROXY_PORT}/v1"
-    r = None
-    try:
-        r = requests.request(method="GET", url=f"{url}/models")
-        r.raise_for_status()
+    if app.state.ENABLE:
+        while not background_process:
+            await asyncio.sleep(0.1)
 
-        data = r.json()
+        url = f"http://localhost:{LITELLM_PROXY_PORT}/v1"
+        r = None
+        try:
+            r = requests.request(method="GET", url=f"{url}/models")
+            r.raise_for_status()
 
-        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"],
+            data = r.json()
+
+            if app.state.ENABLE_MODEL_FILTER:
+                if user and user.role == "user":
+                    data["data"] = list(
+                        filter(
+                            lambda model: model["id"] in app.state.MODEL_FILTER_LIST,
+                            data["data"],
+                        )
                     )
-                )
 
-        return data
-    except Exception as e:
+            return data
+        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']}"
-            except:
-                error_detail = f"External: {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']}"
+                except:
+                    error_detail = f"External: {e}"
 
+            return {
+                "data": [
+                    {
+                        "id": model["model_name"],
+                        "object": "model",
+                        "created": int(time.time()),
+                        "owned_by": "openai",
+                    }
+                    for model in app.state.CONFIG["model_list"]
+                ],
+                "object": "list",
+            }
+    else:
         return {
-            "data": [
-                {
-                    "id": model["model_name"],
-                    "object": "model",
-                    "created": int(time.time()),
-                    "owned_by": "openai",
-                }
-                for model in app.state.CONFIG["model_list"]
-            ],
+            "data": [],
             "object": "list",
         }
 

backend/apps/ollama/main.py

@@ -16,6 +16,7 @@ from fastapi.concurrency import run_in_threadpool
 from pydantic import BaseModel, ConfigDict
 
 import os
+import re
 import copy
 import random
 import requests
@@ -36,7 +37,7 @@ from utils.utils import decode_token, get_current_user, get_admin_user
 from config import (
     SRC_LOG_LEVELS,
     OLLAMA_BASE_URLS,
-    MODEL_FILTER_ENABLED,
+    ENABLE_MODEL_FILTER,
     MODEL_FILTER_LIST,
     UPLOAD_DIR,
 )
@@ -55,7 +56,7 @@ app.add_middleware(
 )
 
 
-app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
 app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
 
 app.state.OLLAMA_BASE_URLS = OLLAMA_BASE_URLS
@@ -168,7 +169,7 @@ async def get_ollama_tags(
     if url_idx == None:
         models = await get_all_models()
 
-        if app.state.MODEL_FILTER_ENABLED:
+        if app.state.ENABLE_MODEL_FILTER:
             if user.role == "user":
                 models["models"] = list(
                     filter(
@@ -216,7 +217,9 @@ async def get_ollama_versions(url_idx: Optional[int] = None):
         if len(responses) > 0:
             lowest_version = min(
                 responses,
-                key=lambda x: tuple(map(int, x["version"].split("-")[0].split("."))),
+                key=lambda x: tuple(
+                    map(int, re.sub(r"^v|-.*", "", x["version"]).split("."))
+                ),
             )
 
             return {"version": lowest_version["version"]}

backend/apps/openai/main.py

@@ -24,7 +24,7 @@ from config import (
     OPENAI_API_BASE_URLS,
     OPENAI_API_KEYS,
     CACHE_DIR,
-    MODEL_FILTER_ENABLED,
+    ENABLE_MODEL_FILTER,
     MODEL_FILTER_LIST,
 )
 from typing import List, Optional
@@ -45,7 +45,7 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
 app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
 
 app.state.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS
@@ -225,7 +225,7 @@ async def get_all_models():
 async def get_models(url_idx: Optional[int] = None, user=Depends(get_current_user)):
     if url_idx == None:
         models = await get_all_models()
-        if app.state.MODEL_FILTER_ENABLED:
+        if app.state.ENABLE_MODEL_FILTER:
             if user.role == "user":
                 models["data"] = list(
                     filter(

backend/apps/rag/main.py

@@ -39,8 +39,6 @@ import json
 
 import sentence_transformers
 
-from apps.ollama.main import generate_ollama_embeddings, GenerateEmbeddingsForm
-
 from apps.web.models.documents import (
     Documents,
     DocumentForm,
@@ -48,9 +46,12 @@ from apps.web.models.documents import (
 )
 
 from apps.rag.utils import (
-    query_embeddings_doc,
-    query_embeddings_collection,
-    generate_openai_embeddings,
+    get_model_path,
+    get_embedding_function,
+    query_doc,
+    query_doc_with_hybrid_search,
+    query_collection,
+    query_collection_with_hybrid_search,
 )
 
 from utils.misc import (
@@ -60,13 +61,22 @@ from utils.misc import (
     extract_folders_after_data_docs,
 )
 from utils.utils import get_current_user, get_admin_user
+
 from config import (
     SRC_LOG_LEVELS,
     UPLOAD_DIR,
     DOCS_DIR,
+    RAG_TOP_K,
+    RAG_RELEVANCE_THRESHOLD,
     RAG_EMBEDDING_ENGINE,
     RAG_EMBEDDING_MODEL,
+    RAG_EMBEDDING_MODEL_AUTO_UPDATE,
     RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
+    ENABLE_RAG_HYBRID_SEARCH,
+    RAG_RERANKING_MODEL,
+    PDF_EXTRACT_IMAGES,
+    RAG_RERANKING_MODEL_AUTO_UPDATE,
+    RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
     RAG_OPENAI_API_BASE_URL,
     RAG_OPENAI_API_KEY,
     DEVICE_TYPE,
@@ -83,31 +93,75 @@ log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 app = FastAPI()
 
+app.state.TOP_K = RAG_TOP_K
+app.state.RELEVANCE_THRESHOLD = RAG_RELEVANCE_THRESHOLD
+
+app.state.ENABLE_RAG_HYBRID_SEARCH = ENABLE_RAG_HYBRID_SEARCH
 
-app.state.TOP_K = 4
 app.state.CHUNK_SIZE = CHUNK_SIZE
 app.state.CHUNK_OVERLAP = CHUNK_OVERLAP
 
-
 app.state.RAG_EMBEDDING_ENGINE = RAG_EMBEDDING_ENGINE
 app.state.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
+app.state.RAG_RERANKING_MODEL = RAG_RERANKING_MODEL
 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.PDF_EXTRACT_IMAGES = PDF_EXTRACT_IMAGES
 
-if app.state.RAG_EMBEDDING_ENGINE == "":
-    app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
-        app.state.RAG_EMBEDDING_MODEL,
-        device=DEVICE_TYPE,
-        trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
-    )
 
+def update_embedding_model(
+    embedding_model: str,
+    update_model: bool = False,
+):
+    if embedding_model and app.state.RAG_EMBEDDING_ENGINE == "":
+        app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
+            get_model_path(embedding_model, update_model),
+            device=DEVICE_TYPE,
+            trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
+        )
+    else:
+        app.state.sentence_transformer_ef = None
+
+
+def update_reranking_model(
+    reranking_model: str,
+    update_model: bool = False,
+):
+    if reranking_model:
+        app.state.sentence_transformer_rf = sentence_transformers.CrossEncoder(
+            get_model_path(reranking_model, update_model),
+            device=DEVICE_TYPE,
+            trust_remote_code=RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
+        )
+    else:
+        app.state.sentence_transformer_rf = None
+
+
+update_embedding_model(
+    app.state.RAG_EMBEDDING_MODEL,
+    RAG_EMBEDDING_MODEL_AUTO_UPDATE,
+)
+
+update_reranking_model(
+    app.state.RAG_RERANKING_MODEL,
+    RAG_RERANKING_MODEL_AUTO_UPDATE,
+)
+
+
+app.state.EMBEDDING_FUNCTION = get_embedding_function(
+    app.state.RAG_EMBEDDING_ENGINE,
+    app.state.RAG_EMBEDDING_MODEL,
+    app.state.sentence_transformer_ef,
+    app.state.OPENAI_API_KEY,
+    app.state.OPENAI_API_BASE_URL,
+)
 
 origins = ["*"]
 
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=origins,
@@ -134,6 +188,7 @@ async def get_status():
         "template": app.state.RAG_TEMPLATE,
         "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.RAG_EMBEDDING_MODEL,
+        "reranking_model": app.state.RAG_RERANKING_MODEL,
     }
 
 
@@ -150,6 +205,11 @@ async def get_embedding_config(user=Depends(get_admin_user)):
     }
 
 
+@app.get("/reranking")
+async def get_reraanking_config(user=Depends(get_admin_user)):
+    return {"status": True, "reranking_model": app.state.RAG_RERANKING_MODEL}
+
+
 class OpenAIConfigForm(BaseModel):
     url: str
     key: str
@@ -170,22 +230,22 @@ async def update_embedding_config(
     )
     try:
         app.state.RAG_EMBEDDING_ENGINE = form_data.embedding_engine
+        app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
 
         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 = sentence_transformers.SentenceTransformer(
-                app.state.RAG_EMBEDDING_MODEL,
-                device=DEVICE_TYPE,
-                trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
-            )
-            app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
-            app.state.sentence_transformer_ef = sentence_transformer_ef
+
+        update_embedding_model(app.state.RAG_EMBEDDING_MODEL, True)
+
+        app.state.EMBEDDING_FUNCTION = get_embedding_function(
+            app.state.RAG_EMBEDDING_ENGINE,
+            app.state.RAG_EMBEDDING_MODEL,
+            app.state.sentence_transformer_ef,
+            app.state.OPENAI_API_KEY,
+            app.state.OPENAI_API_BASE_URL,
+        )
 
         return {
             "status": True,
@@ -196,7 +256,6 @@ async def update_embedding_config(
                 "key": app.state.OPENAI_API_KEY,
             },
         }
-
     except Exception as e:
         log.exception(f"Problem updating embedding model: {e}")
         raise HTTPException(
@@ -205,6 +264,34 @@ async def update_embedding_config(
         )
 
 
+class RerankingModelUpdateForm(BaseModel):
+    reranking_model: str
+
+
+@app.post("/reranking/update")
+async def update_reranking_config(
+    form_data: RerankingModelUpdateForm, user=Depends(get_admin_user)
+):
+    log.info(
+        f"Updating reranking model: {app.state.RAG_RERANKING_MODEL} to {form_data.reranking_model}"
+    )
+    try:
+        app.state.RAG_RERANKING_MODEL = form_data.reranking_model
+
+        update_reranking_model(app.state.RAG_RERANKING_MODEL, True)
+
+        return {
+            "status": True,
+            "reranking_model": app.state.RAG_RERANKING_MODEL,
+        }
+    except Exception as e:
+        log.exception(f"Problem updating reranking 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 {
@@ -257,12 +344,16 @@ async def get_query_settings(user=Depends(get_admin_user)):
         "status": True,
         "template": app.state.RAG_TEMPLATE,
         "k": app.state.TOP_K,
+        "r": app.state.RELEVANCE_THRESHOLD,
+        "hybrid": app.state.ENABLE_RAG_HYBRID_SEARCH,
     }
 
 
 class QuerySettingsForm(BaseModel):
     k: Optional[int] = None
+    r: Optional[float] = None
     template: Optional[str] = None
+    hybrid: Optional[bool] = None
 
 
 @app.post("/query/settings/update")
@@ -271,13 +362,23 @@ async def update_query_settings(
 ):
     app.state.RAG_TEMPLATE = form_data.template if form_data.template else RAG_TEMPLATE
     app.state.TOP_K = form_data.k if form_data.k else 4
-    return {"status": True, "template": app.state.RAG_TEMPLATE}
+    app.state.RELEVANCE_THRESHOLD = form_data.r if form_data.r else 0.0
+    app.state.ENABLE_RAG_HYBRID_SEARCH = form_data.hybrid if form_data.hybrid else False
+    return {
+        "status": True,
+        "template": app.state.RAG_TEMPLATE,
+        "k": app.state.TOP_K,
+        "r": app.state.RELEVANCE_THRESHOLD,
+        "hybrid": app.state.ENABLE_RAG_HYBRID_SEARCH,
+    }
 
 
 class QueryDocForm(BaseModel):
     collection_name: str
     query: str
     k: Optional[int] = None
+    r: Optional[float] = None
+    hybrid: Optional[bool] = None
 
 
 @app.post("/query/doc")
@@ -286,34 +387,22 @@ def query_doc_handler(
     user=Depends(get_current_user),
 ):
     try:
-        if app.state.RAG_EMBEDDING_ENGINE == "":
-            query_embeddings = app.state.sentence_transformer_ef.encode(
-                form_data.query
-            ).tolist()
-        elif app.state.RAG_EMBEDDING_ENGINE == "ollama":
-            query_embeddings = generate_ollama_embeddings(
-                GenerateEmbeddingsForm(
-                    **{
-                        "model": app.state.RAG_EMBEDDING_MODEL,
-                        "prompt": form_data.query,
-                    }
-                )
+        if app.state.ENABLE_RAG_HYBRID_SEARCH:
+            return query_doc_with_hybrid_search(
+                collection_name=form_data.collection_name,
+                query=form_data.query,
+                embeddings_function=app.state.EMBEDDING_FUNCTION,
+                reranking_function=app.state.sentence_transformer_rf,
+                k=form_data.k if form_data.k else app.state.TOP_K,
+                r=form_data.r if form_data.r else app.state.RELEVANCE_THRESHOLD,
             )
-        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,
+        else:
+            return query_doc(
+                collection_name=form_data.collection_name,
+                query=form_data.query,
+                embeddings_function=app.state.EMBEDDING_FUNCTION,
+                k=form_data.k if form_data.k else app.state.TOP_K,
             )
-
-        return query_embeddings_doc(
-            collection_name=form_data.collection_name,
-            query=form_data.query,
-            query_embeddings=query_embeddings,
-            k=form_data.k if form_data.k else app.state.TOP_K,
-        )
-
     except Exception as e:
         log.exception(e)
         raise HTTPException(
@@ -326,6 +415,8 @@ class QueryCollectionsForm(BaseModel):
     collection_names: List[str]
     query: str
     k: Optional[int] = None
+    r: Optional[float] = None
+    hybrid: Optional[bool] = None
 
 
 @app.post("/query/collection")
@@ -334,33 +425,23 @@ def query_collection_handler(
     user=Depends(get_current_user),
 ):
     try:
-        if app.state.RAG_EMBEDDING_ENGINE == "":
-            query_embeddings = app.state.sentence_transformer_ef.encode(
-                form_data.query
-            ).tolist()
-        elif app.state.RAG_EMBEDDING_ENGINE == "ollama":
-            query_embeddings = generate_ollama_embeddings(
-                GenerateEmbeddingsForm(
-                    **{
-                        "model": app.state.RAG_EMBEDDING_MODEL,
-                        "prompt": form_data.query,
-                    }
-                )
+        if app.state.ENABLE_RAG_HYBRID_SEARCH:
+            return query_collection_with_hybrid_search(
+                collection_names=form_data.collection_names,
+                query=form_data.query,
+                embeddings_function=app.state.EMBEDDING_FUNCTION,
+                reranking_function=app.state.sentence_transformer_rf,
+                k=form_data.k if form_data.k else app.state.TOP_K,
+                r=form_data.r if form_data.r else app.state.RELEVANCE_THRESHOLD,
             )
-        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,
+        else:
+            return query_collection(
+                collection_names=form_data.collection_names,
+                query=form_data.query,
+                embeddings_function=app.state.EMBEDDING_FUNCTION,
+                k=form_data.k if form_data.k else app.state.TOP_K,
             )
 
-        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,
-        )
-
     except Exception as e:
         log.exception(e)
         raise HTTPException(
@@ -427,8 +508,6 @@ def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> b
     log.info(f"store_docs_in_vector_db {docs} {collection_name}")
 
     texts = [doc.page_content for doc in docs]
-    texts = list(map(lambda x: x.replace("\n", " "), texts))
-
     metadatas = [doc.metadata for doc in docs]
 
     try:
@@ -440,27 +519,16 @@ def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> b
 
         collection = CHROMA_CLIENT.create_collection(name=collection_name)
 
-        if app.state.RAG_EMBEDDING_ENGINE == "":
-            embeddings = app.state.sentence_transformer_ef.encode(texts).tolist()
-        elif 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
-            ]
+        embedding_func = get_embedding_function(
+            app.state.RAG_EMBEDDING_ENGINE,
+            app.state.RAG_EMBEDDING_MODEL,
+            app.state.sentence_transformer_ef,
+            app.state.OPENAI_API_KEY,
+            app.state.OPENAI_API_BASE_URL,
+        )
+
+        embedding_texts = list(map(lambda x: x.replace("\n", " "), texts))
+        embeddings = embedding_func(embedding_texts)
 
         for batch in create_batches(
             api=CHROMA_CLIENT,

backend/apps/rag/utils.py

@@ -1,3 +1,4 @@
+import os
 import logging
 import requests
 
@@ -8,6 +9,16 @@ from apps.ollama.main import (
     GenerateEmbeddingsForm,
 )
 
+from huggingface_hub import snapshot_download
+
+from langchain_core.documents import Document
+from langchain_community.retrievers import BM25Retriever
+from langchain.retrievers import (
+    ContextualCompressionRetriever,
+    EnsembleRetriever,
+)
+
+from typing import Optional
 from config import SRC_LOG_LEVELS, CHROMA_CLIENT
 
 
@@ -15,88 +26,164 @@ log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
-def query_embeddings_doc(collection_name: str, query: str, query_embeddings, k: int):
+def query_doc(
+    collection_name: str,
+    query: str,
+    embedding_function,
+    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)
-
+        query_embeddings = embedding_function(query)
         result = collection.query(
             query_embeddings=[query_embeddings],
             n_results=k,
         )
 
-        log.info(f"query_embeddings_doc:result {result}")
+        log.info(f"query_doc:result {result}")
         return result
     except Exception as e:
         raise e
 
 
-def merge_and_sort_query_results(query_results, k):
+def query_doc_with_hybrid_search(
+    collection_name: str,
+    query: str,
+    embedding_function,
+    k: int,
+    reranking_function,
+    r: int,
+):
+    try:
+        collection = CHROMA_CLIENT.get_collection(name=collection_name)
+        documents = collection.get()  # get all documents
+
+        bm25_retriever = BM25Retriever.from_texts(
+            texts=documents.get("documents"),
+            metadatas=documents.get("metadatas"),
+        )
+        bm25_retriever.k = k
+
+        chroma_retriever = ChromaRetriever(
+            collection=collection,
+            embedding_function=embedding_function,
+            top_n=k,
+        )
+
+        ensemble_retriever = EnsembleRetriever(
+            retrievers=[bm25_retriever, chroma_retriever], weights=[0.5, 0.5]
+        )
+
+        compressor = RerankCompressor(
+            embedding_function=embedding_function,
+            reranking_function=reranking_function,
+            r_score=r,
+            top_n=k,
+        )
+
+        compression_retriever = ContextualCompressionRetriever(
+            base_compressor=compressor, base_retriever=ensemble_retriever
+        )
+
+        result = compression_retriever.invoke(query)
+        result = {
+            "distances": [[d.metadata.get("score") for d in result]],
+            "documents": [[d.page_content for d in result]],
+            "metadatas": [[d.metadata for d in result]],
+        }
+        log.info(f"query_doc_with_hybrid_search:result {result}")
+        return result
+    except Exception as e:
+        raise e
+
+
+def merge_and_sort_query_results(query_results, k, reverse=False):
     # Initialize lists to store combined data
-    combined_ids = []
     combined_distances = []
-    combined_metadatas = []
     combined_documents = []
+    combined_metadatas = []
 
-    # 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])
+        combined_metadatas.extend(data["metadatas"][0])
 
-    # Create a list of tuples (distance, id, metadata, document)
-    combined = list(
-        zip(combined_distances, combined_ids, combined_metadatas, combined_documents)
-    )
+    # Create a list of tuples (distance, document, metadata)
+    combined = list(zip(combined_distances, combined_documents, combined_metadatas))
 
     # Sort the list based on distances
-    combined.sort(key=lambda x: x[0])
+    combined.sort(key=lambda x: x[0], reverse=reverse)
 
-    # Unzip the sorted list
-    sorted_distances, sorted_ids, sorted_metadatas, sorted_documents = zip(*combined)
+    # We don't have anything :-(
+    if not combined:
+        sorted_distances = []
+        sorted_documents = []
+        sorted_metadatas = []
+    else:
+        # Unzip the sorted list
+        sorted_distances, sorted_documents, sorted_metadatas = 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]
+        # Slicing the lists to include only k elements
+        sorted_distances = list(sorted_distances)[:k]
+        sorted_documents = list(sorted_documents)[:k]
+        sorted_metadatas = list(sorted_metadatas)[:k]
 
     # Create the output dictionary
-    merged_query_results = {
-        "ids": [sorted_ids],
+    result = {
         "distances": [sorted_distances],
-        "metadatas": [sorted_metadatas],
         "documents": [sorted_documents],
-        "embeddings": None,
-        "uris": None,
-        "data": None,
+        "metadatas": [sorted_metadatas],
     }
 
-    return merged_query_results
+    return result
 
 
-def query_embeddings_collection(
-    collection_names: List[str], query: str, query_embeddings, k: int
+def query_collection(
+    collection_names: List[str],
+    query: str,
+    embedding_function,
+    k: int,
+):
+    results = []
+    for collection_name in collection_names:
+        try:
+            result = query_doc(
+                collection_name=collection_name,
+                query=query,
+                k=k,
+                embedding_function=embedding_function,
+            )
+            results.append(result)
+        except:
+            pass
+    return merge_and_sort_query_results(results, k=k)
+
+
+def query_collection_with_hybrid_search(
+    collection_names: List[str],
+    query: str,
+    embedding_function,
+    k: int,
+    reranking_function,
+    r: float,
 ):
 
     results = []
-    log.info(f"query_embeddings_collection {query_embeddings}")
-
     for collection_name in collection_names:
         try:
-            result = query_embeddings_doc(
+            result = query_doc_with_hybrid_search(
                 collection_name=collection_name,
                 query=query,
-                query_embeddings=query_embeddings,
+                embedding_function=embedding_function,
                 k=k,
+                reranking_function=reranking_function,
+                r=r,
             )
             results.append(result)
         except:
             pass
 
-    return merge_and_sort_query_results(results, k)
+    return merge_and_sort_query_results(results, k=k, reverse=True)
 
 
 def rag_template(template: str, context: str, query: str):
@@ -105,20 +192,53 @@ def rag_template(template: str, context: str, query: str):
     return template
 
 
-def rag_messages(
-    docs,
-    messages,
-    template,
-    k,
+def get_embedding_function(
     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}"
-    )
+    if embedding_engine == "":
+        return lambda query: embedding_function.encode(query).tolist()
+    elif embedding_engine in ["ollama", "openai"]:
+        if embedding_engine == "ollama":
+            func = lambda query: generate_ollama_embeddings(
+                GenerateEmbeddingsForm(
+                    **{
+                        "model": embedding_model,
+                        "prompt": query,
+                    }
+                )
+            )
+        elif embedding_engine == "openai":
+            func = lambda query: generate_openai_embeddings(
+                model=embedding_model,
+                text=query,
+                key=openai_key,
+                url=openai_url,
+            )
+
+        def generate_multiple(query, f):
+            if isinstance(query, list):
+                return [f(q) for q in query]
+            else:
+                return f(query)
+
+        return lambda query: generate_multiple(query, func)
+
+
+def rag_messages(
+    docs,
+    messages,
+    template,
+    embedding_function,
+    k,
+    reranking_function,
+    r,
+    hybrid_search,
+):
+    log.debug(f"docs: {docs} {messages} {embedding_function} {reranking_function}")
 
     last_user_message_idx = None
     for i in range(len(messages) - 1, -1, -1):
@@ -145,62 +265,65 @@ def rag_messages(
         content_type = None
         query = ""
 
