Merge pull request #13887 from open-webui/dev

0.6.10

CHANGELOG.md

@@ -5,6 +5,49 @@ 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).
 
+## [0.6.10] - 2025-05-19
+
+### Added
+
+- 🧩 **Experimental Azure OpenAI Support**: Instantly connect to Azure OpenAI endpoints by simply pasting your Azure OpenAI URL into the model connections—bringing flexible, enterprise-grade AI integration directly to your workflow.
+- 💧 **Watermark AI Responses**: Easily add a visible watermark to AI-generated responses for clear content provenance and compliance with EU AI regulations—perfect for regulated environments and transparent communication.
+- 🔍 **Enhanced Search Experience with Dedicated Modal**: Enjoy a modern, powerful search UI in a dedicated modal (open with Ctrl/Cmd + K) accessible from anywhere—quickly find chats, models, or content and boost your productivity.
+- 🔲 **"Toggle" Filter Type for Chat Input**: Add interactive toggle filters (e.g. Web Search, Image, Code Interpreter) right into the chat input—giving you one-click control to activate features and simplifying the chat configuration process.
+- 🧰 **Granular Model Capabilities Editor**: Define detailed capabilities and feature access for each AI model directly from the model editor—enabling tailored behavior, modular control, and a more customized AI environment for every team or use case.
+- 🌐 **Flexible Local and External Connection Support**: Now you can designate any AI connection—whether OpenAI, Ollama, or others—as local or external, enabling seamless setup for on-premise, self-hosted, or cloud configurations and giving you maximum control and flexibility.
+- 🗂️ **Allowed File Extensions for RAG**: Gain full control over your Retrieval-Augmented Generation (RAG) workflows by specifying exactly which file extensions are permitted for upload, improving security and relevance of indexed documents.
+- 🔊 **Enhanced Audio Transcription Logic**: Experience smoother, more reliable audio transcription—very long audio files are now automatically split and processed in segments, preventing errors and ensuring even challenging files are transcribed seamlessly, all part of a broader stability upgrade for robust media workflows.
+- 🦾 **External Document Loader Support**: Enhance knowledge base building by integrating documents using external loaders from a wide range of data sources, expanding what your AI can read and process.
+- 📝 **Preview Button for Code Artifacts**: Instantly jump from an HTML code block to its associated artifacts page with the click of a new preview button—speeding up review and streamlining analysis.
+- 🦻 **Screen Reader Support for Response Messages**: All chat responses are now fully compatible with screen readers, making the platform more inclusive and accessible for everyone.
+- 🧑‍💼 **Customizable Pending User Overlay**: You can now tailor the overlay title and content shown to pending users, ensuring onboarding messaging is perfectly aligned with your organization’s tone and requirements.
+- 🔐 **Option to Disable LDAP Certificate Validation**: You can now disable LDAP certificate validation for maximum flexibility in diverse IT environments—making integrations and troubleshooting much easier.
+- 🎯 **Workspace Search by Username or Email**: Easily search across workspace pages using any username or email address, streamlining user and resource management.
+- 🎨 **High Contrast & Dark Mode Enhancements**: Further improved placeholder, input, suggestion, toast, and model selector contrasts—including a dedicated placeholder dark mode—for more comfortable viewing in all lighting conditions.
+- 🛡️ **Refined Security for Pipelines & Model Uploads**: Strengthened safeguards against path traversal vulnerabilities during uploads—ensuring your platform’s document and model management remains secure.
+- 🌏 **Major Localization Upgrades**: Comprehensive translation updates and improvements across Korean, Bulgarian, Catalan, Japanese, Italian, Traditional Chinese, and Spanish—including more accurate AI terminology for clarity; your experience is now more natural, inclusive, and professional everywhere.
+- 🦾 **General Backend Stability & Security**: Multiple backend improvements (including file upload, command navigation, and logging refactorings) deliver increased resilience, better error handling, and a more robust platform for all users.
+
+### Fixed
+
+- ✅ **Evaluation Feedback Endpoint Reliability**: Addressed issues with feedback submission endpoints to ensure seamless user feedback collection on model responses.
+- 🫰 **Model List State Fixes**: Resolved issues where model status toggles in the workspace page might inadvertently switch or confuse state, making the management of active/inactive models more dependable.
+- ✍️ **Admin Signup Logic**: Admin self-signup experience and validation flow is smoother and more robust.
+- 🔁 **Signout Redirect Flow Improved**: Logging out now redirects more reliably, reducing confusion and making session management seamless.
+
+## [0.6.9] - 2025-05-10
+
+### Added
+
+- 📝 **Edit Attached Images/Files in Messages**: You can now easily edit your sent messages by removing attached files—streamlining document management, correcting mistakes on the fly, and keeping your chats clutter-free.
+- 🚨 **Clear Alerts for Private Task Models**: When interacting with private task models, the UI now clearly alerts you—making it easier to understand resource availability and access, reducing confusion during workflow setup.
+
+### Fixed
+
+- 🛡️ **Confirm Dialog Focus Trap Reliability**: The focus now stays correctly within confirmation dialogs, ensuring keyboard navigation and accessibility is seamless and preventing accidental operations—especially helpful during critical or rapid workflows.
+- 💬 **Temporary Chat Admin Controls & Session Cleanliness**: Admins are now able to properly enable temporary chat mode without errors, and previous session prompts or tool selections no longer carry over—delivering a fresh, predictable, and consistent temporary chat experience every time.
+- 🤖 **External Reranker Integration Functionality Restored**: External reranker integrations now work correctly, allowing you to fully leverage advanced ranking services for sharper, more relevant search results in your RAG and knowledge base workflows.
+
 ## [0.6.8] - 2025-05-10
 
 ### Added

Dockerfile

@@ -26,6 +26,9 @@ ARG BUILD_HASH
 
 WORKDIR /app
 
+# to store git revision in build
+RUN apk add --no-cache git
+
 COPY package.json package-lock.json ./
 RUN npm ci
 

backend/open_webui/config.py

@@ -989,6 +989,26 @@ DEFAULT_USER_ROLE = PersistentConfig(
     os.getenv("DEFAULT_USER_ROLE", "pending"),
 )
 