+    extracted_collections = []
     relevant_contexts = []
 
     for doc in docs:
         context = None
 
-        try:
+        collection = doc.get("collection_name")
+        if collection:
+            collection = [collection]
+        else:
+            collection = doc.get("collection_names", [])
 
+        collection = set(collection).difference(extracted_collections)
+        if not collection:
+            log.debug(f"skipping {doc} as it has already been extracted")
+            continue
+
+        try:
             if doc["type"] == "text":
                 context = doc["content"]
             else:
-                if embedding_engine == "":
-                    query_embeddings = embedding_function.encode(query).tolist()
-                elif 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"],
+                if hybrid_search:
+                    context = query_collection_with_hybrid_search(
+                        collection_names=(
+                            doc["collection_names"]
+                            if doc["type"] == "collection"
+                            else [doc["collection_name"]]
+                        ),
                         query=query,
-                        query_embeddings=query_embeddings,
+                        embedding_function=embedding_function,
                         k=k,
+                        reranking_function=reranking_function,
+                        r=r,
                     )
                 else:
-                    context = query_embeddings_doc(
-                        collection_name=doc["collection_name"],
+                    context = query_collection(
+                        collection_names=(
+                            doc["collection_names"]
+                            if doc["type"] == "collection"
+                            else [doc["collection_name"]]
+                        ),
                         query=query,
-                        query_embeddings=query_embeddings,
+                        embedding_function=embedding_function,
                         k=k,
                     )
-
         except Exception as e:
             log.exception(e)
             context = None
 
-        relevant_contexts.append(context)
+        if context:
+            relevant_contexts.append(context)
 
-    log.debug(f"relevant_contexts: {relevant_contexts}")
+        extracted_collections.extend(collection)
 
     context_string = ""
     for context in relevant_contexts:
-        if context:
-            context_string += " ".join(context["documents"][0]) + "\n"
+        items = context["documents"][0]
+        context_string += "\n\n".join(items)
+    context_string = context_string.strip()
 
     ra_content = rag_template(
         template=template,
@@ -208,6 +331,8 @@ def rag_messages(
         query=query,
     )
 
+    log.debug(f"ra_content: {ra_content}")
+
     if content_type == "list":
         new_content = []
         for content_item in user_message["content"]:
@@ -229,6 +354,44 @@ def rag_messages(
     return messages
 
 
+def get_model_path(model: str, update_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_model
+
+    snapshot_kwargs = {
+        "cache_dir": cache_dir,
+        "local_files_only": local_files_only,
+    }
+
+    log.debug(f"model: {model}")
+    log.debug(f"snapshot_kwargs: {snapshot_kwargs}")
+
+    # Inspiration from upstream sentence_transformers
+    if (
+        os.path.exists(model)
+        or ("\\" in model or model.count("/") > 1)
+        and local_files_only
+    ):
+        # If fully qualified path exists, return input, else set repo_id
+        return model
+    elif "/" not in model:
+        # Set valid repo_id for model short-name
+        model = "sentence-transformers" + "/" + model
+
+    snapshot_kwargs["repo_id"] = model
+
+    # Attempt to query the huggingface_hub library to determine the local path and/or to update
+    try:
+        model_repo_path = snapshot_download(**snapshot_kwargs)
+        log.debug(f"model_repo_path: {model_repo_path}")
+        return model_repo_path
+    except Exception as e:
+        log.exception(f"Cannot determine model snapshot path: {e}")
+        return model
+
+
 def generate_openai_embeddings(
     model: str, text: str, key: str, url: str = "https://api.openai.com/v1"
 ):
@@ -250,3 +413,99 @@ def generate_openai_embeddings(
     except Exception as e:
         print(e)
         return None
+
+
+from typing import Any
+
+from langchain_core.retrievers import BaseRetriever
+from langchain_core.callbacks import CallbackManagerForRetrieverRun
+
+
+class ChromaRetriever(BaseRetriever):
+    collection: Any
+    embedding_function: Any
+    top_n: int
+
+    def _get_relevant_documents(
+        self,
+        query: str,
+        *,
+        run_manager: CallbackManagerForRetrieverRun,
+    ) -> List[Document]:
+        query_embeddings = self.embedding_function(query)
+
+        results = self.collection.query(
+            query_embeddings=[query_embeddings],
+            n_results=self.top_n,
+        )
+
+        ids = results["ids"][0]
+        metadatas = results["metadatas"][0]
+        documents = results["documents"][0]
+
+        return [
+            Document(
+                metadata=metadatas[idx],
+                page_content=documents[idx],
+            )
+            for idx in range(len(ids))
+        ]
+
+
+import operator
+
+from typing import Optional, Sequence
+
+from langchain_core.documents import BaseDocumentCompressor, Document
+from langchain_core.callbacks import Callbacks
+from langchain_core.pydantic_v1 import Extra
+
+from sentence_transformers import util
+
+
+class RerankCompressor(BaseDocumentCompressor):
+    embedding_function: Any
+    reranking_function: Any
+    r_score: float
+    top_n: int
+
+    class Config:
+        extra = Extra.forbid
+        arbitrary_types_allowed = True
+
+    def compress_documents(
+        self,
+        documents: Sequence[Document],
+        query: str,
+        callbacks: Optional[Callbacks] = None,
+    ) -> Sequence[Document]:
+        if self.reranking_function:
+            scores = self.reranking_function.predict(
+                [(query, doc.page_content) for doc in documents]
+            )
+        else:
+            query_embedding = self.embedding_function(query)
+            document_embedding = self.embedding_function(
+                [doc.page_content for doc in documents]
+            )
+            scores = util.cos_sim(query_embedding, document_embedding)[0]
+
+        docs_with_scores = list(zip(documents, scores.tolist()))
+        if self.r_score:
+            docs_with_scores = [
+                (d, s) for d, s in docs_with_scores if s >= self.r_score
+            ]
+
+        reverse = self.reranking_function is not None
+        result = sorted(docs_with_scores, key=operator.itemgetter(1), reverse=reverse)
+
+        final_results = []
+        for doc, doc_score in result[: self.top_n]:
+            metadata = doc.metadata
+            metadata["score"] = doc_score
+            doc = Document(
+                page_content=doc.page_content,
+                metadata=metadata,
+            )
+            final_results.append(doc)
+        return final_results

backend/apps/web/internal/db.py

@@ -1,6 +1,7 @@
 from peewee import *
 from peewee_migrate import Router
-from config import SRC_LOG_LEVELS, DATA_DIR
+from playhouse.db_url import connect
+from config import SRC_LOG_LEVELS, DATA_DIR, DATABASE_URL
 import os
 import logging
 
@@ -11,12 +12,12 @@ log.setLevel(SRC_LOG_LEVELS["DB"])
 if os.path.exists(f"{DATA_DIR}/ollama.db"):
     # Rename the file
     os.rename(f"{DATA_DIR}/ollama.db", f"{DATA_DIR}/webui.db")
-    log.info("File renamed successfully.")
+    log.info("Database migrated from Ollama-WebUI successfully.")
 else:
     pass
 
-
-DB = SqliteDatabase(f"{DATA_DIR}/webui.db")
+DB = connect(DATABASE_URL)
+log.info(f"Connected to a {DB.__class__.__name__} database.")
 router = Router(DB, migrate_dir="apps/web/internal/migrations", logger=log)
 router.run()
 DB.connect(reuse_if_open=True)

backend/apps/web/internal/migrations/001_initial_schema.py

@@ -37,6 +37,18 @@ with suppress(ImportError):
 def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
     """Write your migrations here."""
 
+    # We perform different migrations for SQLite and other databases
+    # This is because SQLite is very loose with enforcing its schema, and trying to migrate other databases like SQLite
+    # will require per-database SQL queries.
+    # Instead, we assume that because external DB support was added at a later date, it is safe to assume a newer base
+    # schema instead of trying to migrate from an older schema.
+    if isinstance(database, pw.SqliteDatabase):
+        migrate_sqlite(migrator, database, fake=fake)
+    else:
+        migrate_external(migrator, database, fake=fake)
+
+
+def migrate_sqlite(migrator: Migrator, database: pw.Database, *, fake=False):
     @migrator.create_model
     class Auth(pw.Model):
         id = pw.CharField(max_length=255, unique=True)
@@ -129,6 +141,99 @@ def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
             table_name = "user"
 
 
+def migrate_external(migrator: Migrator, database: pw.Database, *, fake=False):
+    @migrator.create_model
+    class Auth(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        email = pw.CharField(max_length=255)
+        password = pw.TextField()
+        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.TextField()
+        chat = pw.TextField()
+        timestamp = pw.BigIntegerField()
+
+        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.BigIntegerField()
+
+        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.TextField()
+        filename = pw.TextField()
+        content = pw.TextField(null=True)
+        user_id = pw.CharField(max_length=255)
+        timestamp = pw.BigIntegerField()
+
+        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.BigIntegerField()
+
+        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.TextField()
+        content = pw.TextField()
+        timestamp = pw.BigIntegerField()
+
+        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.TextField()
+        timestamp = pw.BigIntegerField()
+
+        class Meta:
+            table_name = "user"
+
+
 def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
     """Write your rollback migrations here."""
 

backend/apps/web/internal/migrations/005_add_updated_at.py

@@ -37,6 +37,13 @@ with suppress(ImportError):
 def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
     """Write your migrations here."""
 
+    if isinstance(database, pw.SqliteDatabase):
+        migrate_sqlite(migrator, database, fake=fake)
+    else:
+        migrate_external(migrator, database, fake=fake)
+
+
+def migrate_sqlite(migrator: Migrator, database: pw.Database, *, fake=False):
     # Adding fields created_at and updated_at to the 'chat' table
     migrator.add_fields(
         "chat",
@@ -60,9 +67,40 @@ def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
     )
 
 
+def migrate_external(migrator: Migrator, database: pw.Database, *, fake=False):
+    # Adding fields created_at and updated_at to the 'chat' table
+    migrator.add_fields(
+        "chat",
+        created_at=pw.BigIntegerField(null=True),  # Allow null for transition
+        updated_at=pw.BigIntegerField(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.BigIntegerField(null=False),
+        updated_at=pw.BigIntegerField(null=False),
+    )
+
+
 def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
     """Write your rollback migrations here."""
 
+    if isinstance(database, pw.SqliteDatabase):
+        rollback_sqlite(migrator, database, fake=fake)
+    else:
+        rollback_external(migrator, database, fake=fake)
+
+
+def rollback_sqlite(migrator: Migrator, database: pw.Database, *, fake=False):
     # Recreate the timestamp field initially allowing null values for safe transition
     migrator.add_fields("chat", timestamp=pw.DateTimeField(null=True))
 
@@ -75,3 +113,18 @@ def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
 
     # Finally, alter the timestamp field to not allow nulls if that was the original setting
     migrator.change_fields("chat", timestamp=pw.DateTimeField(null=False))
+
+
+def rollback_external(migrator: Migrator, database: pw.Database, *, fake=False):
+    # Recreate the timestamp field initially allowing null values for safe transition
+    migrator.add_fields("chat", timestamp=pw.BigIntegerField(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.BigIntegerField(null=False))

backend/apps/web/internal/migrations/006_migrate_timestamps_and_charfields.py

@@ -0,0 +1,130 @@
+"""Peewee migrations -- 006_migrate_timestamps_and_charfields.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."""
+
+    # Alter the tables with timestamps
+    migrator.change_fields(
+        "chatidtag",
+        timestamp=pw.BigIntegerField(),
+    )
+    migrator.change_fields(
+        "document",
+        timestamp=pw.BigIntegerField(),
+    )
+    migrator.change_fields(
+        "modelfile",
+        timestamp=pw.BigIntegerField(),
+    )
+    migrator.change_fields(
+        "prompt",
+        timestamp=pw.BigIntegerField(),
+    )
+    migrator.change_fields(
+        "user",
+        timestamp=pw.BigIntegerField(),
+    )
+    # Alter the tables with varchar to text where necessary
+    migrator.change_fields(
+        "auth",
+        password=pw.TextField(),
+    )
+    migrator.change_fields(
+        "chat",
+        title=pw.TextField(),
+    )
+    migrator.change_fields(
+        "document",
+        title=pw.TextField(),
+        filename=pw.TextField(),
+    )
+    migrator.change_fields(
+        "prompt",
+        title=pw.TextField(),
+    )
+    migrator.change_fields(
+        "user",
+        profile_image_url=pw.TextField(),
+    )
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    if isinstance(database, pw.SqliteDatabase):
+        # Alter the tables with timestamps
+        migrator.change_fields(
+            "chatidtag",
+            timestamp=pw.DateField(),
+        )
+        migrator.change_fields(
+            "document",
+            timestamp=pw.DateField(),
+        )
+        migrator.change_fields(
+            "modelfile",
+            timestamp=pw.DateField(),
+        )
+        migrator.change_fields(
+            "prompt",
+            timestamp=pw.DateField(),
+        )
+        migrator.change_fields(
+            "user",
+            timestamp=pw.DateField(),
+        )
+    migrator.change_fields(
+        "auth",
+        password=pw.CharField(max_length=255),
+    )
+    migrator.change_fields(
+        "chat",
+        title=pw.CharField(),
+    )
+    migrator.change_fields(
+        "document",
+        title=pw.CharField(),
+        filename=pw.CharField(),
+    )
+    migrator.change_fields(
+        "prompt",
+        title=pw.CharField(),
+    )
+    migrator.change_fields(
+        "user",
+        profile_image_url=pw.CharField(),
+    )

backend/apps/web/internal/migrations/007_add_user_last_active_at.py

@@ -0,0 +1,79 @@
+"""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 'user' table
+    migrator.add_fields(
+        "user",
+        created_at=pw.BigIntegerField(null=True),  # Allow null for transition
+        updated_at=pw.BigIntegerField(null=True),  # Allow null for transition
+        last_active_at=pw.BigIntegerField(null=True),  # Allow null for transition
+    )
+
+    # Populate the new fields from an existing 'timestamp' field
+    migrator.sql(
+        "UPDATE user SET created_at = timestamp, updated_at = timestamp, last_active_at = timestamp WHERE timestamp IS NOT NULL"
+    )
+
+    # Now that the data has been copied, remove the original 'timestamp' field
+    migrator.remove_fields("user", "timestamp")
+
+    # Update the fields to be not null now that they are populated
+    migrator.change_fields(
+        "user",
+        created_at=pw.BigIntegerField(null=False),
+        updated_at=pw.BigIntegerField(null=False),
+        last_active_at=pw.BigIntegerField(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("user", timestamp=pw.BigIntegerField(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 user SET timestamp = created_at")
+
+    # Remove the created_at and updated_at fields
+    migrator.remove_fields("user", "created_at", "updated_at", "last_active_at")
+
+    # Finally, alter the timestamp field to not allow nulls if that was the original setting
+    migrator.change_fields("user", timestamp=pw.BigIntegerField(null=False))

backend/apps/web/models/auths.py

@@ -23,7 +23,7 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 class Auth(Model):
     id = CharField(unique=True)
     email = CharField()
-    password = CharField()
+    password = TextField()
     active = BooleanField()
 
     class Meta:

backend/apps/web/models/chats.py

@@ -17,11 +17,11 @@ from apps.web.internal.db import DB
 class Chat(Model):
     id = CharField(unique=True)
     user_id = CharField()
-    title = CharField()
+    title = TextField()
     chat = TextField()  # Save Chat JSON as Text
 
-    created_at = DateTimeField()
-    updated_at = DateTimeField()
+    created_at = BigIntegerField()
+    updated_at = BigIntegerField()
 
     share_id = CharField(null=True, unique=True)
     archived = BooleanField(default=False)
@@ -191,7 +191,7 @@ class ChatTable:
         except:
             return None
 
-    def get_archived_chat_lists_by_user_id(
+    def get_archived_chat_list_by_user_id(
         self, user_id: str, skip: int = 0, limit: int = 50
     ) -> List[ChatModel]:
         return [
@@ -204,7 +204,7 @@ class ChatTable:
             # .offset(skip)
         ]
 
-    def get_chat_lists_by_user_id(
+    def get_chat_list_by_user_id(
         self, user_id: str, skip: int = 0, limit: int = 50
     ) -> List[ChatModel]:
         return [
@@ -217,7 +217,7 @@ class ChatTable:
             # .offset(skip)
         ]
 
-    def get_chat_lists_by_chat_ids(
+    def get_chat_list_by_chat_ids(
         self, chat_ids: List[str], skip: int = 0, limit: int = 50
     ) -> List[ChatModel]:
         return [
@@ -228,20 +228,6 @@ class ChatTable:
             .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.updated_at.desc())
-        ]
-
-    def get_all_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
-        return [
-            ChatModel(**model_to_dict(chat))
-            for chat in Chat.select()
-            .where(Chat.user_id == user_id)
-            .order_by(Chat.updated_at.desc())
-        ]
-
     def get_chat_by_id(self, id: str) -> Optional[ChatModel]:
         try:
             chat = Chat.get(Chat.id == id)
@@ -271,9 +257,28 @@ class ChatTable:
     def get_chats(self, skip: int = 0, limit: int = 50) -> List[ChatModel]:
         return [
             ChatModel(**model_to_dict(chat))
-            for chat in Chat.select().limit(limit).offset(skip)
+            for chat in Chat.select().order_by(Chat.updated_at.desc())
+            # .limit(limit).offset(skip)
         ]
 
+    def get_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
+        return [
+            ChatModel(**model_to_dict(chat))
+            for chat in Chat.select()
+            .where(Chat.user_id == user_id)
+            .order_by(Chat.updated_at.desc())
+            # .limit(limit).offset(skip)
+        ]
+
+    def delete_chat_by_id(self, id: str) -> bool:
+        try:
+            query = Chat.delete().where((Chat.id == id))
+            query.execute()  # Remove the rows, return number of rows removed.
+
+            return True and self.delete_shared_chat_by_chat_id(id)
+        except:
+            return False
+
     def delete_chat_by_id_and_user_id(self, id: str, user_id: str) -> bool:
         try:
             query = Chat.delete().where((Chat.id == id) & (Chat.user_id == user_id))

backend/apps/web/models/documents.py

@@ -25,11 +25,11 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 class Document(Model):
     collection_name = CharField(unique=True)
     name = CharField(unique=True)
-    title = CharField()
-    filename = CharField()
+    title = TextField()
+    filename = TextField()
     content = TextField(null=True)
     user_id = CharField()
-    timestamp = DateField()
+    timestamp = BigIntegerField()
 
     class Meta:
         database = DB

backend/apps/web/models/modelfiles.py

@@ -20,7 +20,7 @@ class Modelfile(Model):
     tag_name = CharField(unique=True)
     user_id = CharField()
     modelfile = TextField()
-    timestamp = DateField()
+    timestamp = BigIntegerField()
 
     class Meta:
         database = DB

backend/apps/web/models/prompts.py

@@ -19,9 +19,9 @@ import json
 class Prompt(Model):
     command = CharField(unique=True)
     user_id = CharField()
-    title = CharField()
+    title = TextField()
     content = TextField()
-    timestamp = DateField()
+    timestamp = BigIntegerField()
 
     class Meta:
         database = DB

backend/apps/web/models/tags.py

@@ -35,7 +35,7 @@ class ChatIdTag(Model):
     tag_name = CharField()
     chat_id = CharField()
     user_id = CharField()
-    timestamp = DateField()
+    timestamp = BigIntegerField()
 
     class Meta:
         database = DB

backend/apps/web/models/users.py

@@ -18,8 +18,12 @@ class User(Model):
     name = CharField()
     email = CharField()
     role = CharField()
-    profile_image_url = CharField()
-    timestamp = DateField()
+    profile_image_url = TextField()
+
+    last_active_at = BigIntegerField()
+    updated_at = BigIntegerField()
+    created_at = BigIntegerField()
+
     api_key = CharField(null=True, unique=True)
 
     class Meta:
@@ -32,7 +36,11 @@ class UserModel(BaseModel):
     email: str
     role: str = "pending"
     profile_image_url: str
-    timestamp: int  # timestamp in epoch
+
+    last_active_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+    created_at: int  # timestamp in epoch
+
     api_key: Optional[str] = None
 
 
@@ -73,7 +81,9 @@ class UsersTable:
                 "email": email,
                 "role": role,
                 "profile_image_url": profile_image_url,
-                "timestamp": int(time.time()),
+                "last_active_at": int(time.time()),
+                "created_at": int(time.time()),
+                "updated_at": int(time.time()),
             }
         )
         result = User.create(**user.model_dump())
@@ -137,6 +147,16 @@ class UsersTable:
         except:
             return None
 
+    def update_user_last_active_by_id(self, id: str) -> Optional[UserModel]:
+        try:
+            query = User.update(last_active_at=int(time.time())).where(User.id == id)
+            query.execute()
+
+            user = User.get(User.id == id)
+            return UserModel(**model_to_dict(user))
+        except:
+            return None
+
     def update_user_by_id(self, id: str, updated: dict) -> Optional[UserModel]:
         try:
             query = User.update(**updated).where(User.id == id)

backend/apps/web/routers/auths.py

@@ -1,3 +1,5 @@
+import logging
+
 from fastapi import Request
 from fastapi import Depends, HTTPException, status
 

backend/apps/web/routers/chats.py

@@ -36,15 +36,49 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 router = APIRouter()
 
 ############################
-# GetChats
+# GetChatList
 ############################
 
 
 @router.get("/", response_model=List[ChatTitleIdResponse])
-async def get_user_chats(
+@router.get("/list", response_model=List[ChatTitleIdResponse])
+async def get_session_user_chat_list(
     user=Depends(get_current_user), skip: int = 0, limit: int = 50
 ):
-    return Chats.get_chat_lists_by_user_id(user.id, skip, limit)
+    return Chats.get_chat_list_by_user_id(user.id, skip, limit)
+
+
+############################
+# DeleteAllChats
+############################
+
+
+@router.delete("/", response_model=bool)
+async def delete_all_user_chats(request: Request, user=Depends(get_current_user)):
+
+    if (
+        user.role == "user"
+        and not request.app.state.USER_PERMISSIONS["chat"]["deletion"]
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    result = Chats.delete_chats_by_user_id(user.id)
+    return result
+
+
+############################
+# GetUserChatList
+############################
+
+
+@router.get("/list/user/{user_id}", response_model=List[ChatTitleIdResponse])
+async def get_user_chat_list_by_user_id(
+    user_id: str, user=Depends(get_admin_user), skip: int = 0, limit: int = 50
+):
+    return Chats.get_chat_list_by_user_id(user_id, skip, limit)
 
 
 ############################
@@ -53,22 +87,22 @@ async def get_user_chats(
 
 
 @router.get("/archived", response_model=List[ChatTitleIdResponse])
-async def get_archived_user_chats(
+async def get_archived_session_user_chat_list(
     user=Depends(get_current_user), skip: int = 0, limit: int = 50
 ):
-    return Chats.get_archived_chat_lists_by_user_id(user.id, skip, limit)
+    return Chats.get_archived_chat_list_by_user_id(user.id, skip, limit)
 
 
 ############################
-# GetAllChats
+# GetChats
 ############################
 
 
 @router.get("/all", response_model=List[ChatResponse])
-async def get_all_user_chats(user=Depends(get_current_user)):
+async def get_user_chats(user=Depends(get_current_user)):
     return [
         ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
-        for chat in Chats.get_all_chats_by_user_id(user.id)
+        for chat in Chats.get_chats_by_user_id(user.id)
     ]
 
 
@@ -86,7 +120,7 @@ async def get_all_user_chats_in_db(user=Depends(get_admin_user)):
         )
     return [
         ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
-        for chat in Chats.get_all_chats()
+        for chat in Chats.get_chats()
     ]
 
 
@@ -107,45 +141,6 @@ async def create_new_chat(form_data: ChatForm, user=Depends(get_current_user)):
         )
 
 
-############################
-# GetAllTags
-############################
-
-
-@router.get("/tags/all", response_model=List[TagModel])
-async def get_all_tags(user=Depends(get_current_user)):
-    try:
-        tags = Tags.get_tags_by_user_id(user.id)
-        return tags
-    except Exception as e:
-        log.exception(e)
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
-        )
-
-
-############################
-# GetChatsByTags
-############################
-
-
-@router.get("/tags/tag/{tag_name}", response_model=List[ChatTitleIdResponse])
-async def get_user_chats_by_tag_name(
-    tag_name: str, user=Depends(get_current_user), skip: int = 0, limit: int = 50
-):
-    chat_ids = [
-        chat_id_tag.chat_id
-        for chat_id_tag in Tags.get_chat_ids_by_tag_name_and_user_id(tag_name, user.id)
-    ]
-
-    chats = Chats.get_chat_lists_by_chat_ids(chat_ids, skip, limit)
-
-    if len(chats) == 0:
-        Tags.delete_tag_by_tag_name_and_user_id(tag_name, user.id)
-
-    return chats
-
-
 ############################
 # GetChatById
 ############################
@@ -193,17 +188,18 @@ async def update_chat_by_id(
 @router.delete("/{id}", response_model=bool)
 async def delete_chat_by_id(request: Request, id: str, user=Depends(get_current_user)):
 
-    if (
-        user.role == "user"
-        and not request.app.state.USER_PERMISSIONS["chat"]["deletion"]
-    ):
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
+    if user.role == "admin":
+        result = Chats.delete_chat_by_id(id)
+        return result
+    else:
+        if not request.app.state.USER_PERMISSIONS["chat"]["deletion"]:
+            raise HTTPException(
+                status_code=status.HTTP_401_UNAUTHORIZED,
+                detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+            )
 
-    result = Chats.delete_chat_by_id_and_user_id(id, user.id)
-    return result
+        result = Chats.delete_chat_by_id_and_user_id(id, user.id)
+        return result
 
 
 ############################
@@ -303,6 +299,45 @@ async def get_shared_chat_by_id(share_id: str, user=Depends(get_current_user)):
         )
 
 
+############################
+# GetAllTags
+############################
+
+
+@router.get("/tags/all", response_model=List[TagModel])
+async def get_all_tags(user=Depends(get_current_user)):
+    try:
+        tags = Tags.get_tags_by_user_id(user.id)
+        return tags
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
+############################
+# GetChatsByTags
+############################
+
+
+@router.get("/tags/tag/{tag_name}", response_model=List[ChatTitleIdResponse])
+async def get_user_chat_list_by_tag_name(
+    tag_name: str, user=Depends(get_current_user), skip: int = 0, limit: int = 50
+):
+    chat_ids = [
+        chat_id_tag.chat_id
+        for chat_id_tag in Tags.get_chat_ids_by_tag_name_and_user_id(tag_name, user.id)
+    ]
+
+    chats = Chats.get_chat_list_by_chat_ids(chat_ids, skip, limit)
+
+    if len(chats) == 0:
+        Tags.delete_tag_by_tag_name_and_user_id(tag_name, user.id)
+
+    return chats
+
+
 ############################
 # GetChatTagsById
 ############################
@@ -383,24 +418,3 @@ async def delete_all_chat_tags_by_id(id: str, user=Depends(get_current_user)):
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
         )
-
-
-############################
-# DeleteAllChats
-############################
-
-
-@router.delete("/", response_model=bool)
-async def delete_all_user_chats(request: Request, user=Depends(get_current_user)):
-
-    if (
-        user.role == "user"
-        and not request.app.state.USER_PERMISSIONS["chat"]["deletion"]
-    ):
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
-
-    result = Chats.delete_chats_by_user_id(user.id)
-    return result

backend/apps/web/routers/utils.py

@@ -1,5 +1,6 @@
 from fastapi import APIRouter, UploadFile, File, Response
 from fastapi import Depends, HTTPException, status
+from peewee import SqliteDatabase
 from starlette.responses import StreamingResponse, FileResponse
 from pydantic import BaseModel
 
@@ -7,11 +8,11 @@ from pydantic import BaseModel
 from fpdf import FPDF
 import markdown
 
-
+from apps.web.internal.db import DB
 from utils.utils import get_admin_user
 from utils.misc import calculate_sha256, get_gravatar_url
 
-from config import OLLAMA_BASE_URLS, DATA_DIR, UPLOAD_DIR
+from config import OLLAMA_BASE_URLS, DATA_DIR, UPLOAD_DIR, ENABLE_ADMIN_EXPORT
 from constants import ERROR_MESSAGES
 from typing import List
 
@@ -96,8 +97,13 @@ async def download_db(user=Depends(get_admin_user)):
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
         )
+    if not isinstance(DB, SqliteDatabase):
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DB_NOT_SQLITE,
+        )
     return FileResponse(
-        f"{DATA_DIR}/webui.db",
+        DB.database,
         media_type="application/octet-stream",
         filename="webui.db",
     )

backend/config.py

@@ -71,6 +71,9 @@ except ImportError:
     log.warning("dotenv not installed, skipping...")
 
 WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
+if WEBUI_NAME != "Open WebUI":
+    WEBUI_NAME += " (Open WebUI)"
+
 WEBUI_FAVICON_URL = "https://openwebui.com/favicon.png"
 
 ####################################
@@ -195,9 +198,6 @@ if CUSTOM_NAME:
     except Exception as e:
         log.exception(e)
         pass
-else:
-    if WEBUI_NAME != "Open WebUI":
-        WEBUI_NAME += " (Open WebUI)"
 
 
 ####################################
@@ -220,7 +220,7 @@ Path(CACHE_DIR).mkdir(parents=True, exist_ok=True)
 # Docs DIR
 ####################################
 
-DOCS_DIR = f"{DATA_DIR}/docs"
+DOCS_DIR = os.getenv("DOCS_DIR", f"{DATA_DIR}/docs")
 Path(DOCS_DIR).mkdir(parents=True, exist_ok=True)
 
 
@@ -375,8 +375,7 @@ USER_PERMISSIONS_CHAT_DELETION = (
 
 USER_PERMISSIONS = {"chat": {"deletion": USER_PERMISSIONS_CHAT_DELETION}}
 
-
-MODEL_FILTER_ENABLED = os.environ.get("MODEL_FILTER_ENABLED", "False").lower() == "true"
+ENABLE_MODEL_FILTER = os.environ.get("ENABLE_MODEL_FILTER", "False").lower() == "true"
 MODEL_FILTER_LIST = os.environ.get("MODEL_FILTER_LIST", "")
 MODEL_FILTER_LIST = [model.strip() for model in MODEL_FILTER_LIST.split(";")]
 
@@ -418,19 +417,57 @@ if WEBUI_AUTH and WEBUI_SECRET_KEY == "":
 ####################################
 
 CHROMA_DATA_PATH = f"{DATA_DIR}/vector_db"
+CHROMA_TENANT = os.environ.get("CHROMA_TENANT", chromadb.DEFAULT_TENANT)
+CHROMA_DATABASE = os.environ.get("CHROMA_DATABASE", chromadb.DEFAULT_DATABASE)
+CHROMA_HTTP_HOST = os.environ.get("CHROMA_HTTP_HOST", "")
+CHROMA_HTTP_PORT = int(os.environ.get("CHROMA_HTTP_PORT", "8000"))
+# Comma-separated list of header=value pairs
+CHROMA_HTTP_HEADERS = os.environ.get("CHROMA_HTTP_HEADERS", "")
+if CHROMA_HTTP_HEADERS:
+    CHROMA_HTTP_HEADERS = dict(
+        [pair.split("=") for pair in CHROMA_HTTP_HEADERS.split(",")]
+    )
+else:
+    CHROMA_HTTP_HEADERS = None
+CHROMA_HTTP_SSL = os.environ.get("CHROMA_HTTP_SSL", "false").lower() == "true"
 # 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 (sentence-transformers/all-MiniLM-L6-v2)
 
+RAG_TOP_K = int(os.environ.get("RAG_TOP_K", "5"))
+RAG_RELEVANCE_THRESHOLD = float(os.environ.get("RAG_RELEVANCE_THRESHOLD", "0.0"))
+
+ENABLE_RAG_HYBRID_SEARCH = (
+    os.environ.get("ENABLE_RAG_HYBRID_SEARCH", "").lower() == "true"
+)
+
 RAG_EMBEDDING_ENGINE = os.environ.get("RAG_EMBEDDING_ENGINE", "")
 
+PDF_EXTRACT_IMAGES = os.environ.get("PDF_EXTRACT_IMAGES", "False").lower() == "true"
+
 RAG_EMBEDDING_MODEL = os.environ.get(
     "RAG_EMBEDDING_MODEL", "sentence-transformers/all-MiniLM-L6-v2"
 )
 log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL}"),
 
+RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
+    os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
+)
+
 RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE = (
     os.environ.get("RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
 )
 
+RAG_RERANKING_MODEL = os.environ.get("RAG_RERANKING_MODEL", "")
+if not RAG_RERANKING_MODEL == "":
+    log.info(f"Reranking model set: {RAG_RERANKING_MODEL}"),
+
+RAG_RERANKING_MODEL_AUTO_UPDATE = (
+    os.environ.get("RAG_RERANKING_MODEL_AUTO_UPDATE", "").lower() == "true"
+)
+
+RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
+    os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "").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")
 
@@ -439,16 +476,28 @@ if USE_CUDA.lower() == "true":
 else:
     DEVICE_TYPE = "cpu"
 
+if CHROMA_HTTP_HOST != "":
+    CHROMA_CLIENT = chromadb.HttpClient(
+        host=CHROMA_HTTP_HOST,
+        port=CHROMA_HTTP_PORT,
+        headers=CHROMA_HTTP_HEADERS,
+        ssl=CHROMA_HTTP_SSL,
+        tenant=CHROMA_TENANT,
+        database=CHROMA_DATABASE,
+        settings=Settings(allow_reset=True, anonymized_telemetry=False),
+    )
+else:
+    CHROMA_CLIENT = chromadb.PersistentClient(
+        path=CHROMA_DATA_PATH,
+        settings=Settings(allow_reset=True, anonymized_telemetry=False),
+        tenant=CHROMA_TENANT,
+        database=CHROMA_DATABASE,
+    )
 
-CHROMA_CLIENT = chromadb.PersistentClient(
-    path=CHROMA_DATA_PATH,
-    settings=Settings(allow_reset=True, anonymized_telemetry=False),
-)
-CHUNK_SIZE = 1500
-CHUNK_OVERLAP = 100
+CHUNK_SIZE = int(os.environ.get("CHUNK_SIZE", "1500"))
+CHUNK_OVERLAP = int(os.environ.get("CHUNK_OVERLAP", "100"))
 
-
-RAG_TEMPLATE = """Use the following context as your learned knowledge, inside <context></context> XML tags.
+DEFAULT_RAG_TEMPLATE = """Use the following context as your learned knowledge, inside <context></context> XML tags.
 <context>
     [context]
 </context>
@@ -458,10 +507,12 @@ When answer to user:
 - If you don't know when you are not sure, ask for clarification.
 Avoid mentioning that you obtained the information from the context.
 And answer according to the language of the user's question.
-        
+
 Given the context information, answer the query.
 Query: [query]"""
 
+RAG_TEMPLATE = os.environ.get("RAG_TEMPLATE", DEFAULT_RAG_TEMPLATE)
+
 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)
 
@@ -480,18 +531,25 @@ WHISPER_MODEL_AUTO_UPDATE = (
 # Images
 ####################################
 
+IMAGE_GENERATION_ENGINE = os.getenv("IMAGE_GENERATION_ENGINE", "")
+
 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", "")
 
+COMFYUI_BASE_URL = os.getenv("COMFYUI_BASE_URL", "")
 
 IMAGES_OPENAI_API_BASE_URL = os.getenv(
     "IMAGES_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL
 )
 IMAGES_OPENAI_API_KEY = os.getenv("IMAGES_OPENAI_API_KEY", OPENAI_API_KEY)
 
+IMAGE_SIZE = os.getenv("IMAGE_SIZE", "512x512")
+
+IMAGE_STEPS = int(os.getenv("IMAGE_STEPS", 50))
+
+IMAGE_GENERATION_MODEL = os.getenv("IMAGE_GENERATION_MODEL", "")
 
 ####################################
 # Audio
@@ -504,7 +562,17 @@ AUDIO_OPENAI_API_KEY = os.getenv("AUDIO_OPENAI_API_KEY", OPENAI_API_KEY)
 # LiteLLM
 ####################################
 
+
+ENABLE_LITELLM = os.environ.get("ENABLE_LITELLM", "True").lower() == "true"
+
 LITELLM_PROXY_PORT = int(os.getenv("LITELLM_PROXY_PORT", "14365"))
 if LITELLM_PROXY_PORT < 0 or LITELLM_PROXY_PORT > 65535:
     raise ValueError("Invalid port number for LITELLM_PROXY_PORT")
 LITELLM_PROXY_HOST = os.getenv("LITELLM_PROXY_HOST", "127.0.0.1")
+
+
+####################################
+# Database
+####################################
+
+DATABASE_URL = os.environ.get("DATABASE_URL", f"sqlite:///{DATA_DIR}/webui.db")

backend/constants.py

@@ -69,3 +69,5 @@ class ERROR_MESSAGES(str, Enum):
     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."
+
+    DB_NOT_SQLITE = "This feature is only available when running with SQLite databases."

backend/main.py

@@ -47,7 +47,8 @@ from config import (
     FRONTEND_BUILD_DIR,
     CACHE_DIR,
     STATIC_DIR,
-    MODEL_FILTER_ENABLED,
+    ENABLE_LITELLM,
+    ENABLE_MODEL_FILTER,
     MODEL_FILTER_LIST,
     GLOBAL_LOG_LEVEL,
     SRC_LOG_LEVELS,
@@ -89,7 +90,7 @@ 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.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
 app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
 
 app.state.WEBHOOK_URL = WEBHOOK_URL
@@ -116,15 +117,14 @@ class RAGMiddleware(BaseHTTPMiddleware):
             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.OPENAI_API_KEY,
-                    rag_app.state.OPENAI_API_BASE_URL,
+                    docs=data["docs"],
+                    messages=data["messages"],
+                    template=rag_app.state.RAG_TEMPLATE,
+                    embedding_function=rag_app.state.EMBEDDING_FUNCTION,
+                    k=rag_app.state.TOP_K,
+                    reranking_function=rag_app.state.sentence_transformer_rf,
+                    r=rag_app.state.RELEVANCE_THRESHOLD,
+                    hybrid_search=rag_app.state.ENABLE_RAG_HYBRID_SEARCH,
                 )
                 del data["docs"]
 
@@ -176,7 +176,8 @@ async def check_url(request: Request, call_next):
 
 @app.on_event("startup")
 async def on_startup():
-    asyncio.create_task(start_litellm_background())
+    if ENABLE_LITELLM:
+        asyncio.create_task(start_litellm_background())
 
 
 app.mount("/api/v1", webui_app)
@@ -215,7 +216,7 @@ async def get_app_config():
 @app.get("/api/config/model/filter")
 async def get_model_filter_config(user=Depends(get_admin_user)):
     return {
-        "enabled": app.state.MODEL_FILTER_ENABLED,
+        "enabled": app.state.ENABLE_MODEL_FILTER,
         "models": app.state.MODEL_FILTER_LIST,
     }
 
@@ -229,20 +230,20 @@ class ModelFilterConfigForm(BaseModel):
 async def update_model_filter_config(
     form_data: ModelFilterConfigForm, user=Depends(get_admin_user)
 ):
-    app.state.MODEL_FILTER_ENABLED = form_data.enabled
+    app.state.ENABLE_MODEL_FILTER = 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.ENABLE_MODEL_FILTER = app.state.ENABLE_MODEL_FILTER
     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.ENABLE_MODEL_FILTER = app.state.ENABLE_MODEL_FILTER
     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.ENABLE_MODEL_FILTER = app.state.ENABLE_MODEL_FILTER
     litellm_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
 
     return {
-        "enabled": app.state.MODEL_FILTER_ENABLED,
+        "enabled": app.state.ENABLE_MODEL_FILTER,
         "models": app.state.MODEL_FILTER_LIST,
     }
 
@@ -326,4 +327,5 @@ app.mount(
 
 @app.on_event("shutdown")
 async def shutdown_event():
-    await shutdown_litellm_background()
+    if ENABLE_LITELLM:
+        await shutdown_litellm_background()

backend/requirements.txt

@@ -15,6 +15,8 @@ requests
 aiohttp
 peewee
 peewee-migrate
+psycopg2-binary
+pymysql
 bcrypt
 
 litellm==1.35.17

backend/start.sh

@@ -6,6 +6,7 @@ cd "$SCRIPT_DIR" || exit
 KEY_FILE=.webui_secret_key
 
 PORT="${PORT:-8080}"
+HOST="${HOST:-0.0.0.0}"
 if test "$WEBUI_SECRET_KEY $WEBUI_JWT_SECRET_KEY" = " "; then
   echo "No WEBUI_SECRET_KEY provided"
 
@@ -29,4 +30,4 @@ if [ "$USE_CUDA_DOCKER" = "true" ]; then
   export LD_LIBRARY_PATH="$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 '*'
+WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host "$HOST" --port "$PORT" --forwarded-allow-ips '*'

backend/start_windows.bat

@@ -7,7 +7,7 @@ SET "SCRIPT_DIR=%~dp0"
 cd /d "%SCRIPT_DIR%" || exit /b
 
 SET "KEY_FILE=.webui_secret_key"
-SET "PORT=%PORT:8080%"
+IF "%PORT%"=="" SET PORT=8080
 SET "WEBUI_SECRET_KEY=%WEBUI_SECRET_KEY%"
 SET "WEBUI_JWT_SECRET_KEY=%WEBUI_JWT_SECRET_KEY%"
 

backend/utils/utils.py

@@ -89,6 +89,8 @@ def get_current_user(
                 status_code=status.HTTP_401_UNAUTHORIZED,
                 detail=ERROR_MESSAGES.INVALID_TOKEN,
             )
+        else:
+            Users.update_user_last_active_by_id(user.id)
         return user
     else:
         raise HTTPException(
@@ -99,11 +101,15 @@ 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,
         )
+    else:
+        Users.update_user_last_active_by_id(user.id)
+
     return user
 
 

confirm_remove.sh

@@ -2,7 +2,12 @@
 echo "Warning: This will remove all containers and volumes, including persistent data. Do you want to continue? [Y/N]"
 read ans
 if [ "$ans" == "Y" ] || [ "$ans" == "y" ]; then
-  docker-compose down -v
+  command docker-compose 2>/dev/null
+  if [ "$?" == "0" ]; then
+    docker-compose down -v
+  else
+    docker compose down -v
+  fi
 else
   echo "Operation cancelled."
 fi

cypress.config.ts

@@ -0,0 +1,8 @@
+import { defineConfig } from 'cypress';
+
+export default defineConfig({
+	e2e: {
+		baseUrl: 'http://localhost:8080'
+	},
+	video: true
+});

cypress/e2e/chat.cy.ts

@@ -0,0 +1,46 @@
+// eslint-disable-next-line @typescript-eslint/triple-slash-reference
+/// <reference path="../support/index.d.ts" />
+
+// These tests run through the chat flow.
+describe('Settings', () => {
+	// Wait for 2 seconds after all tests to fix an issue with Cypress's video recording missing the last few frames
+	after(() => {
+		// eslint-disable-next-line cypress/no-unnecessary-waiting
+		cy.wait(2000);
+	});
+
+	beforeEach(() => {
+		// Login as the admin user
+		cy.loginAdmin();
+		// Visit the home page
+		cy.visit('/');
+	});
+
+	context('Ollama', () => {
+		it('user can select a model', () => {
+			// Click on the model selector
+			cy.get('button[aria-label="Select a model"]').click();
+			// Select the first model
+			cy.get('div[role="option"][data-value]').first().click();
+		});
+
+		it('user can perform text chat', () => {
+			// Click on the model selector
+			cy.get('button[aria-label="Select a model"]').click();
+			// Select the first model
+			cy.get('div[role="option"][data-value]').first().click();
+			// Type a message
+			cy.get('#chat-textarea').type('Hi, what can you do? A single sentence only please.', {
+				force: true
+			});
+			// Send the message
+			cy.get('button[type="submit"]').click();
+			// User's message should be visible
+			cy.get('.chat-user').should('exist');
+			// Wait for the response
+			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
+				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
+				.should('exist');
+		});
+	});
+});

cypress/e2e/registration.cy.ts

@@ -0,0 +1,52 @@
+// eslint-disable-next-line @typescript-eslint/triple-slash-reference
+/// <reference path="../support/index.d.ts" />
+import { adminUser } from '../support/e2e';
+
+// These tests assume the following defaults:
+// 1. No users exist in the database or that the test admin user is an admin
+// 2. Language is set to English
+// 3. The default role for new users is 'pending'
+describe('Registration and Login', () => {
+	// Wait for 2 seconds after all tests to fix an issue with Cypress's video recording missing the last few frames
+	after(() => {
+		// eslint-disable-next-line cypress/no-unnecessary-waiting
+		cy.wait(2000);
+	});
+
+	beforeEach(() => {
+		cy.visit('/');
+	});
+
+	it('should register a new user as pending', () => {
+		const userName = `Test User - ${Date.now()}`;
+		const userEmail = `cypress-${Date.now()}@example.com`;
+		// Toggle from sign in to sign up
+		cy.contains('Sign up').click();
+		// Fill out the form
+		cy.get('input[autocomplete="name"]').type(userName);
+		cy.get('input[autocomplete="email"]').type(userEmail);
+		cy.get('input[type="password"]').type('password');
+		// Submit the form
+		cy.get('button[type="submit"]').click();
+		// Wait until the user is redirected to the home page
+		cy.contains(userName);
+		// Expect the user to be pending
+		cy.contains('Check Again');
+	});
+
+	it('can login with the admin user', () => {
+		// Fill out the form
+		cy.get('input[autocomplete="email"]').type(adminUser.email);
+		cy.get('input[type="password"]').type(adminUser.password);
+		// Submit the form
+		cy.get('button[type="submit"]').click();
+		// Wait until the user is redirected to the home page
+		cy.contains(adminUser.name);
+		// Dismiss the changelog dialog if it is visible
+		cy.getAllLocalStorage().then((ls) => {
+			if (!ls['version']) {
+				cy.get('button').contains("Okay, Let's Go!").click();
+			}
+		});
+	});
+});