+PENDING_USER_OVERLAY_TITLE = PersistentConfig(
+    "PENDING_USER_OVERLAY_TITLE",
+    "ui.pending_user_overlay_title",
+    os.environ.get("PENDING_USER_OVERLAY_TITLE", ""),
+)
+
+PENDING_USER_OVERLAY_CONTENT = PersistentConfig(
+    "PENDING_USER_OVERLAY_CONTENT",
+    "ui.pending_user_overlay_content",
+    os.environ.get("PENDING_USER_OVERLAY_CONTENT", ""),
+)
+
+
+RESPONSE_WATERMARK = PersistentConfig(
+    "RESPONSE_WATERMARK",
+    "ui.watermark",
+    os.environ.get("RESPONSE_WATERMARK", ""),
+)
+
+
 USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS = (
     os.environ.get("USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS", "False").lower()
     == "true"
@@ -1731,6 +1751,9 @@ QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY", None)
 QDRANT_ON_DISK = os.environ.get("QDRANT_ON_DISK", "false").lower() == "true"
 QDRANT_PREFER_GRPC = os.environ.get("QDRANT_PREFER_GRPC", "False").lower() == "true"
 QDRANT_GRPC_PORT = int(os.environ.get("QDRANT_GRPC_PORT", "6334"))
+ENABLE_QDRANT_MULTITENANCY_MODE = (
+    os.environ.get("ENABLE_QDRANT_MULTITENANCY_MODE", "false").lower() == "true"
+)
 
 # OpenSearch
 OPENSEARCH_URI = os.environ.get("OPENSEARCH_URI", "https://localhost:9200")
@@ -1825,6 +1848,18 @@ CONTENT_EXTRACTION_ENGINE = PersistentConfig(
     os.environ.get("CONTENT_EXTRACTION_ENGINE", "").lower(),
 )
 
+EXTERNAL_DOCUMENT_LOADER_URL = PersistentConfig(
+    "EXTERNAL_DOCUMENT_LOADER_URL",
+    "rag.external_document_loader_url",
+    os.environ.get("EXTERNAL_DOCUMENT_LOADER_URL", ""),
+)
+
+EXTERNAL_DOCUMENT_LOADER_API_KEY = PersistentConfig(
+    "EXTERNAL_DOCUMENT_LOADER_API_KEY",
+    "rag.external_document_loader_api_key",
+    os.environ.get("EXTERNAL_DOCUMENT_LOADER_API_KEY", ""),
+)
+
 TIKA_SERVER_URL = PersistentConfig(
     "TIKA_SERVER_URL",
     "rag.tika_server_url",
@@ -1849,6 +1884,12 @@ DOCLING_OCR_LANG = PersistentConfig(
     os.getenv("DOCLING_OCR_LANG", "eng,fra,deu,spa"),
 )
 
+DOCLING_DO_PICTURE_DESCRIPTION = PersistentConfig(
+    "DOCLING_DO_PICTURE_DESCRIPTION",
+    "rag.docling_do_picture_description",
+    os.getenv("DOCLING_DO_PICTURE_DESCRIPTION", "False").lower() == "true",
+)
+
 DOCUMENT_INTELLIGENCE_ENDPOINT = PersistentConfig(
     "DOCUMENT_INTELLIGENCE_ENDPOINT",
     "rag.document_intelligence_endpoint",
@@ -1920,6 +1961,16 @@ RAG_FILE_MAX_SIZE = PersistentConfig(
     ),
 )
 
+RAG_ALLOWED_FILE_EXTENSIONS = PersistentConfig(
+    "RAG_ALLOWED_FILE_EXTENSIONS",
+    "rag.file.allowed_extensions",
+    [
+        ext.strip()
+        for ext in os.environ.get("RAG_ALLOWED_FILE_EXTENSIONS", "").split(",")
+        if ext.strip()
+    ],
+)
+
 RAG_EMBEDDING_ENGINE = PersistentConfig(
     "RAG_EMBEDDING_ENGINE",
     "rag.embedding_engine",
@@ -2839,6 +2890,12 @@ LDAP_CA_CERT_FILE = PersistentConfig(
     os.environ.get("LDAP_CA_CERT_FILE", ""),
 )
 
+LDAP_VALIDATE_CERT = PersistentConfig(
+    "LDAP_VALIDATE_CERT",
+    "ldap.server.validate_cert",
+    os.environ.get("LDAP_VALIDATE_CERT", "True").lower() == "true",
+)
+
 LDAP_CIPHERS = PersistentConfig(
     "LDAP_CIPHERS", "ldap.server.ciphers", os.environ.get("LDAP_CIPHERS", "ALL")
 )

backend/open_webui/main.py

@@ -197,6 +197,7 @@ from open_webui.config import (
     RAG_EMBEDDING_ENGINE,
     RAG_EMBEDDING_BATCH_SIZE,
     RAG_RELEVANCE_THRESHOLD,
+    RAG_ALLOWED_FILE_EXTENSIONS,
     RAG_FILE_MAX_COUNT,
     RAG_FILE_MAX_SIZE,
     RAG_OPENAI_API_BASE_URL,
@@ -206,10 +207,13 @@ from open_webui.config import (
     CHUNK_OVERLAP,
     CHUNK_SIZE,
     CONTENT_EXTRACTION_ENGINE,
+    EXTERNAL_DOCUMENT_LOADER_URL,
+    EXTERNAL_DOCUMENT_LOADER_API_KEY,
     TIKA_SERVER_URL,
     DOCLING_SERVER_URL,
     DOCLING_OCR_ENGINE,
     DOCLING_OCR_LANG,
+    DOCLING_DO_PICTURE_DESCRIPTION,
     DOCUMENT_INTELLIGENCE_ENDPOINT,
     DOCUMENT_INTELLIGENCE_KEY,
     MISTRAL_OCR_API_KEY,
@@ -291,6 +295,8 @@ from open_webui.config import (
     ENABLE_EVALUATION_ARENA_MODELS,
     USER_PERMISSIONS,
     DEFAULT_USER_ROLE,
+    PENDING_USER_OVERLAY_CONTENT,
+    PENDING_USER_OVERLAY_TITLE,
     DEFAULT_PROMPT_SUGGESTIONS,
     DEFAULT_MODELS,
     DEFAULT_ARENA_MODEL,
@@ -317,6 +323,7 @@ from open_webui.config import (
     LDAP_APP_PASSWORD,
     LDAP_USE_TLS,
     LDAP_CA_CERT_FILE,
+    LDAP_VALIDATE_CERT,
     LDAP_CIPHERS,
     # Misc
     ENV,
@@ -327,6 +334,7 @@ from open_webui.config import (
     DEFAULT_LOCALE,
     OAUTH_PROVIDERS,
     WEBUI_URL,
+    RESPONSE_WATERMARK,
     # Admin
     ENABLE_ADMIN_CHAT_ACCESS,
     ENABLE_ADMIN_EXPORT,
@@ -373,6 +381,7 @@ from open_webui.env import (
     OFFLINE_MODE,
     ENABLE_OTEL,
     EXTERNAL_PWA_MANIFEST_URL,
+    AIOHTTP_CLIENT_SESSION_SSL,
 )
 