cypress/e2e/settings.cy.ts

@@ -0,0 +1,88 @@
+// eslint-disable-next-line @typescript-eslint/triple-slash-reference
+/// <reference path="../support/index.d.ts" />
+import { adminUser } from '../support/e2e';
+
+// These tests run through the various settings pages, ensuring that the user can interact with them as expected
+describe('Settings', () => {
+	// Wait for 2 seconds after all tests to fix an issue with Cypress's video recording missing the last few frames
+	after(() => {
+		// eslint-disable-next-line cypress/no-unnecessary-waiting
+		cy.wait(2000);
+	});
+
+	beforeEach(() => {
+		// Login as the admin user
+		cy.loginAdmin();
+		// Visit the home page
+		cy.visit('/');
+		// Open the sidebar if it is not already open
+		cy.get('[aria-label="Open sidebar"]').then(() => {
+			cy.get('button[id="sidebar-toggle-button"]').click();
+		});
+		// Click on the profile link
+		cy.get('button').contains(adminUser.name).click();
+		// Click on the settings link
+		cy.get('button').contains('Settings').click();
+	});
+
+	context('General', () => {
+		it('user can open the General modal and hit save', () => {
+			cy.get('button').contains('General').click();
+			cy.get('button').contains('Save').click();
+		});
+	});
+
+	context('Connections', () => {
+		it('user can open the Connections modal and hit save', () => {
+			cy.get('button').contains('Connections').click();
+			cy.get('button').contains('Save').click();
+		});
+	});
+
+	context('Models', () => {
+		it('user can open the Models modal', () => {
+			cy.get('button').contains('Models').click();
+		});
+	});
+
+	context('Interface', () => {
+		it('user can open the Interface modal and hit save', () => {
+			cy.get('button').contains('Interface').click();
+			cy.get('button').contains('Save').click();
+		});
+	});
+
+	context('Audio', () => {
+		it('user can open the Audio modal and hit save', () => {
+			cy.get('button').contains('Audio').click();
+			cy.get('button').contains('Save').click();
+		});
+	});
+
+	context('Images', () => {
+		it('user can open the Images modal and hit save', () => {
+			cy.get('button').contains('Images').click();
+			// Currently fails because the backend requires a valid URL
+			// cy.get('button').contains('Save').click();
+		});
+	});
+
+	context('Chats', () => {
+		it('user can open the Chats modal', () => {
+			cy.get('button').contains('Chats').click();
+		});
+	});
+
+	context('Account', () => {
+		it('user can open the Account modal and hit save', () => {
+			cy.get('button').contains('Account').click();
+			cy.get('button').contains('Save').click();
+		});
+	});
+
+	context('About', () => {
+		it('user can open the About modal', () => {
+			cy.get('button').contains('About').click();
+		});
+	});
+});

cypress/support/e2e.ts

@@ -0,0 +1,73 @@
+/// <reference types="cypress" />
+
+export const adminUser = {
+	name: 'Admin User',
+	email: 'admin@example.com',
+	password: 'password'
+};
+
+const login = (email: string, password: string) => {
+	return cy.session(
+		email,
+		() => {
+			// Visit auth page
+			cy.visit('/auth');
+			// Fill out the form
+			cy.get('input[autocomplete="email"]').type(email);
+			cy.get('input[type="password"]').type(password);
+			// Submit the form
+			cy.get('button[type="submit"]').click();
+			// Wait until the user is redirected to the home page
+			cy.get('#chat-search').should('exist');
+			// Get the current version to skip the changelog dialog
+			if (localStorage.getItem('version') === null) {
+				cy.get('button').contains("Okay, Let's Go!").click();
+			}
+		},
+		{
+			validate: () => {
+				cy.request({
+					method: 'GET',
+					url: '/api/v1/auths/',
+					headers: {
+						Authorization: 'Bearer ' + localStorage.getItem('token')
+					}
+				});
+			}
+		}
+	);
+};
+
+const register = (name: string, email: string, password: string) => {
+	return cy
+		.request({
+			method: 'POST',
+			url: '/api/v1/auths/signup',
+			body: {
+				name: name,
+				email: email,
+				password: password
+			},
+			failOnStatusCode: false
+		})
+		.then((response) => {
+			expect(response.status).to.be.oneOf([200, 400]);
+		});
+};
+
+const registerAdmin = () => {
+	return register(adminUser.name, adminUser.email, adminUser.password);
+};
+
+const loginAdmin = () => {
+	return login(adminUser.email, adminUser.password);
+};
+
+Cypress.Commands.add('login', (email, password) => login(email, password));
+Cypress.Commands.add('register', (name, email, password) => register(name, email, password));
+Cypress.Commands.add('registerAdmin', () => registerAdmin());
+Cypress.Commands.add('loginAdmin', () => loginAdmin());
+
+before(() => {
+	cy.registerAdmin();
+});

cypress/support/index.d.ts

@@ -0,0 +1,11 @@
+// load the global Cypress types
+/// <reference types="cypress" />
+
+declare namespace Cypress {
+	interface Chainable {
+		login(email: string, password: string): Chainable<Element>;
+		register(name: string, email: string, password: string): Chainable<Element>;
+		registerAdmin(): Chainable<Element>;
+		loginAdmin(): Chainable<Element>;
+	}
+}

cypress/tsconfig.json

@@ -0,0 +1,7 @@
+{
+	"extends": "../tsconfig.json",
+	"compilerOptions": {
+		"inlineSourceMap": true,
+		"sourceMap": false
+	}
+}

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.1.121",
+	"version": "0.1.122",
 	"private": true,
 	"scripts": {
 		"dev": "vite dev --host",
@@ -14,7 +14,8 @@
 		"lint:backend": "pylint backend/",
 		"format": "prettier --plugin-search-dir --write '**/*.{js,ts,svelte,css,md,html,json}'",
 		"format:backend": "black . --exclude \"/venv/\"",
-		"i18n:parse": "i18next --config i18next-parser.config.ts && prettier --write 'src/lib/i18n/**/*.{js,json}'"
+		"i18n:parse": "i18next --config i18next-parser.config.ts && prettier --write 'src/lib/i18n/**/*.{js,json}'",
+		"cy:open": "cypress open"
 	},
 	"devDependencies": {
 		"@sveltejs/adapter-auto": "^2.0.0",
@@ -25,8 +26,10 @@
 		"@typescript-eslint/eslint-plugin": "^6.17.0",
 		"@typescript-eslint/parser": "^6.17.0",
 		"autoprefixer": "^10.4.16",
+		"cypress": "^13.8.1",
 		"eslint": "^8.56.0",
 		"eslint-config-prettier": "^8.5.0",
+		"eslint-plugin-cypress": "^3.0.2",
 		"eslint-plugin-svelte": "^2.30.0",
 		"i18next-parser": "^8.13.0",
 		"postcss": "^8.4.31",
@@ -53,7 +56,6 @@
 		"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",

run-compose.sh

@@ -82,6 +82,7 @@ usage() {
     echo "Examples:"
     echo "  $0 --drop"
     echo "  $0 --enable-gpu[count=1]"
+    echo "  $0 --enable-gpu[count=all]"
     echo "  $0 --enable-api[port=11435]"
     echo "  $0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000]"
     echo "  $0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000] --data[folder=./ollama-data]"
@@ -160,7 +161,7 @@ else
     if [[ $enable_gpu == true ]]; then
         # Validate and process command-line arguments
         if [[ -n $gpu_count ]]; then
-            if ! [[ $gpu_count =~ ^[0-9]+$ ]]; then
+            if ! [[ $gpu_count =~ ^([0-9]+|all)$ ]]; then
                 echo "Invalid GPU count: $gpu_count"
                 exit 1
             fi

src/app.html

@@ -43,9 +43,46 @@
 			})();
 		</script>
 
+		<title>Open WebUI</title>
+
 		%sveltekit.head%
 	</head>
 	<body data-sveltekit-preload-data="hover">
 		<div style="display: contents">%sveltekit.body%</div>
+
+		<div
+			id="splash-screen"
+			style="
+				position: fixed;
+				z-index: 100;
+				background: #fff;
+				top: 0;
+				left: 0;
+				width: 100%;
+				height: 100%;
+			"
+		>
+			<style type="text/css" nonce="">
+				html {
+					overflow-y: scroll !important;
+				}
+			</style>
+
+			<img
+				style="
+					position: absolute;
+					width: 6rem;
+					height: 6rem;
+					top: 46%;
+					left: 50%;
+					margin: -40px 0 0 -40px;
+				"
+				src="/logo.svg"
+			/>
+
+			<!-- <span style="position: absolute; bottom: 32px; left: 50%; margin: -36px 0 0 -36px">
+				Footer content
+			</span> -->
+		</div>
 	</body>
 </html>

src/lib/apis/chats/index.ts

@@ -62,6 +62,37 @@ export const getChatList = async (token: string = '') => {
 	return res;
 };
 
+export const getChatListByUserId = async (token: string = '', userId: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/list/user/${userId}`, {
+		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 getArchivedChatList = async (token: string = '') => {
 	let error = null;
 

src/lib/apis/openai/index.ts

@@ -211,10 +211,12 @@ export const generateOpenAIChatCompletion = async (
 	token: string = '',
 	body: object,
 	url: string = OPENAI_API_BASE_URL
-) => {
+): Promise<[Response | null, AbortController]> => {
+	const controller = new AbortController();
 	let error = null;
 
 	const res = await fetch(`${url}/chat/completions`, {
+		signal: controller.signal,
 		method: 'POST',
 		headers: {
 			Authorization: `Bearer ${token}`,
@@ -231,7 +233,7 @@ export const generateOpenAIChatCompletion = async (
 		throw error;
 	}
 
-	return res;
+	return [res, controller];
 };
 
 export const synthesizeOpenAISpeech = async (

src/lib/apis/rag/index.ts

@@ -123,6 +123,7 @@ export const getQuerySettings = async (token: string) => {
 
 type QuerySettings = {
 	k: number | null;
+	r: number | null;
 	template: string | null;
 };
 
@@ -413,3 +414,64 @@ export const updateEmbeddingConfig = async (token: string, payload: EmbeddingMod
 
 	return res;
 };
+
+export const getRerankingConfig = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/reranking`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+type RerankingModelUpdateForm = {
+	reranking_model: string;
+};
+
+export const updateRerankingConfig = async (token: string, payload: RerankingModelUpdateForm) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/reranking/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;
+};

src/lib/apis/streaming/index.ts

@@ -26,16 +26,28 @@ async function* openAIStreamToIterator(
 			break;
 		}
 		const lines = value.split('\n');
-		for (const line of lines) {
+		for (let line of lines) {
+			if (line.endsWith('\r')) {
+				// Remove trailing \r
+				line = line.slice(0, -1);
+			}
 			if (line !== '') {
 				console.log(line);
 				if (line === 'data: [DONE]') {
 					yield { done: true, value: '' };
+				} else if (line.startsWith(':')) {
+					// Events starting with : are comments https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#event_stream_format
+					// OpenRouter sends heartbeats like ": OPENROUTER PROCESSING"
+					continue;
 				} else {
-					const data = JSON.parse(line.replace(/^data: /, ''));
-					console.log(data);
+					try {
+						const data = JSON.parse(line.replace(/^data: /, ''));
+						console.log(data);
 
-					yield { done: false, value: data.choices[0].delta.content ?? '' };
+						yield { done: false, value: data.choices?.[0]?.delta?.content ?? '' };
+					} catch (e) {
+						console.error('Error extracting delta from SSE event:', e);
+					}
 				}
 			}
 		}

src/lib/apis/utils/index.ts

@@ -83,9 +83,9 @@ export const downloadDatabase = async (token: string) => {
 			Authorization: `Bearer ${token}`
 		}
 	})
-		.then((response) => {
+		.then(async (response) => {
 			if (!response.ok) {
-				throw new Error('Network response was not ok');
+				throw await response.json();
 			}
 			return response.blob();
 		})
@@ -100,7 +100,11 @@ export const downloadDatabase = async (token: string) => {
 		})
 		.catch((err) => {
 			console.log(err);
-			error = err;
+			error = err.detail;
 			return null;
 		});
+
+	if (error) {
+		throw error;
+	}
 };

src/lib/components/ChangelogModal.svelte

@@ -110,7 +110,7 @@
 					localStorage.version = $config.version;
 					show = false;
 				}}
-				class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+				class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 			>
 				<span class="relative">{$i18n.t("Okay, Let's Go!")}</span>
 			</button>

src/lib/components/admin/EditUserModal.svelte

@@ -86,7 +86,7 @@
 
 							<div class="text-xs text-gray-500">
 								{$i18n.t('Created at')}
-								{dayjs(selectedUser.timestamp * 1000).format($i18n.t('MMMM DD, YYYY'))}
+								{dayjs(selectedUser.created_at * 1000).format($i18n.t('MMMM DD, YYYY'))}
 							</div>
 						</div>
 					</div>
@@ -139,7 +139,7 @@
 
 					<div class="flex justify-end pt-3 text-sm font-medium">
 						<button
-							class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+							class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 							type="submit"
 						>
 							{$i18n.t('Save')}

src/lib/components/admin/Settings/Database.svelte

@@ -2,6 +2,7 @@
 	import { downloadDatabase } from '$lib/apis/utils';
 	import { onMount, getContext } from 'svelte';
 	import { config } from '$lib/stores';
+	import { toast } from 'svelte-sonner';
 
 	const i18n = getContext('i18n');
 
@@ -32,7 +33,9 @@
 						on:click={() => {
 							// exportAllUserChats();
 
-							downloadDatabase(localStorage.token);
+							downloadDatabase(localStorage.token).catch((error) => {
+								toast.error(error);
+							});
 						}}
 					>
 						<div class=" self-center mr-3">
@@ -59,10 +62,11 @@
 
 	<!-- <div class="flex justify-end pt-3 text-sm font-medium">
 		<button
-			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 			type="submit"
 		>
 			Save
 		</button>
+
 	</div> -->
 </form>

src/lib/components/admin/Settings/General.svelte

@@ -159,7 +159,7 @@
 
 	<div class="flex justify-end pt-3 text-sm font-medium">
 		<button
-			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 			type="submit"
 		>
 			{$i18n.t('Save')}

src/lib/components/admin/Settings/Users.svelte

@@ -190,7 +190,7 @@
 
 	<div class="flex justify-end pt-3 text-sm font-medium">
 		<button
-			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 			type="submit"
 		>
 			{$i18n.t('Save')}

src/lib/components/admin/UserChatsModal.svelte

@@ -0,0 +1,141 @@
+<script lang="ts">
+	import { toast } from 'svelte-sonner';
+	import dayjs from 'dayjs';
+	import { getContext, createEventDispatcher } from 'svelte';
+
+	const dispatch = createEventDispatcher();
+
+	import Modal from '$lib/components/common/Modal.svelte';
+	import { getChatListByUserId, deleteChatById, getArchivedChatList } from '$lib/apis/chats';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+
+	const i18n = getContext('i18n');
+
+	export let show = false;
+	export let user;
+
+	let chats = [];
+
+	const deleteChatHandler = async (chatId) => {
+		const res = await deleteChatById(localStorage.token, chatId).catch((error) => {
+			toast.error(error);
+		});
+
+		chats = await getChatListByUserId(localStorage.token, user.id);
+	};
+
+	$: if (show) {
+		(async () => {
+			if (user.id) {
+				chats = await getChatListByUserId(localStorage.token, user.id);
+			}
+		})();
+	}
+</script>
+
+<Modal size="lg" bind:show>
+	<div>
+		<div class=" flex justify-between dark:text-gray-300 px-5 py-4">
+			<div class=" text-lg font-medium self-center capitalize">
+				{$i18n.t("{{user}}'s Chats", { user: user.name })}
+			</div>
+			<button
+				class="self-center"
+				on:click={() => {
+					show = false;
+				}}
+			>
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 20 20"
+					fill="currentColor"
+					class="w-5 h-5"
+				>
+					<path
+						d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+					/>
+				</svg>
+			</button>
+		</div>
+		<hr class=" dark:border-gray-850" />
+
+		<div class="flex flex-col md:flex-row w-full px-5 py-4 md:space-x-4 dark:text-gray-200">
+			<div class=" flex flex-col w-full sm:flex-row sm:justify-center sm:space-x-6">
+				{#if chats.length > 0}
+					<div class="text-left text-sm w-full mb-4 max-h-[22rem] overflow-y-scroll">
+						<div class="relative overflow-x-auto">
+							<table class="w-full text-sm text-left text-gray-600 dark:text-gray-400 table-auto">
+								<thead
+									class="text-xs text-gray-700 uppercase bg-transparent dark:text-gray-200 border-b-2 dark:border-gray-800"
+								>
+									<tr>
+										<th scope="col" class="px-3 py-2"> {$i18n.t('Name')} </th>
+										<th scope="col" class="px-3 py-2 hidden md:flex"> {$i18n.t('Created At')} </th>
+										<th scope="col" class="px-3 py-2 text-right" />
+									</tr>
+								</thead>
+								<tbody>
+									{#each chats as chat, idx}
+										<tr
+											class="bg-transparent {idx !== chats.length - 1 &&
+												'border-b'} dark:bg-gray-900 dark:border-gray-850 text-xs"
+										>
+											<td class="px-3 py-1 w-2/3">
+												<a href="/s/{chat.id}" target="_blank">
+													<div class=" underline line-clamp-1">
+														{chat.title}
+													</div>
+												</a>
+											</td>
+
+											<td class=" px-3 py-1 hidden md:flex h-[2.5rem]">
+												<div class="my-auto">
+													{dayjs(chat.created_at * 1000).format($i18n.t('MMMM DD, YYYY HH:mm'))}
+												</div>
+											</td>
+
+											<td class="px-3 py-1 text-right">
+												<div class="flex justify-end w-full">
+													<Tooltip content="Delete Chat">
+														<button
+															class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
+															on:click={async () => {
+																deleteChatHandler(chat.id);
+															}}
+														>
+															<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="m14.74 9-.346 9m-4.788 0L9.26 9m9.968-3.21c.342.052.682.107 1.022.166m-1.022-.165L18.16 19.673a2.25 2.25 0 0 1-2.244 2.077H8.084a2.25 2.25 0 0 1-2.244-2.077L4.772 5.79m14.456 0a48.108 48.108 0 0 0-3.478-.397m-12 .562c.34-.059.68-.114 1.022-.165m0 0a48.11 48.11 0 0 1 3.478-.397m7.5 0v-.916c0-1.18-.91-2.164-2.09-2.201a51.964 51.964 0 0 0-3.32 0c-1.18.037-2.09 1.022-2.09 2.201v.916m7.5 0a48.667 48.667 0 0 0-7.5 0"
+																/>
+															</svg>
+														</button>
+													</Tooltip>
+												</div>
+											</td>
+										</tr>
+									{/each}
+								</tbody>
+							</table>
+						</div>
+						<!-- {#each chats as chat}
+							<div>
+								{JSON.stringify(chat)}
+							</div>
+						{/each} -->
+					</div>
+				{:else}
+					<div class="text-left text-sm w-full mb-8">You have no archived conversations.</div>
+				{/if}
+			</div>
+		</div>
+	</div>
+</Modal>

src/lib/components/chat/MessageInput.svelte

@@ -13,6 +13,7 @@
 	import Models from './MessageInput/Models.svelte';
 	import { transcribeAudio } from '$lib/apis/audio';
 	import Tooltip from '../common/Tooltip.svelte';
+	import Page from '../../../routes/(app)/+page.svelte';
 
 	const i18n = getContext('i18n');
 
@@ -688,11 +689,13 @@
 								: $i18n.t('Send a Message')}
 							bind:value={prompt}
 							on:keypress={(e) => {
-								if (e.keyCode == 13 && !e.shiftKey) {
-									e.preventDefault();
-								}
-								if (prompt !== '' && e.keyCode == 13 && !e.shiftKey) {
-									submitPrompt(prompt, user);
+								if (window.innerWidth > 1024) {
+									if (e.keyCode == 13 && !e.shiftKey) {
+										e.preventDefault();
+									}
+									if (prompt !== '' && e.keyCode == 13 && !e.shiftKey) {
+										submitPrompt(prompt, user);
+									}
 								}
 							}}
 							on:keydown={async (e) => {
@@ -756,7 +759,11 @@
 										...document.getElementsByClassName('selected-command-option-button')
 									]?.at(-1);
 
-									commandOptionButton?.click();
+									if (commandOptionButton) {
+										commandOptionButton?.click();
+									} else {
+										document.getElementById('send-message-button')?.click();
+									}
 								}
 
 								if (['/', '#', '@'].includes(prompt.charAt(0)) && e.key === 'Tab') {
@@ -895,6 +902,7 @@
 
 								<Tooltip content={$i18n.t('Send message')}>
 									<button
+										id="send-message-button"
 										class="{prompt !== ''
 											? 'bg-black text-white hover:bg-gray-900 dark:bg-white dark:text-black dark:hover:bg-gray-100 '
 											: 'text-white bg-gray-100 dark:text-gray-900 dark:bg-gray-800 disabled'} transition rounded-full p-1.5 self-center"

src/lib/components/chat/Messages/ResponseMessage.svelte

@@ -133,8 +133,9 @@
 	};
 
 	const renderLatex = () => {
-		let chatMessageElements = document.getElementsByClassName('chat-assistant');
-		// let lastChatMessageElement = chatMessageElements[chatMessageElements.length - 1];
+		let chatMessageElements = document
+			.getElementById(`message-${message.id}`)
+			?.getElementsByClassName('chat-assistant');
 
 		for (const element of chatMessageElements) {
 			auto_render(element, {
@@ -322,7 +323,7 @@
 </script>
 
 {#key message.id}
-	<div class=" flex w-full message-{message.id}">
+	<div class=" flex w-full message-{message.id}" id="message-{message.id}">
 		<ProfileImage
 			src={modelfiles[message.model]?.imageUrl ?? `${WEBUI_BASE_URL}/static/favicon.png`}
 		/>
@@ -376,7 +377,7 @@
 
 								<div class=" mt-2 mb-1 flex justify-center space-x-2 text-sm font-medium">
 									<button
-										class="px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded-lg"
+										class="px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg-lg"
 										on:click={() => {
 											editMessageConfirmHandler();
 										}}

src/lib/components/chat/Messages/UserMessage.svelte

@@ -193,7 +193,7 @@
 					<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"
+							class="px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg-lg"
 							on:click={() => {
 								editMessageConfirmHandler();
 							}}

src/lib/components/chat/Settings/Advanced.svelte

@@ -125,7 +125,7 @@
 
 	<div class="flex justify-end pt-3 text-sm font-medium">
 		<button
-			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 			on:click={() => {
 				saveSettings({
 					options: {

src/lib/components/chat/Settings/Chats.svelte

@@ -2,7 +2,7 @@
 	import fileSaver from 'file-saver';
 	const { saveAs } = fileSaver;
 
-	import { chats, user } from '$lib/stores';
+	import { chats, user, config } from '$lib/stores';
 
 	import {
 		createNewChat,

src/lib/components/chat/Settings/General.svelte

@@ -147,8 +147,8 @@
 						<option value="dark">🌑 {$i18n.t('Dark')}</option>
 						<option value="oled-dark">🌃 {$i18n.t('OLED Dark')}</option>
 						<option value="light">☀️ {$i18n.t('Light')}</option>
-						<option value="rose-pine dark">🪻 {$i18n.t('Rosé Pine')}</option>
-						<option value="rose-pine-dawn light">🌷 {$i18n.t('Rosé Pine Dawn')}</option>
+						<!-- <option value="rose-pine dark">🪻 {$i18n.t('Rosé Pine')}</option>
+						<option value="rose-pine-dawn light">🌷 {$i18n.t('Rosé Pine Dawn')}</option> -->
 					</select>
 				</div>
 			</div>

src/lib/components/documents/AddDocModal.svelte

@@ -161,7 +161,7 @@
 
 					<div class="flex justify-end pt-5 text-sm font-medium">
 						<button
-							class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+							class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 							type="submit"
 						>
 							{$i18n.t('Save')}

src/lib/components/documents/EditDocModal.svelte

@@ -158,7 +158,7 @@
 
 					<div class="flex justify-end pt-5 text-sm font-medium">
 						<button
-							class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+							class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 							type="submit"
 						>
 							{$i18n.t('Save')}

src/lib/components/documents/Settings/General.svelte

@@ -8,7 +8,9 @@
 		updateQuerySettings,
 		resetVectorDB,
 		getEmbeddingConfig,
-		updateEmbeddingConfig
+		updateEmbeddingConfig,
+		getRerankingConfig,
+		updateRerankingConfig
 	} from '$lib/apis/rag';
 
 	import { documents, models } from '$lib/stores';
@@ -23,11 +25,13 @@
 
 	let scanDirLoading = false;
 	let updateEmbeddingModelLoading = false;
+	let updateRerankingModelLoading = false;
 
 	let showResetConfirm = false;
 
 	let embeddingEngine = '';
 	let embeddingModel = '';
+	let rerankingModel = '';
 
 	let OpenAIKey = '';
 	let OpenAIUrl = '';
@@ -38,7 +42,9 @@
 
 	let querySettings = {
 		template: '',
-		k: 4
+		r: 0.0,
+		k: 4,
+		hybrid: false
 	};
 
 	const scanHandler = async () => {
@@ -115,6 +121,29 @@
 		}
 	};
 