 
@@ -573,6 +582,11 @@ app.state.config.DEFAULT_MODELS = DEFAULT_MODELS
 app.state.config.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
 app.state.config.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
 
+app.state.config.PENDING_USER_OVERLAY_CONTENT = PENDING_USER_OVERLAY_CONTENT
+app.state.config.PENDING_USER_OVERLAY_TITLE = PENDING_USER_OVERLAY_TITLE
+
+app.state.config.RESPONSE_WATERMARK = RESPONSE_WATERMARK
+
 app.state.config.USER_PERMISSIONS = USER_PERMISSIONS
 app.state.config.WEBHOOK_URL = WEBHOOK_URL
 app.state.config.BANNERS = WEBUI_BANNERS
@@ -609,6 +623,7 @@ app.state.config.LDAP_SEARCH_BASE = LDAP_SEARCH_BASE
 app.state.config.LDAP_SEARCH_FILTERS = LDAP_SEARCH_FILTERS
 app.state.config.LDAP_USE_TLS = LDAP_USE_TLS
 app.state.config.LDAP_CA_CERT_FILE = LDAP_CA_CERT_FILE
+app.state.config.LDAP_VALIDATE_CERT = LDAP_VALIDATE_CERT
 app.state.config.LDAP_CIPHERS = LDAP_CIPHERS
 
 
@@ -631,6 +646,7 @@ app.state.FUNCTIONS = {}
 app.state.config.TOP_K = RAG_TOP_K
 app.state.config.TOP_K_RERANKER = RAG_TOP_K_RERANKER
 app.state.config.RELEVANCE_THRESHOLD = RAG_RELEVANCE_THRESHOLD
+app.state.config.ALLOWED_FILE_EXTENSIONS = RAG_ALLOWED_FILE_EXTENSIONS
 app.state.config.FILE_MAX_SIZE = RAG_FILE_MAX_SIZE
 app.state.config.FILE_MAX_COUNT = RAG_FILE_MAX_COUNT
 
@@ -641,10 +657,13 @@ app.state.config.ENABLE_RAG_HYBRID_SEARCH = ENABLE_RAG_HYBRID_SEARCH
 app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION = ENABLE_WEB_LOADER_SSL_VERIFICATION
 
 app.state.config.CONTENT_EXTRACTION_ENGINE = CONTENT_EXTRACTION_ENGINE
+app.state.config.EXTERNAL_DOCUMENT_LOADER_URL = EXTERNAL_DOCUMENT_LOADER_URL
+app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY = EXTERNAL_DOCUMENT_LOADER_API_KEY
 app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
 app.state.config.DOCLING_SERVER_URL = DOCLING_SERVER_URL
 app.state.config.DOCLING_OCR_ENGINE = DOCLING_OCR_ENGINE
 app.state.config.DOCLING_OCR_LANG = DOCLING_OCR_LANG
+app.state.config.DOCLING_DO_PICTURE_DESCRIPTION = DOCLING_DO_PICTURE_DESCRIPTION
 app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = DOCUMENT_INTELLIGENCE_ENDPOINT
 app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY
 app.state.config.MISTRAL_OCR_API_KEY = MISTRAL_OCR_API_KEY
@@ -1167,11 +1186,12 @@ async def chat_completion(
             "chat_id": form_data.pop("chat_id", None),
             "message_id": form_data.pop("id", None),
             "session_id": form_data.pop("session_id", None),
+            "filter_ids": form_data.pop("filter_ids", []),
             "tool_ids": form_data.get("tool_ids", None),
             "tool_servers": form_data.pop("tool_servers", None),
             "files": form_data.get("files", None),
-            "features": form_data.get("features", None),
+            "features": form_data.get("features", {}),
-            "variables": form_data.get("variables", None),
+            "variables": form_data.get("variables", {}),
             "model": model,
             "direct": model_item.get("direct", False),
             **(
@@ -1395,6 +1415,11 @@ async def get_app_config(request: Request):
                     "sharepoint_url": ONEDRIVE_SHAREPOINT_URL.value,
                     "sharepoint_tenant_id": ONEDRIVE_SHAREPOINT_TENANT_ID.value,
                 },
+                "ui": {
+                    "pending_user_overlay_title": app.state.config.PENDING_USER_OVERLAY_TITLE,
+                    "pending_user_overlay_content": app.state.config.PENDING_USER_OVERLAY_CONTENT,
+                    "response_watermark": app.state.config.RESPONSE_WATERMARK,
+                },
                 "license_metadata": app.state.LICENSE_METADATA,
                 **(
                     {
@@ -1446,7 +1471,8 @@ async def get_app_latest_release_version(user=Depends(get_verified_user)):
         timeout = aiohttp.ClientTimeout(total=1)
         async with aiohttp.ClientSession(timeout=timeout, trust_env=True) as session:
             async with session.get(
-                "https://api.github.com/repos/open-webui/open-webui/releases/latest"
+                "https://api.github.com/repos/open-webui/open-webui/releases/latest",
+                ssl=AIOHTTP_CLIENT_SESSION_SSL,
             ) as response:
                 response.raise_for_status()
                 data = await response.json()

backend/open_webui/retrieval/loaders/external_document.py

@@ -0,0 +1,58 @@
+import requests
+import logging
+from typing import Iterator, List, Union
+
+from langchain_core.document_loaders import BaseLoader
+from langchain_core.documents import Document
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+class ExternalDocumentLoader(BaseLoader):
+    def __init__(
+        self,
+        file_path,
+        url: str,
+        api_key: str,
+        mime_type=None,
+        **kwargs,
+    ) -> None:
+        self.url = url
+        self.api_key = api_key
+
+        self.file_path = file_path
+        self.mime_type = mime_type
+
+    def load(self) -> list[Document]:
+        with open(self.file_path, "rb") as f:
+            data = f.read()
+
+        headers = {}
+        if self.mime_type is not None:
+            headers["Content-Type"] = self.mime_type
+
+        if self.api_key is not None:
+            headers["Authorization"] = f"Bearer {self.api_key}"
+
+        url = self.url
+        if url.endswith("/"):
+            url = url[:-1]
+
+        r = requests.put(f"{url}/process", data=data, headers=headers)
+
+        if r.ok:
+            res = r.json()
+
+            if res:
+                return [
+                    Document(
+                        page_content=res.get("page_content"),
+                        metadata=res.get("metadata"),
+                    )
+                ]
+            else:
+                raise Exception("Error loading document: No content returned")
+        else:
+            raise Exception(f"Error loading document: {r.status_code} {r.text}")

backend/open_webui/retrieval/loaders/external_web.py

@@ -10,7 +10,7 @@ log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
-class ExternalLoader(BaseLoader):
+class ExternalWebLoader(BaseLoader):
     def __init__(
         self,
         web_paths: Union[str, List[str]],
@@ -32,7 +32,7 @@ class ExternalLoader(BaseLoader):
                 response = requests.post(
                     self.external_url,
                     headers={
-                        "User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) RAG Bot",
+                        "User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) External Web Loader",
                         "Authorization": f"Bearer {self.external_api_key}",
                     },
                     json={

backend/open_webui/retrieval/loaders/main.py

@@ -21,6 +21,8 @@ from langchain_community.document_loaders import (
 )
 from langchain_core.documents import Document
 
+
+from open_webui.retrieval.loaders.external_document import ExternalDocumentLoader
 from open_webui.retrieval.loaders.mistral import MistralLoader
 
 from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
@@ -126,14 +128,12 @@ class TikaLoader:
 
 
 class DoclingLoader:
-    def __init__(
+    def __init__(self, url, file_path=None, mime_type=None, params=None):
-        self, url, file_path=None, mime_type=None, ocr_engine=None, ocr_lang=None
-    ):
         self.url = url.rstrip("/")
         self.file_path = file_path
         self.mime_type = mime_type
-        self.ocr_engine = ocr_engine
+
-        self.ocr_lang = ocr_lang
+        self.params = params or {}
 
     def load(self) -> list[Document]:
         with open(self.file_path, "rb") as f:
@@ -150,11 +150,19 @@ class DoclingLoader:
                 "table_mode": "accurate",
             }
 
-            if self.ocr_engine and self.ocr_lang:
+            if self.params:
-                params["ocr_engine"] = self.ocr_engine
+                if self.params.get("do_picture_classification"):
-                params["ocr_lang"] = [
+                    params["do_picture_classification"] = self.params.get(
-                    lang.strip() for lang in self.ocr_lang.split(",") if lang.strip()
+                        "do_picture_classification"
-                ]
+                    )
+
+                if self.params.get("ocr_engine") and self.params.get("ocr_lang"):
+                    params["ocr_engine"] = self.params.get("ocr_engine")
+                    params["ocr_lang"] = [
+                        lang.strip()
+                        for lang in self.params.get("ocr_lang").split(",")
+                        if lang.strip()
+                    ]
 
             endpoint = f"{self.url}/v1alpha/convert/file"
             r = requests.post(endpoint, files=files, data=params)
@@ -207,6 +215,17 @@ class Loader:
     def _get_loader(self, filename: str, file_content_type: str, file_path: str):
         file_ext = filename.split(".")[-1].lower()
 
+        if (
+            self.engine == "external"
+            and self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_URL")
+            and self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_API_KEY")
+        ):
+            loader = ExternalDocumentLoader(
+                file_path=file_path,
+                url=self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_URL"),
+                api_key=self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_API_KEY"),
+                mime_type=file_content_type,
+            )
         if self.engine == "tika" and self.kwargs.get("TIKA_SERVER_URL"):
             if self._is_text_file(file_ext, file_content_type):
                 loader = TextLoader(file_path, autodetect_encoding=True)
@@ -225,8 +244,13 @@ class Loader:
                     url=self.kwargs.get("DOCLING_SERVER_URL"),
                     file_path=file_path,
                     mime_type=file_content_type,
-                    ocr_engine=self.kwargs.get("DOCLING_OCR_ENGINE"),
+                    params={
-                    ocr_lang=self.kwargs.get("DOCLING_OCR_LANG"),
+                        "ocr_engine": self.kwargs.get("DOCLING_OCR_ENGINE"),
+                        "ocr_lang": self.kwargs.get("DOCLING_OCR_LANG"),
+                        "do_picture_classification": self.kwargs.get(
+                            "DOCLING_DO_PICTURE_DESCRIPTION"
+                        ),
+                    },
                 )
         elif (
             self.engine == "document_intelligence"
@@ -258,6 +282,15 @@ class Loader:
             loader = MistralLoader(
                 api_key=self.kwargs.get("MISTRAL_OCR_API_KEY"), file_path=file_path
             )
+        elif (
+            self.engine == "external"
+            and self.kwargs.get("MISTRAL_OCR_API_KEY") != ""
+            and file_ext
+            in ["pdf"]  # Mistral OCR currently only supports PDF and images
+        ):
+            loader = MistralLoader(
+                api_key=self.kwargs.get("MISTRAL_OCR_API_KEY"), file_path=file_path
+            )
         else:
             if file_ext == "pdf":
                 loader = PyPDFLoader(

backend/open_webui/retrieval/utils.py

@@ -12,7 +12,7 @@ from langchain_community.retrievers import BM25Retriever
 from langchain_core.documents import Document
 
 from open_webui.config import VECTOR_DB
-from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
+from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
 
 from open_webui.models.users import UserModel
 from open_webui.models.files import Files
@@ -818,7 +818,9 @@ class RerankCompressor(BaseDocumentCompressor):
             )
             scores = util.cos_sim(query_embedding, document_embedding)[0]
 