+	const rerankingModelUpdateHandler = async () => {
+		console.log('Update reranking model attempt:', rerankingModel);
+
+		updateRerankingModelLoading = true;
+		const res = await updateRerankingConfig(localStorage.token, {
+			reranking_model: rerankingModel
+		}).catch(async (error) => {
+			toast.error(error);
+			await setRerankingConfig();
+			return null;
+		});
+		updateRerankingModelLoading = false;
+
+		if (res) {
+			console.log('rerankingModelUpdateHandler:', res);
+			if (res.status === true) {
+				toast.success($i18n.t('Reranking model set to "{{reranking_model}}"', res), {
+					duration: 1000 * 10
+				});
+			}
+		}
+	};
+
 	const submitHandler = async () => {
 		const res = await updateRAGConfig(localStorage.token, {
 			pdf_extract_images: pdfExtractImages,
@@ -138,6 +167,20 @@
 		}
 	};
 
+	const setRerankingConfig = async () => {
+		const rerankingConfig = await getRerankingConfig(localStorage.token);
+
+		if (rerankingConfig) {
+			rerankingModel = rerankingConfig.reranking_model;
+		}
+	};
+
+	const toggleHybridSearch = async () => {
+		querySettings.hybrid = !querySettings.hybrid;
+
+		querySettings = await updateQuerySettings(localStorage.token, querySettings);
+	};
+
 	onMount(async () => {
 		const res = await getRAGConfig(localStorage.token);
 
@@ -149,6 +192,7 @@
 		}
 
 		await setEmbeddingConfig();
+		await setRerankingConfig();
 
 		querySettings = await getQuerySettings(localStorage.token);
 	});
@@ -165,6 +209,24 @@
 		<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">{$i18n.t('Hybrid Search')}</div>
+
+				<button
+					class="p-1 px-3 text-xs flex rounded transition"
+					on:click={() => {
+						toggleHybridSearch();
+					}}
+					type="button"
+				>
+					{#if querySettings.hybrid === true}
+						<span class="ml-2 self-center">{$i18n.t('On')}</span>
+					{:else}
+						<span class="ml-2 self-center">{$i18n.t('Off')}</span>
+					{/if}
+				</button>
+			</div>
+
 			<div class=" flex w-full justify-between">
 				<div class=" self-center text-xs font-medium">{$i18n.t('Embedding Model Engine')}</div>
 				<div class="flex items-center relative">
@@ -349,6 +411,75 @@
 
 				<hr class=" dark:border-gray-700 my-3" />
 
+				{#if querySettings.hybrid === true}
+					<div class=" ">
+						<div class=" mb-2 text-sm font-medium">{$i18n.t('Update Reranking Model')}</div>
+
+						<div class="flex w-full">
+							<div class="flex-1 mr-2">
+								<input
+									class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+									placeholder={$i18n.t('Update reranking model (e.g. {{model}})', {
+										model: rerankingModel.slice(-40)
+									})}
+									bind:value={rerankingModel}
+								/>
+							</div>
+							<button
+								class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-gray-100 rounded-lg transition"
+								on:click={() => {
+									rerankingModelUpdateHandler();
+								}}
+								disabled={updateRerankingModelLoading}
+							>
+								{#if updateRerankingModelLoading}
+									<div class="self-center">
+										<svg
+											class=" w-4 h-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>
+								{:else}
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 16 16"
+										fill="currentColor"
+										class="w-4 h-4"
+									>
+										<path
+											d="M8.75 2.75a.75.75 0 0 0-1.5 0v5.69L5.03 6.22a.75.75 0 0 0-1.06 1.06l3.5 3.5a.75.75 0 0 0 1.06 0l3.5-3.5a.75.75 0 0 0-1.06-1.06L8.75 8.44V2.75Z"
+										/>
+										<path
+											d="M3.5 9.75a.75.75 0 0 0-1.5 0v1.5A2.75 2.75 0 0 0 4.75 14h6.5A2.75 2.75 0 0 0 14 11.25v-1.5a.75.75 0 0 0-1.5 0v1.5c0 .69-.56 1.25-1.25 1.25h-6.5c-.69 0-1.25-.56-1.25-1.25v-1.5Z"
+										/>
+									</svg>
+								{/if}
+							</button>
+						</div>
+					</div>
+
+					<hr class=" dark:border-gray-700 my-3" />
+				{/if}
+
 				<div class="  flex w-full justify-between">
 					<div class=" self-center text-xs font-medium">
 						{$i18n.t('Scan for documents from {{path}}', { path: '/data/docs' })}
@@ -473,6 +604,28 @@
 						</div>
 					</div>
 
+					{#if querySettings.hybrid === true}
+						<div class=" flex">
+							<div class="  flex w-full justify-between">
+								<div class="self-center text-xs font-medium flex-1">
+									{$i18n.t('Relevance Threshold')}
+								</div>
+
+								<div class="self-center p-3">
+									<input
+										class=" w-full rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+										type="number"
+										step="0.01"
+										placeholder={$i18n.t('Enter Relevance Threshold')}
+										bind:value={querySettings.r}
+										autocomplete="off"
+										min="0.0"
+									/>
+								</div>
+							</div>
+						</div>
+					{/if}
+
 					<div>
 						<div class=" mb-2.5 text-sm font-medium">{$i18n.t('RAG Template')}</div>
 						<textarea
@@ -581,7 +734,7 @@
 	</div>
 	<div class="flex justify-end pt-3 text-sm font-medium">
 		<button
-			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
 			type="submit"
 		>
 			{$i18n.t('Save')}

src/lib/components/icons/ChatBubble.svelte

@@ -0,0 +1,19 @@
+<script lang="ts">
+	export let className = 'size-4';
+	export let strokeWidth = '1.5';
+</script>
+
+<svg
+	xmlns="http://www.w3.org/2000/svg"
+	fill="none"
+	viewBox="0 0 24 24"
+	stroke-width={strokeWidth}
+	stroke="currentColor"
+	class={className}
+>
+	<path
+		stroke-linecap="round"
+		stroke-linejoin="round"
+		d="M8.625 12a.375.375 0 1 1-.75 0 .375.375 0 0 1 .75 0Zm0 0H8.25m4.125 0a.375.375 0 1 1-.75 0 .375.375 0 0 1 .75 0Zm0 0H12m4.125 0a.375.375 0 1 1-.75 0 .375.375 0 0 1 .75 0Zm0 0h-.375M21 12c0 4.556-4.03 8.25-9 8.25a9.764 9.764 0 0 1-2.555-.337A5.972 5.972 0 0 1 5.41 20.97a5.969 5.969 0 0 1-.474-.065 4.48 4.48 0 0 0 .978-2.025c.09-.457-.133-.901-.467-1.226C3.93 16.178 3 14.189 3 12c0-4.556 4.03-8.25 9-8.25s9 3.694 9 8.25Z"
+	/>
+</svg>

src/lib/components/icons/ChatBubbles.svelte

@@ -0,0 +1,19 @@
+<script lang="ts">
+	export let className = 'size-4';
+	export let strokeWidth = '1.5';
+</script>
+
+<svg
+	xmlns="http://www.w3.org/2000/svg"
+	fill="none"
+	viewBox="0 0 24 24"
+	stroke-width={strokeWidth}
+	stroke="currentColor"
+	class={className}
+>
+	<path
+		stroke-linecap="round"
+		stroke-linejoin="round"
+		d="M20.25 8.511c.884.284 1.5 1.128 1.5 2.097v4.286c0 1.136-.847 2.1-1.98 2.193-.34.027-.68.052-1.02.072v3.091l-3-3c-1.354 0-2.694-.055-4.02-.163a2.115 2.115 0 0 1-.825-.242m9.345-8.334a2.126 2.126 0 0 0-.476-.095 48.64 48.64 0 0 0-8.048 0c-1.131.094-1.976 1.057-1.976 2.192v4.286c0 .837.46 1.58 1.155 1.951m9.345-8.334V6.637c0-1.621-1.152-3.026-2.76-3.235A48.455 48.455 0 0 0 11.25 3c-2.115 0-4.198.137-6.24.402-1.608.209-2.76 1.614-2.76 3.235v6.226c0 1.621 1.152 3.026 2.76 3.235.577.075 1.157.14 1.74.194V21l4.155-4.155"
+	/>
+</svg>

src/lib/components/layout/Navbar/Menu.svelte

@@ -4,8 +4,6 @@
 	import fileSaver from 'file-saver';
 	const { saveAs } = fileSaver;
 
-	import { jsPDF } from 'jspdf';
-
 	import { showSettings } from '$lib/stores';
 	import { flyAndScale } from '$lib/utils/transitions';
 

src/lib/components/layout/Sidebar.svelte

@@ -29,6 +29,7 @@
 	import ArchiveBox from '../icons/ArchiveBox.svelte';
 	import ArchivedChatsModal from './Sidebar/ArchivedChatsModal.svelte';
 
+	const BREAKPOINT = 1024;
 	let show = false;
 	let navElement;
 
@@ -49,9 +50,7 @@
 	let isEditing = false;
 
 	onMount(async () => {
-		if (window.innerWidth > 1024) {
-			show = true;
-		}
+		show = window.innerWidth > BREAKPOINT;
 		await chats.set(await getChatList(localStorage.token));
 
 		let touchstartX = 0;
@@ -79,12 +78,20 @@
 			checkDirection();
 		};
 
+		const onResize = () => {
+			if (show && window.innerWidth < BREAKPOINT) {
+				show = false;
+			}
+		};
+
 		document.addEventListener('touchstart', onTouchStart);
 		document.addEventListener('touchend', onTouchEnd);
+		window.addEventListener('resize', onResize);
 
 		return () => {
 			document.removeEventListener('touchstart', onTouchStart);
 			document.removeEventListener('touchend', onTouchEnd);
+			document.removeEventListener('resize', onResize);
 		};
 	});
 
@@ -172,7 +179,7 @@
 		<div class="px-2 flex justify-center space-x-2">
 			<a
 				id="sidebar-new-chat-button"
-				class="flex-grow flex justify-between rounded-xl px-4 py-2 hover:bg-gray-200 dark:hover:bg-gray-900 transition"
+				class="flex-grow flex justify-between rounded-xl px-4 py-2 hover:bg-gray-100 dark:hover:bg-gray-900 transition"
 				href="/"
 				on:click={async () => {
 					selectedChatId = null;
@@ -217,7 +224,7 @@
 		{#if $user?.role === 'admin'}
 			<div class="px-2 flex justify-center mt-0.5">
 				<a
-					class="flex-grow flex space-x-3 rounded-xl px-3.5 py-2 hover:bg-gray-200 dark:hover:bg-gray-900 transition"
+					class="flex-grow flex space-x-3 rounded-xl px-3.5 py-2 hover:bg-gray-100 dark:hover:bg-gray-900 transition"
 					href="/modelfiles"
 					on:click={() => {
 						selectedChatId = null;
@@ -249,7 +256,7 @@
 
 			<div class="px-2 flex justify-center">
 				<a
-					class="flex-grow flex space-x-3 rounded-xl px-3.5 py-2 hover:bg-gray-200 dark:hover:bg-gray-900 transition"
+					class="flex-grow flex space-x-3 rounded-xl px-3.5 py-2 hover:bg-gray-100 dark:hover:bg-gray-900 transition"
 					href="/prompts"
 					on:click={() => {
 						selectedChatId = null;
@@ -281,7 +288,7 @@
 
 			<div class="px-2 flex justify-center mb-1">
 				<a
-					class="flex-grow flex space-x-3 rounded-xl px-3.5 py-2 hover:bg-gray-200 dark:hover:bg-gray-900 transition"
+					class="flex-grow flex space-x-3 rounded-xl px-3.5 py-2 hover:bg-gray-100 dark:hover:bg-gray-900 transition"
 					href="/documents"
 					on:click={() => {
 						selectedChatId = null;
@@ -328,7 +335,7 @@
 
 						<div class="mt-3">
 							<button
-								class="flex justify-center items-center space-x-1.5 px-3 py-2.5 rounded-lg text-xs bg-gray-200 hover:bg-gray-300 transition text-gray-800 font-medium w-full"
+								class="flex justify-center items-center space-x-1.5 px-3 py-2.5 rounded-lg text-xs bg-gray-100 hover:bg-gray-200 transition text-gray-800 font-medium w-full"
 								type="button"
 								on:click={() => {
 									saveSettings({
@@ -438,7 +445,7 @@
 								class=" w-full flex justify-between rounded-xl px-3 py-2 {chat.id === $chatId ||
 								chat.id === chatTitleEditId ||
 								chat.id === chatDeleteId
-									? 'bg-gray-300 dark:bg-gray-900'
+									? 'bg-gray-200 dark:bg-gray-900'
 									: chat.id === selectedChatId
 									? 'bg-gray-100 dark:bg-gray-950'
 									: 'group-hover:bg-gray-100 dark:group-hover:bg-gray-950'}  whitespace-nowrap text-ellipsis"
@@ -450,7 +457,7 @@
 								class=" w-full flex justify-between rounded-xl px-3 py-2 {chat.id === $chatId ||
 								chat.id === chatTitleEditId ||
 								chat.id === chatDeleteId
-									? 'bg-gray-300 dark:bg-gray-900'
+									? 'bg-gray-200 dark:bg-gray-900'
 									: chat.id === selectedChatId
 									? 'bg-gray-100 dark:bg-gray-950'
 									: ' group-hover:bg-gray-100 dark:group-hover:bg-gray-950'}  whitespace-nowrap text-ellipsis"
@@ -473,14 +480,14 @@
 
 						<div
 							class="
-							
+
 							{chat.id === $chatId || chat.id === chatTitleEditId || chat.id === chatDeleteId
-								? 'from-gray-300 dark:from-gray-900'
+								? 'from-gray-200 dark:from-gray-900'
 								: chat.id === selectedChatId
 								? 'from-gray-100 dark:from-gray-950'
 								: 'invisible group-hover:visible from-gray-100 dark:from-gray-950'}
 								absolute right-[10px] top-[10px] pr-2 pl-5 bg-gradient-to-l from-80%
-								
+
 								  to-transparent"
 						>
 							{#if chatTitleEditId === chat.id}
@@ -628,7 +635,7 @@
 			<div class="flex flex-col">
 				{#if $user !== undefined}
 					<button
-						class=" flex rounded-xl py-3 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-900 transition"
+						class=" flex rounded-xl py-3 px-3.5 w-full hover:bg-gray-100 dark:hover:bg-gray-900 transition"
 						on:click={() => {
 							showDropdown = !showDropdown;
 						}}

src/lib/components/layout/Sidebar/ArchivedChatsModal.svelte

@@ -69,9 +69,9 @@
 				{#if chats.length > 0}
 					<div class="text-left text-sm w-full mb-4 max-h-[22rem] overflow-y-scroll">
 						<div class="relative overflow-x-auto">
-							<table class="w-full text-sm text-left text-gray-500 dark:text-gray-400 table-auto">
+							<table class="w-full text-sm text-left text-gray-600 dark:text-gray-400 table-auto">
 								<thead
-									class="text-xs text-gray-700 uppercase bg-transparent dark:text-gray-200 border-b-2 border-gray-800"
+									class="text-xs text-gray-700 uppercase bg-transparent dark:text-gray-200 border-b-2 dark:border-gray-800"
 								>
 									<tr>
 										<th scope="col" class="px-3 py-2"> {$i18n.t('Name')} </th>
@@ -82,7 +82,7 @@
 								<tbody>
 									{#each chats as chat, idx}
 										<tr
-											class="bg-white {idx !== chats.length - 1 &&
+											class="bg-transparent {idx !== chats.length - 1 &&
 												'border-b'} dark:bg-gray-900 dark:border-gray-850 text-xs"
 										>
 											<td class="px-3 py-1 w-2/3">

src/lib/i18n/locales/bn-BD/translation.json

@@ -0,0 +1,373 @@
+{
+	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' অথবা অনির্দিষ্টকাল মেয়াদের জন্য '-1' ",
+	"(Beta)": "(পরিক্ষামূলক)",
+	"(e.g. `sh webui.sh --api`)": "(যেমন `sh webui.sh --api`)",
+	"(latest)": "(সর্বশেষ)",
+	"{{modelName}} is thinking...": "{{modelName}} চিন্তা করছে...",
+	"{{webUIName}} Backend Required": "{{webUIName}} ব্যাকএন্ড আবশ্যক",
+	"a user": "একজন ব্যাবহারকারী",
+	"About": "সম্পর্কে",
+	"Account": "একাউন্ট",
+	"Action": "একশন",
+	"Add a model": "একটি মডেল যোগ করুন",
+	"Add a model tag name": "একটি মডেল ট্যাগ যোগ করুন",
+	"Add a short description about what this modelfile does": "এই মডেলফাইলটির সম্পর্কে সংক্ষিপ্ত বিবরণ যোগ করুন",
+	"Add a short title for this prompt": "এই প্রম্পটের জন্য একটি সংক্ষিপ্ত টাইটেল যোগ করুন",
+	"Add a tag": "একটি ট্যাগ যোগ করুন",
+	"Add Docs": "ডকুমেন্ট যোগ করুন",
+	"Add Files": "ফাইল যোগ করুন",
+	"Add message": "মেসেজ যোগ করুন",
+	"add tags": "ট্যাগ যোগ করুন",
+	"Adjusting these settings will apply changes universally to all users.": "এই সেটিংগুলো পরিবর্তন করলে তা সব ইউজারের উপরেই প্রয়োগ করা হবে",
+	"admin": "এডমিন",
+	"Admin Panel": "এডমিন প্যানেল",
+	"Admin Settings": "এডমিন সেটিংস",
+	"Advanced Parameters": "এডভান্সড প্যারামিটার্স",
+	"all": "সব",
+	"All Users": "সব ইউজার",
+	"Allow": "অনুমোদন",
+	"Allow Chat Deletion": "চ্যাট ডিলিট করতে দিন",
+	"alphanumeric characters and hyphens": "ইংরেজি অক্ষর, সংখ্যা এবং হাইফেন",
+	"Already have an account?": "আগে থেকেই একাউন্ট আছে?",
+	"an assistant": "একটা এসিস্ট্যান্ট",
+	"and": "এবং",
+	"API Base URL": "এপিআই বেজ ইউআরএল",
+	"API Key": "এপিআই কোড",
+	"API RPM": "এপিআই আরপিএম",
+	"are allowed - Activate this command by typing": "অনুমোদিত - কমান্ডটি চালু করার জন্য লিখুন",
+	"Are you sure?": "আপনি নিশ্চিত?",
+	"Audio": "অডিও",
+	"Auto-playback response": "রেসপন্স অটো-প্লেব্যাক",
+	"Auto-send input after 3 sec.": "৩ সেকেন্ড পর ইনপুট সংয়ক্রিয়ভাবে পাঠান",
+	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 বেজ ইউআরএল",
+	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 বেজ ইউআরএল আবশ্যক",
+	"available!": "উপলব্ধ!",
+	"Back": "পেছনে",
+	"Builder Mode": "বিল্ডার মোড",
+	"Cancel": "বাতিল",
+	"Categories": "ক্যাটাগরিসমূহ",
+	"Change Password": "পাসওয়ার্ড পরিবর্তন করুন",
+	"Chat": "চ্যাট",
+	"Chat History": "চ্যাট হিস্টোরি",
+	"Chat History is off for this browser.": "এই ব্রাউজারের জন্য চ্যাট হিস্টোরি বন্ধ আছে",
+	"Chats": "চ্যাটসমূহ",
+	"Check Again": "আবার চেক করুন",
+	"Check for updates": "নতুন আপডেট আছে কিনা চেক করুন",
+	"Checking for updates...": "নতুন আপডেট আছে কিনা চেক করা হচ্ছে...",
+	"Choose a model before saving...": "সেভ করার আগে একটি মডেল নির্বাচন করুন",
+	"Chunk Overlap": "চাঙ্ক ওভারল্যাপ",
+	"Chunk Params": "চাঙ্ক প্যারামিটার্স",
+	"Chunk Size": "চাঙ্ক সাইজ",
+	"Click here for help.": "সাহায্যের জন্য এখানে ক্লিক করুন",
+	"Click here to check other modelfiles.": "অন্যান্য মডেলফাইল চেক করার জন্য এখানে ক্লিক করুন",
+	"Click here to select": "নির্বাচন করার জন্য এখানে ক্লিক করুন",
+	"Click here to select documents.": "ডকুমেন্টগুলো নির্বাচন করার জন্য এখানে ক্লিক করুন",
+	"click here.": "এখানে ক্লিক করুন",
+	"Click on the user role button to change a user's role.": "ইউজারের পদবি পরিবর্তন করার জন্য ইউজারের পদবি বাটনে ক্লিক করুন",
+	"Close": "বন্ধ",
+	"Collection": "সংগ্রহ",
+	"Command": "কমান্ড",
+	"Confirm Password": "পাসওয়ার্ড নিশ্চিত করুন",
+	"Connections": "কানেকশনগুলো",
+	"Content": "বিষয়বস্তু",
+	"Context Length": "কনটেক্সটের দৈর্ঘ্য",
+	"Conversation Mode": "কথোপকথন মোড",
+	"Copy last code block": "সর্বশেষ কোড ব্লক কপি করুন",
+	"Copy last response": "সর্বশেষ রেসপন্স কপি করুন",
+	"Copying to clipboard was successful!": "ক্লিপবোর্ডে কপি করা সফল হয়েছে",
+	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "'title' শব্দটি ব্যবহার না করে নিম্মোক্ত অনুসন্ধানের জন্য সংক্ষেপে সর্বোচ্চ ৩-৫ শব্দের একটি হেডার তৈরি করুন",
+	"Create a modelfile": "একটি মডেলফাইল তৈরি করুন",
+	"Create Account": "একাউন্ট তৈরি করুন",
+	"Created at": "নির্মানকাল",
+	"Created by": "নির্মাতা",
+	"Current Model": "বর্তমান মডেল",
+	"Current Password": "বর্তমান পাসওয়ার্ড",
+	"Custom": "কাস্টম",
+	"Customize Ollama models for a specific purpose": "নির্দিষ্ট উদ্দেশ্যে Ollama মডেল পরিবর্তন করুন",
+	"Dark": "ডার্ক",
+	"Database": "ডেটাবেজ",
+	"DD/MM/YYYY HH:mm": "DD/MM/YYYY HH:mm",
+	"Default": "ডিফল্ট",
+	"Default (Automatic1111)": "ডিফল্ট (Automatic1111)",
+	"Default (Web API)": "ডিফল্ট (Web API)",
+	"Default model updated": "ডিফল্ট মডেল আপডেট হয়েছে",
+	"Default Prompt Suggestions": "ডিফল্ট প্রম্পট সাজেশন",
+	"Default User Role": "ইউজারের ডিফল্ট পদবি",
+	"delete": "মুছে ফেলুন",
+	"Delete a model": "একটি মডেল মুছে ফেলুন",
+	"Delete chat": "চ্যাট মুছে ফেলুন",
+	"Delete Chats": "চ্যাটগুলো মুছে ফেলুন",
+	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} মুছে ফেলা হয়েছে",
+	"Deleted {tagName}": "{tagName} মুছে ফেলা হয়েছে",
+	"Description": "বিবরণ",
+	"Notifications": "নোটিফিকেশনসমূহ",
+	"Disabled": "অক্ষম",
+	"Discover a modelfile": "একটি মডেলফাইল খুঁজে বের করুন",
+	"Discover a prompt": "একটি প্রম্পট খুঁজে বের করুন",
+	"Discover, download, and explore custom prompts": "কাস্টম প্রম্পটগুলো আবিস্কার, ডাউনলোড এবং এক্সপ্লোর করুন",
+	"Discover, download, and explore model presets": "মডেল প্রিসেটগুলো আবিস্কার, ডাউনলোড এবং এক্সপ্লোর করুন",
+	"Display the username instead of You in the Chat": "চ্যাটে 'আপনি'-র পরবর্তে ইউজারনেম দেখান",
+	"Document": "ডকুমেন্ট",
+	"Document Settings": "ডকুমেন্ট সেটিংসমূহ",
+	"Documents": "ডকুমেন্টসমূহ",
+	"does not make any external connections, and your data stays securely on your locally hosted server.": "কোন এক্সটার্নাল কানেকশন তৈরি করে না, এবং আপনার ডেটা আর লোকালি হোস্টেড সার্ভারেই নিরাপদে থাকে।",
+	"Don't Allow": "অনুমোদন দেবেন না",
+	"Don't have an account?": "একাউন্ট নেই?",
+	"Download as a File": "ফাইল হিসেবে ডাউনলোড করুন",
+	"Download Database": "ডেটাবেজ ডাউনলোড করুন",
+	"Drop any files here to add to the conversation": "আলোচনায় যুক্ত করার জন্য যে কোন ফাইল এখানে ড্রপ করুন",
+	"e.g. '30s','10m'. Valid time units are 's', 'm', 'h'.": "যেমন '30s','10m'. সময়ের অনুমোদিত অনুমোদিত এককগুলি হচ্ছে 's', 'm', 'h'.",
+	"Edit Doc": "ডকুমেন্ট এডিট করুন",
+	"Edit User": "ইউজার এডিট করুন",
+	"Email": "ইমেইল",
+	"Embedding model: {{embedding_model}}": "এমবেডিং মডেল: {{embedding_model}}",
+	"Enable Chat History": "চ্যাট হিস্টোরি চালু করুন",
+	"Enable New Sign Ups": "নতুন সাইনআপ চালু করুন",
+	"Enabled": "চালু করা হয়েছে",
+	"Enter {{role}} message here": "{{role}} মেসেজ এখানে লিখুন",
+	"Enter API Key": "API Key লিখুন",
+	"Enter Chunk Overlap": "চাঙ্ক ওভারল্যাপ লিখুন",
+	"Enter Chunk Size": "চাংক সাইজ লিখুন",
+	"Enter Image Size (e.g. 512x512)": "ছবির মাপ লিখুন (যেমন 512x512)",
+	"Enter LiteLLM API Base URL (litellm_params.api_base)": "LiteLLM এপিআই বেজ ইউআরএল লিখুন (litellm_params.api_base)",
+	"Enter LiteLLM API Key (litellm_params.api_key)": "LiteLLM এপিআই কোড লিখুন (litellm_params.api_key)",
+	"Enter LiteLLM API RPM (litellm_params.rpm)": "LiteLLM এপিআই RPM দিন (litellm_params.rpm)",
+	"Enter LiteLLM Model (litellm_params.model)": "LiteLLM মডেল দিন (litellm_params.model)",
+	"Enter Max Tokens (litellm_params.max_tokens)": "সর্বোচ্চ টোকেন সংখ্যা দিন (litellm_params.max_tokens)",
+	"Enter model tag (e.g. {{modelTag}})": "মডেল ট্যাগ লিখুন (e.g. {{modelTag}})",
+	"Enter Number of Steps (e.g. 50)": "ধাপের সংখ্যা দিন (যেমন: 50)",
+	"Enter stop sequence": "স্টপ সিকোয়েন্স লিখুন",
+	"Enter Top K": "Top K লিখুন",
+	"Enter URL (e.g. http://127.0.0.1:7860/)": "ইউআরএল দিন (যেমন http://127.0.0.1:7860/)",
+	"Enter Your Email": "আপনার ইমেইল লিখুন",
+	"Enter Your Full Name": "আপনার পূর্ণ নাম লিখুন",
+	"Enter Your Password": "আপনার পাসওয়ার্ড লিখুন",
+	"Experimental": "পরিক্ষামূলক",
+	"Export All Chats (All Users)": "সব চ্যাট এক্সপোর্ট করুন (সব ইউজারের)",
+	"Export Chats": "চ্যাটগুলো এক্সপোর্ট করুন",
+	"Export Documents Mapping": "ডকুমেন্টসমূহ ম্যাপিং এক্সপোর্ট করুন",
+	"Export Modelfiles": "মডেলফাইলগুলো এক্সপোর্ট করুন",
+	"Export Prompts": "প্রম্পটগুলো একপোর্ট করুন",
+	"Failed to read clipboard contents": "ক্লিপবোর্ডের বিষয়বস্তু পড়া সম্ভব হয়নি",
+	"File Mode": "ফাইল মোড",
+	"File not found.": "ফাইল পাওয়া যায়নি",
+	"Fingerprint spoofing detected: Unable to use initials as avatar. Defaulting to default profile image.": "ফিঙ্গারপ্রিন্ট স্পুফিং ধরা পড়েছে: অ্যাভাটার হিসেবে নামের আদ্যক্ষর ব্যবহার করা যাচ্ছে না। ডিফল্ট প্রোফাইল পিকচারে ফিরিয়ে নেয়া হচ্ছে।",
+	"Fluidly stream large external response chunks": "বড় এক্সটার্নাল রেসপন্স চাঙ্কগুলো মসৃণভাবে প্রবাহিত করুন",
+	"Focus chat input": "চ্যাট ইনপুট ফোকাস করুন",
+	"Format your variables using square brackets like this:": "আপনার ভেরিয়বলগুলো এভাবে স্কয়ার ব্রাকেটের মাধ্যমে সাজান",
+	"From (Base Model)": "উৎস (বেজ মডেল)",
+	"Full Screen Mode": "ফুলস্ক্রিন মোড",
+	"General": "সাধারণ",
+	"General Settings": "সাধারণ সেটিংসমূহ",
+	"Hello, {{name}}": "হ্যালো, {{name}}",
+	"Hide": "লুকান",
+	"Hide Additional Params": "অতিরিক্ত প্যারামিটাগুলো লুকান",
+	"How can I help you today?": "আপনাকে আজ কিভাবে সাহায্য করতে পারি?",
+	"Image Generation (Experimental)": "ইমেজ জেনারেশন (পরিক্ষামূলক)",
+	"Image Generation Engine": "ইমেজ জেনারেশন ইঞ্জিন",
+	"Image Settings": "ছবির সেটিংসমূহ",
+	"Images": "ছবিসমূহ",
+	"Import Chats": "চ্যাটগুলি ইমপোর্ট করুন",
+	"Import Documents Mapping": "ডকুমেন্টসমূহ ম্যাপিং ইমপোর্ট করুন",
+	"Import Modelfiles": "মডেলফাইলগুলো ইমপোর্ট করুন",
+	"Import Prompts": "প্রম্পটগুলো ইমপোর্ট করুন",
+	"Include `--api` flag when running stable-diffusion-webui": "stable-diffusion-webui চালু করার সময় `--api` ফ্ল্যাগ সংযুক্ত করুন",
+	"Interface": "ইন্টারফেস",
+	"join our Discord for help.": "সাহায্যের জন্য আমাদের Discord-এ যুক্ত হোন",
+	"JSON": "JSON",
+	"JWT Expiration": "JWT-র মেয়াদ",
+	"JWT Token": "JWT টোকেন",
+	"Keep Alive": "সচল রাখুন",
+	"Keyboard shortcuts": "কিবোর্ড শর্টকাটসমূহ",
+	"Language": "ভাষা",
+	"Light": "লাইট",
+	"Listening...": "শুনছে...",
+	"LLMs can make mistakes. Verify important information.": "LLM ভুল করতে পারে। গুরুত্বপূর্ণ তথ্য যাচাই করে নিন।",
+	"Made by OpenWebUI Community": "OpenWebUI কমিউনিটিকর্তৃক নির্মিত",
+	"Make sure to enclose them with": "এটা দিয়ে বন্ধনী দিতে ভুলবেন না",
+	"Manage LiteLLM Models": "LiteLLM মডেল ব্যবস্থাপনা করুন",
+	"Manage Models": "মডেলসমূহ ব্যবস্থাপনা করুন",
+	"Manage Ollama Models": "Ollama মডেলসূহ ব্যবস্থাপনা করুন",
+	"Max Tokens": "সর্বোচ্চ টোকন",
+	"Maximum of 3 models can be downloaded simultaneously. Please try again later.": "একসঙ্গে সর্বোচ্চ তিনটি মডেল ডাউনলোড করা যায়। দয়া করে পরে আবার চেষ্টা করুন।",
+	"Mirostat": "Mirostat",
+	"Mirostat Eta": "Mirostat Eta",
+	"Mirostat Tau": "Mirostat Tau",
+	"MMMM DD, YYYY": "MMMM DD, YYYY",
+	"Model '{{modelName}}' has been successfully downloaded.": "'{{modelName}}' মডেল সফলভাবে ডাউনলোড হয়েছে।",
+	"Model '{{modelTag}}' is already in queue for downloading.": "{{modelTag}} ডাউনলোডের জন্য আগে থেকেই অপেক্ষমান আছে।",
+	"Model {{embedding_model}} update complete!": "{{embedding_model}} মডেল আপডেট হয়ে গেছে!",
+	"Model {{embedding_model}} update failed or not required!": "{{embedding_model}} মডেল আপডেট ব্যর্থ হয়েছে অথবা প্রয়োজন নেই",
+	"Model {{modelId}} not found": "{{modelId}} মডেল পাওয়া যায়নি",
+	"Model {{modelName}} already exists.": "{{modelName}} মডেল আগে থেকেই আছে",
+	"Model filesystem path detected. Model shortname is required for update, cannot continue.": "মডেল ফাইলসিস্টেম পাথ পাওয়া গেছে। আপডেটের জন্য মডেলের শর্টনেম আবশ্যক, এগিয়ে যাওয়া যাচ্ছে না।",
+	"Model Name": "মডেলের নাম",
+	"Model not selected": "মডেল নির্বাচন করা হয়নি",
+	"Model Tag Name": "মডেলের ট্যাগ নাম",
+	"Model Whitelisting": "মডেল হোয়াইটলিস্টিং",
+	"Model(s) Whitelisted": "হোয়াইটলিস্টেড মডেল(সমূহ)",
+	"Modelfile": "মডেলফাইল",
+	"Modelfile Advanced Settings": "মডেলফাইল এডভান্সড সেটিসমূহ",
+	"Modelfile Content": "মডেলফাইল কনটেন্ট",
+	"Modelfiles": "মডেলফাইলসমূহ",
+	"Models": "মডেলসমূহ",
+	"My Documents": "আমার ডকুমেন্টসমূহ",
+	"My Modelfiles": "আমার মডেলফাইলসমূহ",
+	"My Prompts": "আমার প্রম্পটসমূহ",
+	"Name": "নাম",
+	"Name Tag": "নামের ট্যাগ",
+	"Name your modelfile": "আপনার মডেলফাইলের নাম দিন",
+	"New Chat": "নতুন চ্যাট",
+	"New Password": "নতুন পাসওয়ার্ড",
+	"Not sure what to add?": "কী যুক্ত করতে হবে নিশ্চিত না?",
+	"Not sure what to write? Switch to": "কী লিখতে হবে নিশ্চিত না? পরিবর্তন করুন:",
+	"Off": "বন্ধ",
+	"Okay, Let's Go!": "ঠিক আছে, চলুন যাই!",
+	"Ollama Base URL": "Ollama বেজ ইউআরএল",
+	"Ollama Version": "Ollama ভার্সন",
+	"On": "চালু",
+	"Only": "শুধুমাত্র",
+	"Only alphanumeric characters and hyphens are allowed in the command string.": "কমান্ড স্ট্রিং-এ শুধুমাত্র ইংরেজি অক্ষর, সংখ্যা এবং হাইফেন ব্যবহার করা যাবে।",
+	"Oops! Hold tight! Your files are still in the processing oven. We're cooking them up to perfection. Please be patient and we'll let you know once they're ready.": "আহা! আরেকটু ধৈর্য্য ধরুন! আপনার ফাইলগুলো এখনো প্রোসেস চলছে, আমরা ওগুলোকে সেরা প্রক্রিয়াজাত করছি। তৈরি হয়ে গেলে আপনাকে জানিয়ে দেয়া হবে।",
+	"Oops! Looks like the URL is invalid. Please double-check and try again.": "ওহ, মনে হচ্ছে ইউআরএলটা ইনভ্যালিড। দয়া করে আর চেক করে চেষ্টা করুন।",
+	"Oops! You're using an unsupported method (frontend only). Please serve the WebUI from the backend.": "আপনি একটা আনসাপোর্টেড পদ্ধতি (শুধু ফ্রন্টএন্ড) ব্যবহার করছেন। দয়া করে WebUI ব্যাকএন্ড থেকে চালনা করুন।",
+	"Open": "খোলা",
+	"Open AI": "Open AI",
+	"Open AI (Dall-E)": "Open AI (Dall-E)",
+	"Open new chat": "নতুন চ্যাট খুলুন",
+	"OpenAI API": "OpenAI এপিআই",
+	"OpenAI API Key": "OpenAI এপিআই কোড",
+	"OpenAI API Key is required.": "OpenAI API কোড আবশ্যক",
+	"or": "অথবা",
+	"Parameters": "প্যারামিটারসমূহ",
+	"Password": "পাসওয়ার্ড",
+	"PDF Extract Images (OCR)": "পিডিএফ এর ছবি থেকে লেখা বের করুন (OCR)",
+	"pending": "অপেক্ষমান",
+	"Permission denied when accessing microphone: {{error}}": "মাইক্রোফোন ব্যবহারের অনুমতি পাওয়া যায়নি: {{error}}",
+	"Playground": "খেলাঘর",
+	"Profile": "প্রোফাইল",
+	"Prompt Content": "প্রম্পট কন্টেন্ট",
+	"Prompt suggestions": "প্রম্পট সাজেশনসমূহ",
+	"Prompts": "প্রম্পটসমূহ",
+	"Pull a model from Ollama.com": "Ollama.com থেকে একটি টেনে আনুন আনুন",
+	"Pull Progress": "Pull চলমান",
+	"Query Params": "Query প্যারামিটারসমূহ",
+	"RAG Template": "RAG টেম্পলেট",
+	"Raw Format": "Raw ফরম্যাট",
+	"Record voice": "ভয়েস রেকর্ড করুন",
+	"Redirecting you to OpenWebUI Community": "আপনাকে OpenWebUI কমিউনিটিতে পাঠানো হচ্ছে",
+	"Release Notes": "রিলিজ নোটসমূহ",
+	"Repeat Last N": "রিপিট Last N",
+	"Repeat Penalty": "রিপিট প্যানাল্টি",
+	"Request Mode": "রিকোয়েস্ট মোড",
+	"Reset Vector Storage": "ভেক্টর স্টোরেজ রিসেট করুন",
+	"Response AutoCopy to Clipboard": "রেসপন্সগুলো স্বয়ংক্রিভাবে ক্লিপবোর্ডে কপি হবে",
+	"Role": "পদবি",
+	"Rosé Pine": "রোজ পাইন",
+	"Rosé Pine Dawn": "ভোরের রোজ পাইন",
+	"Save": "সংরক্ষণ",
+	"Save & Create": "সংরক্ষণ এবং তৈরি করুন",
+	"Save & Submit": "সংরক্ষণ এবং সাবমিট করুন",
+	"Save & Update": "সংরক্ষণ এবং আপডেট করুন",
+	"Saving chat logs directly to your browser's storage is no longer supported. Please take a moment to download and delete your chat logs by clicking the button below. Don't worry, you can easily re-import your chat logs to the backend through": "মাধ্যমে",
+	"Scan": "স্ক্যান",
+	"Scan complete!": "স্ক্যান সম্পন্ন হয়েছে!",
+	"Scan for documents from {{path}}": "ডকুমেন্টসমূহের জন্য {{path}} স্ক্যান করুন",
+	"Search": "অনুসন্ধান",
+	"Search Documents": "ডকুমেন্টসমূহ অনুসন্ধান করুন",
+	"Search Prompts": "প্রম্পটসমূহ অনুসন্ধান করুন",
+	"See readme.md for instructions": "নির্দেশিকার জন্য readme.md দেখুন",
+	"See what's new": "নতুন কী আছে দেখুন",
+	"Seed": "সীড",
+	"Select a mode": "একটি মডেল নির্বাচন করুন",
+	"Select a model": "একটি মডেল নির্বাচন করুন",
+	"Select an Ollama instance": "একটি Ollama ইন্সট্যান্স নির্বাচন করুন",
+	"Send a Message": "একটি মেসেজ পাঠান",
+	"Send message": "মেসেজ পাঠান",
+	"Server connection verified": "সার্ভার কানেকশন যাচাই করা হয়েছে",
+	"Set as default": "ডিফল্ট হিসেবে নির্ধারণ করুন",
+	"Set Default Model": "ডিফল্ট মডেল নির্ধারণ করুন",
+	"Set Image Size": "ছবির সাইজ নির্ধারণ করুন",
+	"Set Steps": "পরবর্তী ধাপসমূহ",
+	"Set Title Auto-Generation Model": "শিরোনাম অটোজেনারেশন মডেন নির্ধারণ করুন",
+	"Set Voice": "কন্ঠস্বর নির্ধারণ করুন",
+	"Settings": "সেটিংসমূহ",
+	"Settings saved successfully!": "সেটিংগুলো সফলভাবে সংরক্ষিত হয়েছে",
+	"Share to OpenWebUI Community": "OpenWebUI কমিউনিটিতে শেয়ার করুন",
+	"short-summary": "সংক্ষিপ্ত বিবরণ",
+	"Show": "দেখান",
+	"Show Additional Params": "অতিরিক্ত প্যারামিটারগুলো দেখান",
+	"Show shortcuts": "শর্টকাটগুলো দেখান",
+	"sidebar": "সাইডবার",
+	"Sign in": "সাইন ইন",
+	"Sign Out": "সাইন আউট",
+	"Sign up": "সাইন আপ",
+	"Speech recognition error: {{error}}": "স্পিচ রিকগনিশনে সমস্যা: {{error}}",
+	"Speech-to-Text Engine": "স্পিচ-টু-টেক্সট ইঞ্জিন",
+	"SpeechRecognition API is not supported in this browser.": "এই ব্রাউজার স্পিচরিকগনিশন এপিআই সাপোর্ট করে না।",
+	"Stop Sequence": "সিকোয়েন্স থামান",
+	"STT Settings": "STT সেটিংস",
+	"Submit": "সাবমিট",
+	"Success": "সফল",
+	"Successfully updated.": "সফলভাবে আপডেট হয়েছে",
+	"Sync All": "সব সিংক্রোনাইজ করুন",
+	"System": "সিস্টেম",
+	"System Prompt": "সিস্টেম প্রম্পট",
+	"Tags": "ট্যাগসমূহ",
+	"Temperature": "তাপমাত্রা",
+	"Template": "টেম্পলেট",
+	"Text Completion": "লেখা সম্পন্নকরণ",
+	"Text-to-Speech Engine": "টেক্সট-টু-স্পিচ ইঞ্জিন",
+	"Tfs Z": "Tfs Z",
+	"Theme": "থিম",
+	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "এটা নিশ্চিত করে যে, আপনার গুরুত্বপূর্ণ আলোচনা নিরাপদে আপনার ব্যাকএন্ড ডেটাবেজে সংরক্ষিত আছে। ধন্যবাদ!",
+	"This setting does not sync across browsers or devices.": "এই সেটিং অন্যন্য ব্রাউজার বা ডিভাইসের সাথে সিঙ্ক্রোনাইজ নয় না।",
+	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "পরামর্শ: একাধিক ভেরিয়েবল স্লট একের পর এক রিপ্লেস করার জন্য চ্যাট ইনপুটে কিবোর্ডের Tab বাটন ব্যবহার করুন।",
+	"Title": "শিরোনাম",
+	"Title Auto-Generation": "স্বয়ংক্রিয় শিরোনামগঠন",
+	"Title Generation Prompt": "শিরোনামগঠন প্রম্পট",
+	"to": "প্রতি",
+	"To access the available model names for downloading,": "ডাউনলোডের জন্য এভেইলএবল মডেলের নামগুলো এক্সেস করতে,",
+	"To access the GGUF models available for downloading,": "ডাউলোডের জন্য এভেইলএবল GGUF মডেলগুলো এক্সেস করতে,",
+	"to chat input.": "চ্যাট ইনপুটে",
+	"Toggle settings": "সেটিংস টোগল",
+	"Toggle sidebar": "সাইডবার টোগল",
+	"Top K": "Top K",
+	"Top P": "Top P",
+	"Trouble accessing Ollama?": "Ollama এক্সেস করতে সমস্যা হচ্ছে?",
+	"TTS Settings": "TTS সেটিংসমূহ",
+	"Type Hugging Face Resolve (Download) URL": "Hugging Face থেকে ডাউনলোড করার ইউআরএল টাইপ করুন",
+	"Uh-oh! There was an issue connecting to {{provider}}.": "ওহ-হো! {{provider}} এর সাথে কানেকশনে সমস্যা হয়েছে।",
+	"Understand that updating or changing your embedding model requires reset of the vector database and re-import of all documents. You have been warned!": "জেনে রাখুন, এমবেডিং মডেল আপডেট বা পরিবর্তন করতে হলে ভেক্টর ডেটাবেজ রিসেট করতে হবে এবং সব ডকুমেন্ট আবার নতুন করে ইমপোর্ট করতে হবে। এ বিষয়ে আপনাকে আগেই সাবধান করা হলো।",
+	"Unknown File Type '{{file_type}}', but accepting and treating as plain text": "অপরিচিত ফাইল ফরম্যাট '{{file_type}}', তবে প্লেইন টেক্সট হিসেবে গ্রহণ করা হলো",
+	"Update": "আপডেট",
+	"Update embedding model {{embedding_model}}": "{{embedding_model}} এমবেডিং মডেল আপডেট করুন",
+	"Update password": "পাসওয়ার্ড আপডেট করুন",
+	"Upload a GGUF model": "একটি GGUF মডেল আপলোড করুন",
+	"Upload files": "ফাইলগুলো আপলোড করুন",
+	"Upload Progress": "আপলোড হচ্ছে",
+	"URL Mode": "ইউআরএল মোড",
+	"Use '#' in the prompt input to load and select your documents.": "আপনার ডকুমেন্টসমূহ নির্বাচন করার জন্য আপনার প্রম্পট ইনপুটে '# ব্যবহার করুন।",
+	"Use Gravatar": "Gravatar ব্যবহার করুন",
+	"Use Initials": "নামের আদ্যক্ষর ব্যবহার করুন",
+	"user": "ব্যবহারকারী",
+	"User Permissions": "ইউজার পারমিশনসমূহ",
+	"Users": "ব্যাবহারকারীগণ",
+	"Utilize": "ইউটিলাইজ",
+	"Valid time units:": "সময়ের গ্রহণযোগ্য এককসমূহ:",
+	"variable": "ভেরিয়েবল",
+	"variable to have them replaced with clipboard content.": "ক্লিপবোর্ডের কন্টেন্ট দিয়ে যেই ভেরিয়েবল রিপ্লেস করা যাবে।",
+	"Version": "ভার্সন",
+	"Web": "ওয়েব",
+	"WebUI Add-ons": "WebUI এড-অনসমূহ",
+	"WebUI Settings": "WebUI সেটিংসমূহ",
+	"WebUI will make requests to": "WebUI যেখানে রিকোয়েস্ট পাঠাবে",
+	"What’s New in": "এতে নতুন কী",
+	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "যদি হিস্টোরি বন্ধ থাকে তাহলে এই ব্রাউজারের নতুন চ্যাটগুলো আপনার কোন ডিভাইসের হিস্টোরিতেই দেখা যাবে না।",
+	"Whisper (Local)": "Whisper (লোকাল)",
+	"Write a prompt suggestion (e.g. Who are you?)": "একটি প্রম্পট সাজেশন লিখুন (যেমন Who are you?)",
+	"Write a summary in 50 words that summarizes [topic or keyword].": "৫০ শব্দের মধ্যে [topic or keyword] এর একটি সারসংক্ষেপ লিখুন।",
+	"You": "আপনি",
+	"You're a helpful assistant.": "আপনি একজন উপকারী এসিস্ট্যান্ট",
+	"You're now logged in.": "আপনি এখন লগইন করা অবস্থায় আছেন"
+}