-        docs_with_scores = list(zip(documents, scores.tolist()))
+        docs_with_scores = list(
+            zip(documents, scores.tolist() if not isinstance(scores, list) else scores)
+        )
         if self.r_score:
             docs_with_scores = [
                 (d, s) for d, s in docs_with_scores if s >= self.r_score

backend/open_webui/retrieval/vector/connector.py

@@ -1,30 +0,0 @@
-from open_webui.config import VECTOR_DB
-
-if VECTOR_DB == "milvus":
-    from open_webui.retrieval.vector.dbs.milvus import MilvusClient
-
-    VECTOR_DB_CLIENT = MilvusClient()
-elif VECTOR_DB == "qdrant":
-    from open_webui.retrieval.vector.dbs.qdrant import QdrantClient
-
-    VECTOR_DB_CLIENT = QdrantClient()
-elif VECTOR_DB == "opensearch":
-    from open_webui.retrieval.vector.dbs.opensearch import OpenSearchClient
-
-    VECTOR_DB_CLIENT = OpenSearchClient()
-elif VECTOR_DB == "pgvector":
-    from open_webui.retrieval.vector.dbs.pgvector import PgvectorClient
-
-    VECTOR_DB_CLIENT = PgvectorClient()
-elif VECTOR_DB == "elasticsearch":
-    from open_webui.retrieval.vector.dbs.elasticsearch import ElasticsearchClient
-
-    VECTOR_DB_CLIENT = ElasticsearchClient()
-elif VECTOR_DB == "pinecone":
-    from open_webui.retrieval.vector.dbs.pinecone import PineconeClient
-
-    VECTOR_DB_CLIENT = PineconeClient()
-else:
-    from open_webui.retrieval.vector.dbs.chroma import ChromaClient
-
-    VECTOR_DB_CLIENT = ChromaClient()

backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py

@@ -0,0 +1,712 @@
+import logging
+from typing import Optional, Tuple
+from urllib.parse import urlparse
+
+import grpc
+from open_webui.config import (
+    QDRANT_API_KEY,
+    QDRANT_GRPC_PORT,
+    QDRANT_ON_DISK,
+    QDRANT_PREFER_GRPC,
+    QDRANT_URI,
+)
+from open_webui.env import SRC_LOG_LEVELS
+from open_webui.retrieval.vector.main import (
+    GetResult,
+    SearchResult,
+    VectorDBBase,
+    VectorItem,
+)
+from qdrant_client import QdrantClient as Qclient
+from qdrant_client.http.exceptions import UnexpectedResponse
+from qdrant_client.http.models import PointStruct
+from qdrant_client.models import models
+
+NO_LIMIT = 999999999
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+class QdrantClient(VectorDBBase):
+    def __init__(self):
+        self.collection_prefix = "open-webui"
+        self.QDRANT_URI = QDRANT_URI
+        self.QDRANT_API_KEY = QDRANT_API_KEY
+        self.QDRANT_ON_DISK = QDRANT_ON_DISK
+        self.PREFER_GRPC = QDRANT_PREFER_GRPC
+        self.GRPC_PORT = QDRANT_GRPC_PORT
+
+        if not self.QDRANT_URI:
+            self.client = None
+            return
+
+        # Unified handling for either scheme
+        parsed = urlparse(self.QDRANT_URI)
+        host = parsed.hostname or self.QDRANT_URI
+        http_port = parsed.port or 6333  # default REST port
+
+        if self.PREFER_GRPC:
+            self.client = Qclient(
+                host=host,
+                port=http_port,
+                grpc_port=self.GRPC_PORT,
+                prefer_grpc=self.PREFER_GRPC,
+                api_key=self.QDRANT_API_KEY,
+            )
+        else:
+            self.client = Qclient(url=self.QDRANT_URI, api_key=self.QDRANT_API_KEY)
+
+        # Main collection types for multi-tenancy
+        self.MEMORY_COLLECTION = f"{self.collection_prefix}_memories"
+        self.KNOWLEDGE_COLLECTION = f"{self.collection_prefix}_knowledge"
+        self.FILE_COLLECTION = f"{self.collection_prefix}_files"
+        self.WEB_SEARCH_COLLECTION = f"{self.collection_prefix}_web-search"
+        self.HASH_BASED_COLLECTION = f"{self.collection_prefix}_hash-based"
+
+    def _result_to_get_result(self, points) -> GetResult:
+        ids = []
+        documents = []
+        metadatas = []
+
+        for point in points:
+            payload = point.payload
+            ids.append(point.id)
+            documents.append(payload["text"])
+            metadatas.append(payload["metadata"])
+
+        return GetResult(
+            **{
+                "ids": [ids],
+                "documents": [documents],
+                "metadatas": [metadatas],
+            }
+        )
+
+    def _get_collection_and_tenant_id(self, collection_name: str) -> Tuple[str, str]:
+        """
+        Maps the traditional collection name to multi-tenant collection and tenant ID.
+
+        Returns:
+            tuple: (collection_name, tenant_id)
+        """
+        # Check for user memory collections
+        tenant_id = collection_name
+
+        if collection_name.startswith("user-memory-"):
+            return self.MEMORY_COLLECTION, tenant_id
+
+        # Check for file collections
+        elif collection_name.startswith("file-"):
+            return self.FILE_COLLECTION, tenant_id
+
+        # Check for web search collections
+        elif collection_name.startswith("web-search-"):
+            return self.WEB_SEARCH_COLLECTION, tenant_id
+
+        # Handle hash-based collections (YouTube and web URLs)
+        elif len(collection_name) == 63 and all(
+            c in "0123456789abcdef" for c in collection_name
+        ):
+            return self.HASH_BASED_COLLECTION, tenant_id
+
+        else:
+            return self.KNOWLEDGE_COLLECTION, tenant_id
+
+    def _extract_error_message(self, exception):
+        """
+        Extract error message from either HTTP or gRPC exceptions
+
+        Returns:
+            tuple: (status_code, error_message)
+        """
+        # Check if it's an HTTP exception
+        if isinstance(exception, UnexpectedResponse):
+            try:
+                error_data = exception.structured()
+                error_msg = error_data.get("status", {}).get("error", "")
+                return exception.status_code, error_msg
+            except Exception as inner_e:
+                log.error(f"Failed to parse HTTP error: {inner_e}")
+                return exception.status_code, str(exception)
+
+        # Check if it's a gRPC exception
+        elif isinstance(exception, grpc.RpcError):
+            # Extract status code from gRPC error
+            status_code = None
+            if hasattr(exception, "code") and callable(exception.code):
+                status_code = exception.code().value[0]
+
+            # Extract error message
+            error_msg = str(exception)
+            if "details =" in error_msg:
+                # Parse the details line which contains the actual error message
+                try:
+                    details_line = [
+                        line.strip()
+                        for line in error_msg.split("\n")
+                        if "details =" in line
+                    ][0]
+                    error_msg = details_line.split("details =")[1].strip(' "')
+                except (IndexError, AttributeError):
+                    # Fall back to full message if parsing fails
+                    pass
+
+            return status_code, error_msg
+
+        # For any other type of exception
+        return None, str(exception)
+
+    def _is_collection_not_found_error(self, exception):
+        """
+        Check if the exception is due to collection not found, supporting both HTTP and gRPC
+        """
+        status_code, error_msg = self._extract_error_message(exception)
+
+        # HTTP error (404)
+        if (
+            status_code == 404
+            and "Collection" in error_msg
+            and "doesn't exist" in error_msg
+        ):
+            return True
+
+        # gRPC error (NOT_FOUND status)
+        if (
+            isinstance(exception, grpc.RpcError)
+            and exception.code() == grpc.StatusCode.NOT_FOUND
+        ):
+            return True
+
+        return False
+
+    def _is_dimension_mismatch_error(self, exception):
+        """
+        Check if the exception is due to dimension mismatch, supporting both HTTP and gRPC
+        """
+        status_code, error_msg = self._extract_error_message(exception)
+
+        # Common patterns in both HTTP and gRPC
+        return (
+            "Vector dimension error" in error_msg
+            or "dimensions mismatch" in error_msg
+            or "invalid vector size" in error_msg
+        )
+
+    def _create_multi_tenant_collection_if_not_exists(
+        self, mt_collection_name: str, dimension: int = 384
+    ):
+        """
+        Creates a collection with multi-tenancy configuration if it doesn't exist.
+        Default dimension is set to 384 which corresponds to 'sentence-transformers/all-MiniLM-L6-v2'.
+        When creating collections dynamically (insert/upsert), the actual vector dimensions will be used.
+        """
+        try:
+            # Try to create the collection directly - will fail if it already exists
+            self.client.create_collection(
+                collection_name=mt_collection_name,
+                vectors_config=models.VectorParams(
+                    size=dimension,
+                    distance=models.Distance.COSINE,
+                    on_disk=self.QDRANT_ON_DISK,
+                ),
+                hnsw_config=models.HnswConfigDiff(
+                    payload_m=16,  # Enable per-tenant indexing
+                    m=0,
+                    on_disk=self.QDRANT_ON_DISK,
+                ),
+            )
+
+            # Create tenant ID payload index
+            self.client.create_payload_index(
+                collection_name=mt_collection_name,
+                field_name="tenant_id",
+                field_schema=models.KeywordIndexParams(
+                    type=models.KeywordIndexType.KEYWORD,
+                    is_tenant=True,
+                    on_disk=self.QDRANT_ON_DISK,
+                ),
+                wait=True,
+            )
+
+            log.info(
+                f"Multi-tenant collection {mt_collection_name} created with dimension {dimension}!"
+            )
+        except (UnexpectedResponse, grpc.RpcError) as e:
+            # Check for the specific error indicating collection already exists
+            status_code, error_msg = self._extract_error_message(e)
+
+            # HTTP status code 409 or gRPC ALREADY_EXISTS
+            if (isinstance(e, UnexpectedResponse) and status_code == 409) or (
+                isinstance(e, grpc.RpcError)
+                and e.code() == grpc.StatusCode.ALREADY_EXISTS
+            ):
+                if "already exists" in error_msg:
+                    log.debug(f"Collection {mt_collection_name} already exists")