src/lib/i18n/locales/es-ES/translation.json

@@ -44,7 +44,7 @@
 	"available!": "¡disponible!",
 	"Back": "Vuelve atrás",
 	"Builder Mode": "Modo de Constructor",
-	"Cancel": "Cancela",
+	"Cancel": "Cancelar",
 	"Categories": "Categorías",
 	"Change Password": "Cambia la Contraseña",
 	"Chat": "Chat",
@@ -152,6 +152,7 @@
 	"File Mode": "Modo de archivo",
 	"File not found.": "Archivo no encontrado.",
 	"Fingerprint spoofing detected: Unable to use initials as avatar. Defaulting to default profile image.": "Se detectó suplantación de huellas: No se pueden usar las iniciales como avatar. Por defecto se utiliza la imagen de perfil predeterminada.",
+	"Fluidly stream large external response chunks": "Transmita con fluidez grandes fragmentos de respuesta externa",
 	"Focus chat input": "Enfoca la entrada del chat",
 	"Format your variables using square brackets like this:": "Formatee sus variables usando corchetes así:",
 	"From (Base Model)": "Desde (Modelo Base)",

src/lib/i18n/locales/languages.json

@@ -7,6 +7,10 @@
 		"code": "bg-BG",
 		"title": "Bulgarian (BG)"
 	},
+	{
+		"code": "bn-BD",
+		"title": "Banlga (বাংলা)"
+	},
 	{
 		"code": "ca-ES",
 		"title": "Catalan"

src/lib/i18n/locales/tr-TR/translation.json

@@ -120,6 +120,7 @@
 	"Edit Doc": "Belgeyi Düzenle",
 	"Edit User": "Kullanıcıyı Düzenle",
 	"Email": "E-posta",
+	"Embedding model: {{embedding_model}}": "Gömme modeli: {{embedding_model}}",
 	"Enable Chat History": "Sohbet Geçmişini Etkinleştir",
 	"Enable New Sign Ups": "Yeni Kayıtları Etkinleştir",
 	"Enabled": "Etkin",
@@ -150,6 +151,8 @@
 	"Failed to read clipboard contents": "Pano içeriği okunamadı",
 	"File Mode": "Dosya Modu",
 	"File not found.": "Dosya bulunamadı.",
+	"Fingerprint spoofing detected: Unable to use initials as avatar. Defaulting to default profile image.": "Parmak izi sahteciliği tespit edildi: Avatar olarak baş harfler kullanılamıyor. Varsayılan profil resmine dönülüyor.",
+	"Fluidly stream large external response chunks": "Büyük harici yanıt chunklarını akıcı bir şekilde yayınlayın",
 	"Focus chat input": "Sohbet girişine odaklan",
 	"Format your variables using square brackets like this:": "Değişkenlerinizi şu şekilde kare parantezlerle biçimlendirin:",
 	"From (Base Model)": "(Temel Model)'den",
@@ -193,8 +196,11 @@
 	"MMMM DD, YYYY": "DD MMMM YYYY",
 	"Model '{{modelName}}' has been successfully downloaded.": "'{{modelName}}' başarıyla indirildi.",
 	"Model '{{modelTag}}' is already in queue for downloading.": "'{{modelTag}}' zaten indirme sırasında.",
+	"Model {{embedding_model}} update complete!": "Model {{embedding_model}} güncellemesi tamamlandı!",
+	"Model {{embedding_model}} update failed or not required!": "Model {{embedding_model}} güncellemesi başarısız oldu veya gerekli değil!",
 	"Model {{modelId}} not found": "{{modelId}} bulunamadı",
 	"Model {{modelName}} already exists.": "{{modelName}} zaten mevcut.",
+	"Model filesystem path detected. Model shortname is required for update, cannot continue.": "Model dosya sistemi yolu algılandı. Güncelleme için model kısa adı gerekli, devam edilemiyor.",
 	"Model Name": "Model Adı",
 	"Model not selected": "Model seçilmedi",
 	"Model Tag Name": "Model Etiket Adı",
@@ -332,7 +338,10 @@
 	"TTS Settings": "TTS Ayarları",
 	"Type Hugging Face Resolve (Download) URL": "Hugging Face Resolve (Download) URL'sini Yazın",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Ah! {{provider}}'a bağlanırken bir sorun oluştu.",
+	"Understand that updating or changing your embedding model requires reset of the vector database and re-import of all documents. You have been warned!": "Gömme modelinizi güncellemenin veya değiştirmenin, vektör veritabanının sıfırlanmasını ve tüm belgelerin yeniden içe aktarılmasını gerektirdiğini anlayın. Uyarıldın!",
 	"Unknown File Type '{{file_type}}', but accepting and treating as plain text": "Bilinmeyen Dosya Türü '{{file_type}}', ancak düz metin olarak kabul ediliyor ve işleniyor",
+	"Update": "Güncelleme",
+	"Update embedding model {{embedding_model}}": "Gömme modelini güncelle: {{embedding_model}}",
 	"Update password": "Parolayı Güncelle",
 	"Upload a GGUF model": "Bir GGUF modeli yükle",
 	"Upload files": "Dosyaları Yükle",
@@ -340,6 +349,7 @@
 	"URL Mode": "URL Modu",
 	"Use '#' in the prompt input to load and select your documents.": "Belgelerinizi yüklemek ve seçmek için promptda '#' kullanın.",
 	"Use Gravatar": "Gravatar Kullan",
+	"Use Initials": "Baş Harfleri Kullan",
 	"user": "kullanıcı",
 	"User Permissions": "Kullanıcı İzinleri",
 	"Users": "Kullanıcılar",

src/lib/i18n/locales/uk-UA/translation.json

@@ -341,7 +341,7 @@
 	"Use '#' in the prompt input to load and select your documents.": "Для введення промтів до веб-сторінок (URL) або вибору документів, будь ласка, використовуйте символ '#'.",
 	"Use Gravatar": "Змінити аватар",
 	"user": "користувач",
-	"User Permissions": "Дозволи користувача",
+	"User Permissions": "Права користувача",
 	"Users": "Користувачі",
 	"Utilize": "Використовувати",
 	"Valid time units:": "Дійсні одиниці часу:",

src/lib/i18n/locales/zh-CN/translation.json

@@ -5,20 +5,20 @@
 	"(latest)": "",
 	"{{modelName}} is thinking...": "{{modelName}} 正在思考...",
 	"{{webUIName}} Backend Required": "需要 {{webUIName}} 后端",
-	"a user": "",
+	"a user": "用户",
 	"About": "关于",
 	"Account": "账户",
 	"Action": "操作",
 	"Add a model": "添加模型",
 	"Add a model tag name": "添加模型标签名称",
-	"Add a short description about what this modelfile does": "添加关于此模型文件功能的简短描述",
-	"Add a short title for this prompt": "为这个提示添加一个简短的标题",
-	"Add a tag": "",
+	"Add a short description about what this modelfile does": "为这个模型文件添加一段简短的描述",
+	"Add a short title for this prompt": "为这个提示词添加一个简短的标题",
+	"Add a tag": "添加标签",
 	"Add Docs": "添加文档",
 	"Add Files": "添加文件",
 	"Add message": "添加消息",
 	"add tags": "添加标签",
-	"Adjusting these settings will apply changes universally to all users.": "调整这些设置将对所有用户普遍应用更改。",
+	"Adjusting these settings will apply changes universally to all users.": "调整这些设置将会对所有用户应用更改。",
 	"admin": "管理员",
 	"Admin Panel": "管理员面板",
 	"Admin Settings": "管理员设置",
@@ -26,15 +26,15 @@
 	"all": "所有",
 	"All Users": "所有用户",
 	"Allow": "允许",
-	"Allow Chat Deletion": "允许删除聊天",
+	"Allow Chat Deletion": "允许删除聊天记录",
 	"alphanumeric characters and hyphens": "字母数字字符和连字符",
 	"Already have an account?": "已经有账户了吗？",
-	"an assistant": "",
+	"an assistant": "助手",
 	"and": "和",
 	"API Base URL": "API 基础 URL",
 	"API Key": "API 密钥",
 	"API RPM": "API RPM",
-	"are allowed - Activate this command by typing": "被允许 - 通过输入激活此命令",
+	"are allowed - Activate this command by typing": "允许 - 通过输入来激活这个命令",
 	"Are you sure?": "你确定吗？",
 	"Audio": "音频",
 	"Auto-playback response": "自动播放回应",
@@ -43,21 +43,21 @@
 	"AUTOMATIC1111 Base URL is required.": "需要 AUTOMATIC1111 基础 URL。",
 	"available!": "可用！",
 	"Back": "返回",
-	"Builder Mode": "构建者模式",
+	"Builder Mode": "构建模式",
 	"Cancel": "取消",
 	"Categories": "分类",
 	"Change Password": "更改密码",
 	"Chat": "聊天",
 	"Chat History": "聊天历史",
-	"Chat History is off for this browser.": "此浏览器已关闭聊天历史。",
+	"Chat History is off for this browser.": "此浏览器已关闭聊天历史功能。",
 	"Chats": "聊天",
 	"Check Again": "再次检查",
 	"Check for updates": "检查更新",
 	"Checking for updates...": "正在检查更新...",
 	"Choose a model before saving...": "保存前选择一个模型...",
-	"Chunk Overlap": "块重叠",
-	"Chunk Params": "块参数",
-	"Chunk Size": "块大小",
+	"Chunk Overlap": "块重叠(Chunk Overlap)",
+	"Chunk Params": "块参数(Chunk Params)",
+	"Chunk Size": "块大小(Chunk Size)",
 	"Click here for help.": "点击这里获取帮助。",
 	"Click here to check other modelfiles.": "点击这里检查其他模型文件。",
 	"Click here to select": "点击这里选择",
@@ -83,7 +83,7 @@
 	"Current Model": "当前模型",
 	"Current Password": "当前密码",
 	"Custom": "自定义",
-	"Customize Ollama models for a specific purpose": "为特定目的定制Ollama模型",
+	"Customize Ollama models for a specific purpose": "定制特定用途的Ollama模型",
 	"Dark": "暗色",
 	"Database": "数据库",
 	"DD/MM/YYYY HH:mm": "DD/MM/YYYY HH:mm",
@@ -106,7 +106,7 @@
 	"Discover a prompt": "探索提示词",
 	"Discover, download, and explore custom prompts": "发现、下载并探索自定义提示词",
 	"Discover, download, and explore model presets": "发现、下载并探索模型预设",
-	"Display the username instead of You in the Chat": "在聊天中显示用户名而不是“您”",
+	"Display the username instead of You in the Chat": "在聊天中显示用户名而不是“你”",
 	"Document": "文档",
 	"Document Settings": "文档设置",
 	"Documents": "文档",
@@ -115,7 +115,7 @@
 	"Don't have an account?": "没有账户？",
 	"Download as a File": "下载为文件",
 	"Download Database": "下载数据库",
-	"Drop any files here to add to the conversation": "将任何文件拖到这里以添加到对话中",
+	"Drop any files here to add to the conversation": "拖动文件到此处以添加到对话中",
 	"e.g. '30s','10m'. Valid time units are 's', 'm', 'h'.": "例如 '30s','10m'。有效的时间单位是's', 'm', 'h'。",
 	"Edit Doc": "编辑文档",
 	"Edit User": "编辑用户",
@@ -123,21 +123,21 @@
 	"Enable Chat History": "启用聊天历史",
 	"Enable New Sign Ups": "启用新注册",
 	"Enabled": "启用",
-	"Enter {{role}} message here": "",
-	"Enter API Key": "",
-	"Enter Chunk Overlap": "",
-	"Enter Chunk Size": "",
-	"Enter Image Size (e.g. 512x512)": "",
-	"Enter LiteLLM API Base URL (litellm_params.api_base)": "",
-	"Enter LiteLLM API Key (litellm_params.api_key)": "",
-	"Enter LiteLLM API RPM (litellm_params.rpm)": "",
-	"Enter LiteLLM Model (litellm_params.model)": "",
-	"Enter Max Tokens (litellm_params.max_tokens)": "",
-	"Enter model tag (e.g. {{modelTag}})": "",
-	"Enter Number of Steps (e.g. 50)": "",
+	"Enter {{role}} message here": "在此处输入 {{role}} 信息",
+	"Enter API Key": "输入API密匙",
+	"Enter Chunk Overlap": "输入块重叠(Chunk Overlap)",
+	"Enter Chunk Size": "输入块大小(Chunk Size)",
+	"Enter Image Size (e.g. 512x512)": "输入图片大小(例如 512x512)",
+	"Enter LiteLLM API Base URL (litellm_params.api_base)": "输入 LiteLLM API 基本 URL (litellm_params.api_base)",
+	"Enter LiteLLM API Key (litellm_params.api_key)": "输入 LiteLLM API 密匙 (litellm_params.api_key)",
+	"Enter LiteLLM API RPM (litellm_params.rpm)": "输入 LiteLLM API 速率限制 (litellm_params.rpm)",
+	"Enter LiteLLM Model (litellm_params.model)": "输入 LiteLLM 模型 (litellm_params.model)",
+	"Enter Max Tokens (litellm_params.max_tokens)": "输入模型的 Max Tokens (litellm_params.max_tokens)",
+	"Enter model tag (e.g. {{modelTag}})": "输入模型标签(例如{{modelTag}})",
+	"Enter Number of Steps (e.g. 50)": "输入步数(例如50)",
 	"Enter stop sequence": "输入停止序列",
-	"Enter Top K": "",
-	"Enter URL (e.g. http://127.0.0.1:7860/)": "",
+	"Enter Top K": "输入 Top K",
+	"Enter URL (e.g. http://127.0.0.1:7860/)": "输入 URL (例如 http://127.0.0.1:7860/)",
 	"Enter Your Email": "输入您的电子邮件",
 	"Enter Your Full Name": "输入您的全名",
 	"Enter Your Password": "输入您的密码",
@@ -159,7 +159,7 @@
 	"Hello, {{name}}": "你好，{{name}}",
 	"Hide": "隐藏",
 	"Hide Additional Params": "隐藏额外参数",
-	"How can I help you today?": "今天我如何能帮到你？",
+	"How can I help you today?": "我今天能帮你做什么？",
 	"Image Generation (Experimental)": "图像生成（实验性）",
 	"Image Generation Engine": "图像生成引擎",
 	"Image Settings": "图像设置",
@@ -179,14 +179,14 @@
 	"Language": "语言",
 	"Light": "浅色",
 	"Listening...": "监听中...",
-	"LLMs can make mistakes. Verify important information.": "大型语言模型可能会犯错。验证重要信息。",
+	"LLMs can make mistakes. Verify important information.": "LLM可能会生成错误信息，请验证重要信息。",
 	"Made by OpenWebUI Community": "由OpenWebUI社区制作",
 	"Make sure to enclose them with": "确保将它们包含在内",
 	"Manage LiteLLM Models": "管理LiteLLM模型",
-	"Manage Models": "",
+	"Manage Models": "管理模型",
 	"Manage Ollama Models": "管理Ollama模型",
 	"Max Tokens": "最大令牌数",
-	"Maximum of 3 models can be downloaded simultaneously. Please try again later.": "最多可以同时下载3个模型。请稍后再试。",
+	"Maximum of 3 models can be downloaded simultaneously. Please try again later.": "最多可以同时下载3个模型，请稍后重试。",
 	"Mirostat": "Mirostat",
 	"Mirostat Eta": "Mirostat Eta",
 	"Mirostat Tau": "Mirostat Tau",
@@ -198,8 +198,8 @@
 	"Model Name": "模型名称",
 	"Model not selected": "未选择模型",
 	"Model Tag Name": "模型标签名称",
-	"Model Whitelisting": "",
-	"Model(s) Whitelisted": "",
+	"Model Whitelisting": "白名单模型",
+	"Model(s) Whitelisted": "模型已加入白名单",
 	"Modelfile": "模型文件",
 	"Modelfile Advanced Settings": "模型文件高级设置",
 	"Modelfile Content": "模型文件内容",
@@ -207,7 +207,7 @@
 	"Models": "模型",
 	"My Documents": "我的文档",
 	"My Modelfiles": "我的模型文件",
-	"My Prompts": "我的提示",
+	"My Prompts": "我的提示词",
 	"Name": "名称",
 	"Name Tag": "名称标签",
 	"Name your modelfile": "命名你的模型文件",
@@ -221,7 +221,7 @@
 	"Ollama Version": "Ollama 版本",
 	"On": "开",
 	"Only": "仅",
-	"Only alphanumeric characters and hyphens are allowed in the command string.": "命令字符串中只允许使用字母数字字符和连字符。",
+	"Only alphanumeric characters and hyphens are allowed in the command string.": "命令字符串中只允许使用英文字母，数字(0-9)以及连字符(-)。",
 	"Oops! Hold tight! Your files are still in the processing oven. We're cooking them up to perfection. Please be patient and we'll let you know once they're ready.": "哎呀！请稍等！您的文件仍在处理中。我们正在将它们做得尽善尽美，请耐心等待，一旦准备好我们会通知您。",
 	"Oops! Looks like the URL is invalid. Please double-check and try again.": "哎呀！看起来 URL 无效。请仔细检查后再试一次。",
 	"Oops! You're using an unsupported method (frontend only). Please serve the WebUI from the backend.": "哎呀！您正在使用不支持的方法（仅限前端）。请从后端提供 WebUI。",
@@ -235,10 +235,10 @@
 	"or": "或",
 	"Parameters": "参数",
 	"Password": "密码",
-	"PDF Extract Images (OCR)": "",
+	"PDF Extract Images (OCR)": "PDF图像处理(使用OCR)",
 	"pending": "待定",
 	"Permission denied when accessing microphone: {{error}}": "访问麦克风时权限被拒绝：{{error}}",
-	"Playground": "游乐场",
+	"Playground": "Playground",
 	"Profile": "个人资料",
 	"Prompt Content": "提示词内容",
 	"Prompt suggestions": "提示词建议",
@@ -255,7 +255,7 @@
 	"Repeat Penalty": "重复惩罚",
 	"Request Mode": "请求模式",
 	"Reset Vector Storage": "重置向量存储",
-	"Response AutoCopy to Clipboard": "响应自动复制到剪贴板",
+	"Response AutoCopy to Clipboard": "自动复制回答到剪贴板",
 	"Role": "角色",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Rosé Pine Dawn",
@@ -263,7 +263,7 @@
 	"Save & Create": "保存并创建",
 	"Save & Submit": "保存并提交",
 	"Save & Update": "保存并更新",
-	"Saving chat logs directly to your browser's storage is no longer supported. Please take a moment to download and delete your chat logs by clicking the button below. Don't worry, you can easily re-import your chat logs to the backend through": "直接将聊天记录保存到浏览器存储中不再受支持。请点击下面的按钮下载并删除您的聊天记录。别担心，您可以通过轻松地将聊天记录重新导入到后端",
+	"Saving chat logs directly to your browser's storage is no longer supported. Please take a moment to download and delete your chat logs by clicking the button below. Don't worry, you can easily re-import your chat logs to the backend through": "不再支持直接将聊天记录保存到浏览器存储中。请点击下面的按钮下载并删除您的聊天记录。别担心，您可以通过轻松地将聊天记录重新导入到后端",
 	"Scan": "扫描",
 	"Scan complete!": "扫描完成！",
 	"Scan for documents from {{path}}": "从 {{path}} 扫描文档",
@@ -275,10 +275,10 @@
 	"Seed": "种子",
 	"Select a mode": "选择一个模式",
 	"Select a model": "选择一个模型",
-	"Select an Ollama instance": "",
+	"Select an Ollama instance": "选择一个Ollama实例",
 	"Send a Message": "发送消息",
 	"Send message": "发送消息",
-	"Server connection verified": "服务器连接已验证",
+	"Server connection verified": "已验证服务器连接",
 	"Set as default": "设为默认",
 	"Set Default Model": "设置默认模型",
 	"Set Image Size": "设置图片大小",
@@ -286,7 +286,7 @@
 	"Set Title Auto-Generation Model": "设置标题自动生成模型",
 	"Set Voice": "设置声音",
 	"Settings": "设置",
-	"Settings saved successfully!": "",
+	"Settings saved successfully!": "设置已保存",
 	"Share to OpenWebUI Community": "分享到OpenWebUI社区",
 	"short-summary": "简短总结",
 	"Show": "显示",
@@ -316,10 +316,10 @@
 	"Theme": "主题",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "这确保了您宝贵的对话被安全保存到后端数据库中。谢谢！",
 	"This setting does not sync across browsers or devices.": "此设置不会在浏览器或设备之间同步。",
-	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "提示：在每次替换后，在聊天输入中按Tab键可以连续更新多个变量槽。",
+	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "提示：在每次替换后，在聊天输入中按Tab键可以连续更新多个变量。",
 	"Title": "标题",
 	"Title Auto-Generation": "标题自动生成",
-	"Title Generation Prompt": "标题生成提示",
+	"Title Generation Prompt": "自动生成标题的提示词",
 	"to": "到",
 	"To access the available model names for downloading,": "要访问可下载的模型名称，",
 	"To access the GGUF models available for downloading,": "要访问可下载的GGUF模型，",
@@ -331,9 +331,9 @@
 	"Trouble accessing Ollama?": "访问Ollama时遇到问题？",
 	"TTS Settings": "文本转语音设置",
 	"Type Hugging Face Resolve (Download) URL": "输入Hugging Face解析（下载）URL",
-	"Uh-oh! There was an issue connecting to {{provider}}.": "哦哦！连接到{{provider}}时出现问题。",
-	"Unknown File Type '{{file_type}}', but accepting and treating as plain text": "未知文件类型'{{file_type}}'，但接受并视为纯文本",
-	"Update password": "",
+	"Uh-oh! There was an issue connecting to {{provider}}.": "哎呀！连接到{{provider}}时出现问题。",
+	"Unknown File Type '{{file_type}}', but accepting and treating as plain text": "未知文件类型'{{file_type}}'，将视为纯文本进行处理",
+	"Update password": "更新密码",
 	"Upload a GGUF model": "上传一个GGUF模型",
 	"Upload files": "上传文件",
 	"Upload Progress": "上传进度",
@@ -347,17 +347,17 @@
 	"Valid time units:": "有效时间单位：",
 	"variable": "变量",
 	"variable to have them replaced with clipboard content.": "变量将被剪贴板内容替换。",
-	"Version": "",
+	"Version": "版本",
 	"Web": "网页",
 	"WebUI Add-ons": "WebUI 插件",
 	"WebUI Settings": "WebUI 设置",
-	"WebUI will make requests to": "",
+	"WebUI will make requests to": "WebUI将请求",
 	"What’s New in": "最新变化",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "当历史记录被关闭时，这个浏览器上的新聊天不会出现在你任何设备的历史记录中。",
-	"Whisper (Local)": "私语（本地）",
+	"Whisper (Local)": "Whisper（本地）",
 	"Write a prompt suggestion (e.g. Who are you?)": "写一个提示建议（例如：你是谁？）",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "用50个字写一个总结[主题或关键词]。",
 	"You": "你",
 	"You're a helpful assistant.": "你是一个有帮助的助手。",
-	"You're now logged in.": "你现在已经登录了。"
+	"You're now logged in.": "已登录。"
 }

src/routes/(app)/+layout.svelte

@@ -7,11 +7,11 @@
 
 	import { goto } from '$app/navigation';
 
-	import { getOllamaModels, getOllamaVersion } from '$lib/apis/ollama';
+	import { getModels as _getModels } from '$lib/utils';
+	import { getOllamaVersion } from '$lib/apis/ollama';
 	import { getModelfiles } from '$lib/apis/modelfiles';
 	import { getPrompts } from '$lib/apis/prompts';
-	import { getOpenAIModels } from '$lib/apis/openai';
-	import { getLiteLLMModels } from '$lib/apis/litellm';
+
 	import { getDocs } from '$lib/apis/documents';
 	import { getAllChatTags } from '$lib/apis/chats';
 
@@ -47,26 +47,7 @@
 	let showShortcuts = false;
 
 	const getModels = async () => {
-		let models = await Promise.all([
-			await getOllamaModels(localStorage.token).catch((error) => {
-				console.log(error);
-				return null;
-			}),
-			await getOpenAIModels(localStorage.token).catch((error) => {
-				console.log(error);
-				return null;
-			}),
-			await getLiteLLMModels(localStorage.token).catch((error) => {
-				console.log(error);
-				return null;
-			})
-		]);
-
-		models = models
-			.filter((models) => models)
-			.reduce((a, e, i, arr) => a.concat(e, ...(i < arr.length - 1 ? [{ name: 'hr' }] : [])), []);
-
-		return models;
+		return _getModels(localStorage.token);
 	};
 
 	const setOllamaVersion = async (version: string = '') => {
@@ -195,128 +176,128 @@
 	});
 </script>
 
-{#if loaded}
-	<div class=" hidden lg:flex fixed bottom-0 right-0 px-3 py-3 z-10">
-		<Tooltip content="Help" placement="left">
-			<button
-				id="show-shortcuts-button"
-				bind:this={showShortcutsButtonElement}
-				class="text-gray-600 dark:text-gray-300 bg-gray-300/20 w-6 h-6 flex items-center justify-center text-xs rounded-full"
-				on:click={() => {
-					showShortcuts = !showShortcuts;
-				}}
-			>
-				?
-			</button>
-		</Tooltip>
-	</div>
-
-	<ShortcutsModal bind:show={showShortcuts} />
-
-	<div class="app relative">
-		{#if !['user', 'admin'].includes($user.role)}
-			<div class="fixed w-full h-full flex z-50">
-				<div
-					class="absolute w-full h-full backdrop-blur-md bg-white/20 dark:bg-gray-900/50 flex justify-center"
-				>
-					<div class="m-auto pb-44 flex flex-col justify-center">
-						<div class="max-w-md">
-							<div class="text-center dark:text-white text-2xl font-medium z-50">
-								Account Activation Pending<br /> Contact Admin for WebUI Access
-							</div>
-
-							<div class=" mt-4 text-center text-sm dark:text-gray-200 w-full">
-								Your account status is currently pending activation. To access the WebUI, please
-								reach out to the administrator. Admins can manage user statuses from the Admin
-								Panel.
-							</div>
-
-							<div class=" mt-6 mx-auto relative group w-fit">
-								<button
-									class="relative z-20 flex px-5 py-2 rounded-full bg-white border border-gray-100 dark:border-none hover:bg-gray-100 transition font-medium text-sm"
-									on:click={async () => {
-										location.href = '/';
-									}}
-								>
-									{$i18n.t('Check Again')}
-								</button>
-
-								<button
-									class="text-xs text-center w-full mt-2 text-gray-400 underline"
-									on:click={async () => {
-										localStorage.removeItem('token');
-										location.href = '/auth';
-									}}>{$i18n.t('Sign Out')}</button
-								>
-							</div>
-						</div>
-					</div>
-				</div>
-			</div>
-		{:else if localDBChats.length > 0}
-			<div class="fixed w-full h-full flex z-50">
-				<div
-					class="absolute w-full h-full backdrop-blur-md bg-white/20 dark:bg-gray-900/50 flex justify-center"
-				>
-					<div class="m-auto pb-44 flex flex-col justify-center">
-						<div class="max-w-md">
-							<div class="text-center dark:text-white text-2xl font-medium z-50">
-								Important Update<br /> Action Required for Chat Log Storage
-							</div>
-
-							<div class=" mt-4 text-center text-sm dark:text-gray-200 w-full">
-								{$i18n.t(
-									"Saving chat logs directly to your browser's storage is no longer supported. Please take a moment to download and delete your chat logs by clicking the button below. Don't worry, you can easily re-import your chat logs to the backend through"
-								)}
-								<span class="font-semibold dark:text-white"
-									>{$i18n.t('Settings')} > {$i18n.t('Chats')} > {$i18n.t('Import Chats')}</span
-								>. {$i18n.t(
-									'This ensures that your valuable conversations are securely saved to your backend database. Thank you!'
-								)}
-							</div>
-
-							<div class=" mt-6 mx-auto relative group w-fit">
-								<button
-									class="relative z-20 flex px-5 py-2 rounded-full bg-white border border-gray-100 dark:border-none hover:bg-gray-100 transition font-medium text-sm"
-									on:click={async () => {
-										let blob = new Blob([JSON.stringify(localDBChats)], {
-											type: 'application/json'
-										});
-										saveAs(blob, `chat-export-${Date.now()}.json`);
-
-										const tx = DB.transaction('chats', 'readwrite');
-										await Promise.all([tx.store.clear(), tx.done]);
-										await deleteDB('Chats');
-
-										localDBChats = [];
-									}}
-								>
-									Download & Delete
-								</button>
-
-								<button
-									class="text-xs text-center w-full mt-2 text-gray-400 underline"
-									on:click={async () => {
-										localDBChats = [];
-									}}>{$i18n.t('Close')}</button
-								>
-							</div>
-						</div>
-					</div>
-				</div>
-			</div>
-		{/if}
-
-		<div
-			class=" text-gray-700 dark:text-gray-100 bg-white dark:bg-gray-900 min-h-screen overflow-auto flex flex-row"
+<div class=" hidden lg:flex fixed bottom-0 right-0 px-3 py-3 z-10">
+	<Tooltip content="Help" placement="left">
+		<button
+			id="show-shortcuts-button"
+			bind:this={showShortcutsButtonElement}
+			class="text-gray-600 dark:text-gray-300 bg-gray-300/20 w-6 h-6 flex items-center justify-center text-xs rounded-full"
+			on:click={() => {
+				showShortcuts = !showShortcuts;
+			}}
 		>
+			?
+		</button>
+	</Tooltip>
+</div>
+
+<ShortcutsModal bind:show={showShortcuts} />
+
+<div class="app relative">
+	<div
+		class=" text-gray-700 dark:text-gray-100 bg-white dark:bg-gray-900 min-h-screen overflow-auto flex flex-row"
+	>
+		{#if loaded}
+			{#if !['user', 'admin'].includes($user.role)}
+				<div class="fixed w-full h-full flex z-50">
+					<div
+						class="absolute w-full h-full backdrop-blur-md bg-white/20 dark:bg-gray-900/50 flex justify-center"
+					>
+						<div class="m-auto pb-44 flex flex-col justify-center">
+							<div class="max-w-md">
+								<div class="text-center dark:text-white text-2xl font-medium z-50">
+									Account Activation Pending<br /> Contact Admin for WebUI Access
+								</div>
+
+								<div class=" mt-4 text-center text-sm dark:text-gray-200 w-full">
+									Your account status is currently pending activation. To access the WebUI, please
+									reach out to the administrator. Admins can manage user statuses from the Admin
+									Panel.
+								</div>
+
+								<div class=" mt-6 mx-auto relative group w-fit">
+									<button
+										class="relative z-20 flex px-5 py-2 rounded-full bg-white border border-gray-100 dark:border-none hover:bg-gray-100 text-gray-700 transition font-medium text-sm"
+										on:click={async () => {
+											location.href = '/';
+										}}
+									>
+										{$i18n.t('Check Again')}
+									</button>
+
+									<button
+										class="text-xs text-center w-full mt-2 text-gray-400 underline"
+										on:click={async () => {
+											localStorage.removeItem('token');
+											location.href = '/auth';
+										}}>{$i18n.t('Sign Out')}</button
+									>
+								</div>
+							</div>
+						</div>
+					</div>
+				</div>
+			{:else if localDBChats.length > 0}
+				<div class="fixed w-full h-full flex z-50">
+					<div
+						class="absolute w-full h-full backdrop-blur-md bg-white/20 dark:bg-gray-900/50 flex justify-center"
+					>
+						<div class="m-auto pb-44 flex flex-col justify-center">
+							<div class="max-w-md">
+								<div class="text-center dark:text-white text-2xl font-medium z-50">
+									Important Update<br /> Action Required for Chat Log Storage
+								</div>
+
+								<div class=" mt-4 text-center text-sm dark:text-gray-200 w-full">
+									{$i18n.t(
+										"Saving chat logs directly to your browser's storage is no longer supported. Please take a moment to download and delete your chat logs by clicking the button below. Don't worry, you can easily re-import your chat logs to the backend through"
+									)}
+									<span class="font-semibold dark:text-white"
+										>{$i18n.t('Settings')} > {$i18n.t('Chats')} > {$i18n.t('Import Chats')}</span
+									>. {$i18n.t(
+										'This ensures that your valuable conversations are securely saved to your backend database. Thank you!'
+									)}
+								</div>
+
+								<div class=" mt-6 mx-auto relative group w-fit">
+									<button
+										class="relative z-20 flex px-5 py-2 rounded-full bg-white border border-gray-100 dark:border-none hover:bg-gray-100 transition font-medium text-sm"
+										on:click={async () => {
+											let blob = new Blob([JSON.stringify(localDBChats)], {
+												type: 'application/json'
+											});
+											saveAs(blob, `chat-export-${Date.now()}.json`);
+
+											const tx = DB.transaction('chats', 'readwrite');
+											await Promise.all([tx.store.clear(), tx.done]);
+											await deleteDB('Chats');
+
+											localDBChats = [];
+										}}
+									>
+										Download & Delete
+									</button>
+
+									<button
+										class="text-xs text-center w-full mt-2 text-gray-400 underline"
+										on:click={async () => {
+											localDBChats = [];
+										}}>{$i18n.t('Close')}</button
+									>
+								</div>
+							</div>
+						</div>
+					</div>
+				</div>
+			{/if}
+
 			<Sidebar />
 			<SettingsModal bind:show={$showSettings} />
 			<ChangelogModal bind:show={$showChangelog} />
 			<slot />
-		</div>
+		{/if}
 	</div>
-{/if}
+</div>
 
 <style>
 	.loading {

src/routes/(app)/+page.svelte

@@ -351,7 +351,13 @@
 			model: model,
 			messages: messagesBody,
 			options: {
-				...($settings.options ?? {})
+				...($settings.options ?? {}),
+				stop:
+					$settings?.options?.stop ?? undefined
+						? $settings.options.stop.map((str) =>
+								decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
+						  )
+						: undefined
 			},
 			format: $settings.requestFormat ?? undefined,
 			keep_alive: $settings.keepAlive ?? undefined,
@@ -532,7 +538,7 @@
 
 		console.log(model);
 
-		const res = await generateOpenAIChatCompletion(
+		const [res, controller] = await generateOpenAIChatCompletion(
 			localStorage.token,
 			{
 				model: model.id,
@@ -576,7 +582,12 @@
 							  })
 					})),
 				seed: $settings?.options?.seed ?? undefined,
-				stop: $settings?.options?.stop ?? undefined,
+				stop:
+					$settings?.options?.stop ?? undefined
+						? $settings?.options?.stop.map((str) =>
+								decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
+						  )
+						: undefined,
 				temperature: $settings?.options?.temperature ?? undefined,
 				top_p: $settings?.options?.top_p ?? undefined,
 				num_ctx: $settings?.options?.num_ctx ?? undefined,
@@ -608,6 +619,11 @@
 				if (done || stopResponseFlag || _chatId !== $chatId) {
 					responseMessage.done = true;
 					messages = messages;
+
+					if (stopResponseFlag) {
+						controller.abort('User: Stop Response');
+					}
+
 					break;
 				}
 

src/routes/(app)/admin/+page.svelte

@@ -5,6 +5,8 @@
 	import { onMount, getContext } from 'svelte';
 
 	import dayjs from 'dayjs';
+	import relativeTime from 'dayjs/plugin/relativeTime';
+	dayjs.extend(relativeTime);
 
 	import { toast } from 'svelte-sonner';
 
@@ -13,6 +15,9 @@
 	import EditUserModal from '$lib/components/admin/EditUserModal.svelte';
 	import SettingsModal from '$lib/components/admin/SettingsModal.svelte';
 	import Pagination from '$lib/components/common/Pagination.svelte';
+	import ChatBubbles from '$lib/components/icons/ChatBubbles.svelte';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import UserChatsModal from '$lib/components/admin/UserChatsModal.svelte';
 
 	const i18n = getContext('i18n');
 
@@ -25,6 +30,8 @@
 	let page = 1;
 
 	let showSettingsModal = false;
+
+	let showUserChatsModal = false;
 	let showEditUserModal = false;
 
 	const updateRoleHandler = async (id, role) => {
@@ -84,6 +91,7 @@
 	/>
 {/key}
 
+<UserChatsModal bind:show={showUserChatsModal} user={selectedUser} />
 <SettingsModal bind:show={showSettingsModal} />
 
 <div class="min-h-screen max-h-[100dvh] w-full flex justify-center dark:text-white">
@@ -157,7 +165,10 @@
 											<th scope="col" class="px-3 py-2"> {$i18n.t('Role')} </th>
 											<th scope="col" class="px-3 py-2"> {$i18n.t('Name')} </th>
 											<th scope="col" class="px-3 py-2"> {$i18n.t('Email')} </th>
+											<th scope="col" class="px-3 py-2"> {$i18n.t('Last Active')} </th>
+
 											<th scope="col" class="px-3 py-2"> {$i18n.t('Created at')} </th>
+
 											<th scope="col" class="px-3 py-2 text-right" />
 										</tr>
 									</thead>
@@ -215,55 +226,75 @@
 												<td class=" px-3 py-2"> {user.email} </td>
 
 												<td class=" px-3 py-2">
-													{dayjs(user.timestamp * 1000).format($i18n.t('MMMM DD, YYYY'))}
+													{dayjs(user.last_active_at * 1000).fromNow()}
+												</td>
+
+												<td class=" px-3 py-2">
+													{dayjs(user.created_at * 1000).format($i18n.t('MMMM DD, YYYY'))}
 												</td>
 
 												<td class="px-3 py-2 text-right">
 													<div class="flex justify-end w-full">
-														<button
-															class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
-															on:click={async () => {
-																showEditUserModal = !showEditUserModal;
-																selectedUser = user;
-															}}
-														>
-															<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"
+														<Tooltip content="Chats">
+															<button
+																class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
+																on:click={async () => {
+																	showUserChatsModal = !showUserChatsModal;
+																	selectedUser = user;
+																}}
 															>
-																<path
-																	stroke-linecap="round"
-																	stroke-linejoin="round"
-																	d="m16.862 4.487 1.687-1.688a1.875 1.875 0 1 1 2.652 2.652L6.832 19.82a4.5 4.5 0 0 1-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 0 1 1.13-1.897L16.863 4.487Zm0 0L19.5 7.125"
-																/>
-															</svg>
-														</button>
+																<ChatBubbles />
+															</button>
+														</Tooltip>
 
-														<button
-															class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
-															on:click={async () => {
-																deleteUserHandler(user.id);
-															}}
-														>
-															<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"
+														<Tooltip content="Edit User">
+															<button
+																class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
+																on:click={async () => {
+																	showEditUserModal = !showEditUserModal;
+																	selectedUser = user;
+																}}
 															>
-																<path
-																	stroke-linecap="round"
-																	stroke-linejoin="round"
-																	d="m14.74 9-.346 9m-4.788 0L9.26 9m9.968-3.21c.342.052.682.107 1.022.166m-1.022-.165L18.16 19.673a2.25 2.25 0 0 1-2.244 2.077H8.084a2.25 2.25 0 0 1-2.244-2.077L4.772 5.79m14.456 0a48.108 48.108 0 0 0-3.478-.397m-12 .562c.34-.059.68-.114 1.022-.165m0 0a48.11 48.11 0 0 1 3.478-.397m7.5 0v-.916c0-1.18-.91-2.164-2.09-2.201a51.964 51.964 0 0 0-3.32 0c-1.18.037-2.09 1.022-2.09 2.201v.916m7.5 0a48.667 48.667 0 0 0-7.5 0"
-																/>
-															</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="m16.862 4.487 1.687-1.688a1.875 1.875 0 1 1 2.652 2.652L6.832 19.82a4.5 4.5 0 0 1-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 0 1 1.13-1.897L16.863 4.487Zm0 0L19.5 7.125"
+																	/>
+																</svg>
+															</button>
+														</Tooltip>
+
+														<Tooltip content="Delete User">
+															<button
+																class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
+																on:click={async () => {
+																	deleteUserHandler(user.id);
+																}}
+															>
+																<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="m14.74 9-.346 9m-4.788 0L9.26 9m9.968-3.21c.342.052.682.107 1.022.166m-1.022-.165L18.16 19.673a2.25 2.25 0 0 1-2.244 2.077H8.084a2.25 2.25 0 0 1-2.244-2.077L4.772 5.79m14.456 0a48.108 48.108 0 0 0-3.478-.397m-12 .562c.34-.059.68-.114 1.022-.165m0 0a48.11 48.11 0 0 1 3.478-.397m7.5 0v-.916c0-1.18-.91-2.164-2.09-2.201a51.964 51.964 0 0 0-3.32 0c-1.18.037-2.09 1.022-2.09 2.201v.916m7.5 0a48.667 48.667 0 0 0-7.5 0"
+																	/>
+																</svg>
+															</button>
+														</Tooltip>
 													</div>
 												</td>
 											</tr>

src/routes/(app)/c/[id]/+page.svelte

@@ -365,7 +365,13 @@
 			model: model,
 			messages: messagesBody,
 			options: {
-				...($settings.options ?? {})
+				...($settings.options ?? {}),
+				stop:
+					$settings?.options?.stop ?? undefined
+						? $settings.options.stop.map((str) =>
+								decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
+						  )
+						: undefined
 			},
 			format: $settings.requestFormat ?? undefined,
 			keep_alive: $settings.keepAlive ?? undefined,
@@ -544,7 +550,7 @@
 
 		console.log(docs);
 
-		const res = await generateOpenAIChatCompletion(
+		const [res, controller] = await generateOpenAIChatCompletion(
 			localStorage.token,
 			{
 				model: model.id,
@@ -588,7 +594,12 @@
 							  })
 					})),
 				seed: $settings?.options?.seed ?? undefined,
-				stop: $settings?.options?.stop ?? undefined,
+				stop:
+					$settings?.options?.stop ?? undefined
+						? $settings.options.stop.map((str) =>
+								decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
+						  )
+						: undefined,
 				temperature: $settings?.options?.temperature ?? undefined,
 				top_p: $settings?.options?.top_p ?? undefined,
 				num_ctx: $settings?.options?.num_ctx ?? undefined,
@@ -620,6 +631,11 @@
 				if (done || stopResponseFlag || _chatId !== $chatId) {
 					responseMessage.done = true;
 					messages = messages;
+
+					if (stopResponseFlag) {
+						controller.abort('User: Stop Response');
+					}
+
 					break;
 				}
 

src/routes/(app)/modelfiles/+page.svelte

@@ -28,7 +28,7 @@
 		});
 
 		if (success) {
-			toast.success($i18n.t(`Deleted {tagName}`, { tagName }));
+			toast.success($i18n.t(`Deleted {{tagName}}`, { tagName }));
 		}
 
 		return success;

src/routes/(app)/playground/+page.svelte

@@ -67,7 +67,7 @@
 	const textCompletionHandler = async () => {
 		const model = $models.find((model) => model.id === selectedModelId);
 
-		const res = await generateOpenAIChatCompletion(
+		const [res, controller] = await generateOpenAIChatCompletion(
 			localStorage.token,
 			{
 				model: model.id,
@@ -96,7 +96,7 @@
 				const { value, done } = await reader.read();
 				if (done || stopResponseFlag) {
 					if (stopResponseFlag) {
-						await cancelOllamaRequest(localStorage.token, currentRequestId);
+						controller.abort('User: Stop Response');
 					}
 
 					currentRequestId = null;
@@ -135,7 +135,7 @@
 	const chatCompletionHandler = async () => {
 		const model = $models.find((model) => model.id === selectedModelId);
 
-		const res = await generateOpenAIChatCompletion(
+		const [res, controller] = await generateOpenAIChatCompletion(
 			localStorage.token,
 			{
 				model: model.id,
@@ -182,7 +182,7 @@
 				const { value, done } = await reader.read();
 				if (done || stopResponseFlag) {
 					if (stopResponseFlag) {
-						await cancelOllamaRequest(localStorage.token, currentRequestId);
+						controller.abort('User: Stop Response');
 					}
 
 					currentRequestId = null;

src/routes/+layout.svelte

@@ -7,9 +7,11 @@
 	import { getBackendConfig } from '$lib/apis';
 	import { getSessionUser } from '$lib/apis/auths';
 
-	import '../app.css';
 	import '../tailwind.css';
+	import '../app.css';
+
 	import 'tippy.js/dist/tippy.css';
+
 	import { WEBUI_BASE_URL } from '$lib/constants';
 	import i18n, { initI18n } from '$lib/i18n';
 
@@ -60,6 +62,8 @@
 		}
 
 		await tick();
+
+		document.getElementById('splash-screen')?.remove();
 		loaded = true;
 	});
 </script>
@@ -68,8 +72,10 @@
 	<title>{$WEBUI_NAME}</title>
 	<link rel="icon" href="{WEBUI_BASE_URL}/static/favicon.png" />
 
-	<link rel="stylesheet" type="text/css" href="/themes/rosepine.css" />
-	<link rel="stylesheet" type="text/css" href="/themes/rosepine-dawn.css" />
+	<!-- rosepine themes have been disabled as it's not up to date with our latest version. -->
+	<!-- feel free to make a PR to fix if anyone wants to see it return -->
+	<!-- <link rel="stylesheet" type="text/css" href="/themes/rosepine.css" />
+	<link rel="stylesheet" type="text/css" href="/themes/rosepine-dawn.css" /> -->
 </svelte:head>
 
 {#if loaded}

src/routes/auth/+page.svelte

@@ -215,6 +215,8 @@
 
 <style>
 	.font-mona {
-		font-family: 'Mona Sans';
+		font-family: 'Mona Sans', -apple-system, 'Arimo', ui-sans-serif, system-ui, 'Segoe UI', Roboto,
+			Ubuntu, Cantarell, 'Noto Sans', sans-serif, 'Helvetica Neue', Arial, 'Apple Color Emoji',
+			'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
 	}
 </style>