+                    return
+            # If it's not an already exists error, re-raise
+            raise e
+        except Exception as e:
+            raise e
+
+    def _create_points(self, items: list[VectorItem], tenant_id: str):
+        """
+        Create point structs from vector items with tenant ID.
+        """
+        return [
+            PointStruct(
+                id=item["id"],
+                vector=item["vector"],
+                payload={
+                    "text": item["text"],
+                    "metadata": item["metadata"],
+                    "tenant_id": tenant_id,
+                },
+            )
+            for item in items
+        ]
+
+    def has_collection(self, collection_name: str) -> bool:
+        """
+        Check if a logical collection exists by checking for any points with the tenant ID.
+        """
+        if not self.client:
+            return False
+
+        # Map to multi-tenant collection and tenant ID
+        mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
+
+        # Create tenant filter
+        tenant_filter = models.FieldCondition(
+            key="tenant_id", match=models.MatchValue(value=tenant_id)
+        )
+
+        try:
+            # Try directly querying - most of the time collection should exist
+            response = self.client.query_points(
+                collection_name=mt_collection,
+                query_filter=models.Filter(must=[tenant_filter]),
+                limit=1,
+            )
+
+            # Collection exists with this tenant ID if there are points
+            return len(response.points) > 0
+        except (UnexpectedResponse, grpc.RpcError) as e:
+            if self._is_collection_not_found_error(e):
+                log.debug(f"Collection {mt_collection} doesn't exist")
+                return False
+            else:
+                # For other API errors, log and return False
+                _, error_msg = self._extract_error_message(e)
+                log.warning(f"Unexpected Qdrant error: {error_msg}")
+                return False
+        except Exception as e:
+            # For any other errors, log and return False
+            log.debug(f"Error checking collection {mt_collection}: {e}")
+            return False
+
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[list[str]] = None,
+        filter: Optional[dict] = None,
+    ):
+        """
+        Delete vectors by ID or filter from a collection with tenant isolation.
+        """
+        if not self.client:
+            return None
+
+        # Map to multi-tenant collection and tenant ID
+        mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
+
+        # Create tenant filter
+        tenant_filter = models.FieldCondition(
+            key="tenant_id", match=models.MatchValue(value=tenant_id)
+        )
+
+        must_conditions = [tenant_filter]
+        should_conditions = []
+
+        if ids:
+            for id_value in ids:
+                should_conditions.append(
+                    models.FieldCondition(
+                        key="metadata.id",
+                        match=models.MatchValue(value=id_value),
+                    ),
+                )
+        elif filter:
+            for key, value in filter.items():
+                must_conditions.append(
+                    models.FieldCondition(
+                        key=f"metadata.{key}",
+                        match=models.MatchValue(value=value),
+                    ),
+                )
+
+        try:
+            # Try to delete directly - most of the time collection should exist
+            update_result = self.client.delete(
+                collection_name=mt_collection,
+                points_selector=models.FilterSelector(
+                    filter=models.Filter(must=must_conditions, should=should_conditions)
+                ),
+            )
+
+            return update_result
+        except (UnexpectedResponse, grpc.RpcError) as e:
+            if self._is_collection_not_found_error(e):
+                log.debug(
+                    f"Collection {mt_collection} doesn't exist, nothing to delete"
+                )
+                return None
+            else:
+                # For other API errors, log and re-raise
+                _, error_msg = self._extract_error_message(e)
+                log.warning(f"Unexpected Qdrant error: {error_msg}")
+                raise
+        except Exception as e:
+            # For non-Qdrant exceptions, re-raise
+            raise
+
+    def search(
+        self, collection_name: str, vectors: list[list[float | int]], limit: int
+    ) -> Optional[SearchResult]:
+        """
+        Search for the nearest neighbor items based on the vectors with tenant isolation.
+        """
+        if not self.client:
+            return None
+
+        # Map to multi-tenant collection and tenant ID
+        mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
+
+        # Get the vector dimension from the query vector
+        dimension = len(vectors[0]) if vectors and len(vectors) > 0 else None
+
+        try:
+            # Try the search operation directly - most of the time collection should exist
+
+            # Create tenant filter
+            tenant_filter = models.FieldCondition(
+                key="tenant_id", match=models.MatchValue(value=tenant_id)
+            )
+
+            # Ensure vector dimensions match the collection
+            collection_dim = self.client.get_collection(
+                mt_collection
+            ).config.params.vectors.size
+
+            if collection_dim != dimension:
+                if collection_dim < dimension:
+                    vectors = [vector[:collection_dim] for vector in vectors]
+                else:
+                    vectors = [
+                        vector + [0] * (collection_dim - dimension)
+                        for vector in vectors
+                    ]
+
+            # Search with tenant filter
+            prefetch_query = models.Prefetch(
+                filter=models.Filter(must=[tenant_filter]),
+                limit=NO_LIMIT,
+            )
+            query_response = self.client.query_points(
+                collection_name=mt_collection,
+                query=vectors[0],
+                prefetch=prefetch_query,
+                limit=limit,
+            )
+
+            get_result = self._result_to_get_result(query_response.points)
+            return SearchResult(
+                ids=get_result.ids,
+                documents=get_result.documents,
+                metadatas=get_result.metadatas,
+                # qdrant distance is [-1, 1], normalize to [0, 1]
+                distances=[
+                    [(point.score + 1.0) / 2.0 for point in query_response.points]
+                ],
+            )
+        except (UnexpectedResponse, grpc.RpcError) as e:
+            if self._is_collection_not_found_error(e):
+                log.debug(
+                    f"Collection {mt_collection} doesn't exist, search returns None"
+                )
+                return None
+            else:
+                # For other API errors, log and re-raise
+                _, error_msg = self._extract_error_message(e)
+                log.warning(f"Unexpected Qdrant error during search: {error_msg}")
+                raise
+        except Exception as e:
+            # For non-Qdrant exceptions, log and return None
+            log.exception(f"Error searching collection '{collection_name}': {e}")
+            return None
+
+    def query(self, collection_name: str, filter: dict, limit: Optional[int] = None):
+        """
+        Query points with filters and tenant isolation.
+        """
+        if not self.client:
+            return None
+
+        # Map to multi-tenant collection and tenant ID
+        mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
+
+        # Set default limit if not provided
+        if limit is None:
+            limit = NO_LIMIT
+
+        # Create tenant filter
+        tenant_filter = models.FieldCondition(
+            key="tenant_id", match=models.MatchValue(value=tenant_id)
+        )
+
+        # Create metadata filters
+        field_conditions = []
+        for key, value in filter.items():
+            field_conditions.append(
+                models.FieldCondition(
+                    key=f"metadata.{key}", match=models.MatchValue(value=value)
+                )
+            )
+
+        # Combine tenant filter with metadata filters
+        combined_filter = models.Filter(must=[tenant_filter, *field_conditions])
+
+        try:
+            # Try the query directly - most of the time collection should exist
+            points = self.client.query_points(
+                collection_name=mt_collection,
+                query_filter=combined_filter,
+                limit=limit,
+            )
+
+            return self._result_to_get_result(points.points)
+        except (UnexpectedResponse, grpc.RpcError) as e:
+            if self._is_collection_not_found_error(e):
+                log.debug(
+                    f"Collection {mt_collection} doesn't exist, query returns None"
+                )
+                return None
+            else:
+                # For other API errors, log and re-raise
+                _, error_msg = self._extract_error_message(e)
+                log.warning(f"Unexpected Qdrant error during query: {error_msg}")
+                raise
+        except Exception as e:
+            # For non-Qdrant exceptions, log and re-raise
+            log.exception(f"Error querying collection '{collection_name}': {e}")
+            return None
+
+    def get(self, collection_name: str) -> Optional[GetResult]:
+        """
+        Get all items in a collection with tenant isolation.
+        """
+        if not self.client:
+            return None
+
+        # Map to multi-tenant collection and tenant ID
+        mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
+
+        # Create tenant filter
+        tenant_filter = models.FieldCondition(
+            key="tenant_id", match=models.MatchValue(value=tenant_id)
+        )
+
+        try:
+            # Try to get points directly - most of the time collection should exist
+            points = self.client.query_points(
+                collection_name=mt_collection,
+                query_filter=models.Filter(must=[tenant_filter]),
+                limit=NO_LIMIT,
+            )
+
+            return self._result_to_get_result(points.points)
+        except (UnexpectedResponse, grpc.RpcError) as e:
+            if self._is_collection_not_found_error(e):
+                log.debug(f"Collection {mt_collection} doesn't exist, get returns None")
+                return None
+            else:
+                # For other API errors, log and re-raise
+                _, error_msg = self._extract_error_message(e)
+                log.warning(f"Unexpected Qdrant error during get: {error_msg}")
+                raise
+        except Exception as e:
+            # For non-Qdrant exceptions, log and return None
+            log.exception(f"Error getting collection '{collection_name}': {e}")
+            return None
+
+    def _handle_operation_with_error_retry(
+        self, operation_name, mt_collection, points, dimension
+    ):
+        """
+        Private helper to handle common error cases for insert and upsert operations.
+
+        Args:
+            operation_name: 'insert' or 'upsert'
+            mt_collection: The multi-tenant collection name
+            points: The vector points to insert/upsert
+            dimension: The dimension of the vectors
+
+        Returns:
+            The operation result (for upsert) or None (for insert)
+        """
+        try:
+            if operation_name == "insert":
+                self.client.upload_points(mt_collection, points)
+                return None
+            else:  # upsert
+                return self.client.upsert(mt_collection, points)
+        except (UnexpectedResponse, grpc.RpcError) as e:
+            # Handle collection not found
+            if self._is_collection_not_found_error(e):
+                log.info(
+                    f"Collection {mt_collection} doesn't exist. Creating it with dimension {dimension}."
+                )
+                # Create collection with correct dimensions from our vectors
+                self._create_multi_tenant_collection_if_not_exists(
+                    mt_collection_name=mt_collection, dimension=dimension
+                )
+                # Try operation again - no need for dimension adjustment since we just created with correct dimensions
+                if operation_name == "insert":
+                    self.client.upload_points(mt_collection, points)
+                    return None
+                else:  # upsert
+                    return self.client.upsert(mt_collection, points)
+
+            # Handle dimension mismatch
+            elif self._is_dimension_mismatch_error(e):
+                # For dimension errors, the collection must exist, so get its configuration
+                mt_collection_info = self.client.get_collection(mt_collection)
+                existing_size = mt_collection_info.config.params.vectors.size
+
+                log.info(
+                    f"Dimension mismatch: Collection {mt_collection} expects {existing_size}, got {dimension}"
+                )
+
+                if existing_size < dimension:
+                    # Truncate vectors to fit
+                    log.info(
+                        f"Truncating vectors from {dimension} to {existing_size} dimensions"
+                    )
+                    points = [
+                        PointStruct(
+                            id=point.id,
+                            vector=point.vector[:existing_size],
+                            payload=point.payload,
+                        )
+                        for point in points
+                    ]
+                elif existing_size > dimension:
+                    # Pad vectors with zeros
+                    log.info(
+                        f"Padding vectors from {dimension} to {existing_size} dimensions with zeros"
+                    )
+                    points = [
+                        PointStruct(
+                            id=point.id,
+                            vector=point.vector
+                            + [0] * (existing_size - len(point.vector)),
+                            payload=point.payload,
+                        )
+                        for point in points
+                    ]
+                # Try operation again with adjusted dimensions
+                if operation_name == "insert":
+                    self.client.upload_points(mt_collection, points)
+                    return None
+                else:  # upsert
+                    return self.client.upsert(mt_collection, points)
+            else:
+                # Not a known error we can handle, log and re-raise
+                _, error_msg = self._extract_error_message(e)
+                log.warning(f"Unhandled Qdrant error: {error_msg}")
+                raise
+        except Exception as e:
+            # For non-Qdrant exceptions, re-raise
+            raise
+
+    def insert(self, collection_name: str, items: list[VectorItem]):
+        """
+        Insert items with tenant ID.
+        """
+        if not self.client or not items:
+            return None
+
+        # Map to multi-tenant collection and tenant ID
+        mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
+
+        # Get dimensions from the actual vectors
+        dimension = len(items[0]["vector"]) if items else None
+
+        # Create points with tenant ID
+        points = self._create_points(items, tenant_id)
+
+        # Handle the operation with error retry
+        return self._handle_operation_with_error_retry(
+            "insert", mt_collection, points, dimension
+        )
+
+    def upsert(self, collection_name: str, items: list[VectorItem]):
+        """
+        Upsert items with tenant ID.
+        """
+        if not self.client or not items:
+            return None
+
+        # Map to multi-tenant collection and tenant ID
+        mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
+
+        # Get dimensions from the actual vectors
+        dimension = len(items[0]["vector"]) if items else None
+
+        # Create points with tenant ID
+        points = self._create_points(items, tenant_id)
+
+        # Handle the operation with error retry
+        return self._handle_operation_with_error_retry(
+            "upsert", mt_collection, points, dimension
+        )
+
+    def reset(self):
+        """
+        Reset the database by deleting all collections.
+        """
+        if not self.client:
+            return None
+
+        collection_names = self.client.get_collections().collections
+        for collection_name in collection_names:
+            if collection_name.name.startswith(self.collection_prefix):
+                self.client.delete_collection(collection_name=collection_name.name)
+
+    def delete_collection(self, collection_name: str):
+        """
+        Delete a collection.
+        """
+        if not self.client:
+            return None
+
+        # Map to multi-tenant collection and tenant ID
+        mt_collection, tenant_id = self._get_collection_and_tenant_id(collection_name)
+
+        tenant_filter = models.FieldCondition(
+            key="tenant_id", match=models.MatchValue(value=tenant_id)
+        )
+
+        field_conditions = [tenant_filter]
+
+        update_result = self.client.delete(
+            collection_name=mt_collection,
+            points_selector=models.FilterSelector(
+                filter=models.Filter(must=field_conditions)
+            ),
+        )
+
+        if self.client.get_collection(mt_collection).points_count == 0:
+            self.client.delete_collection(mt_collection)
+
+        return update_result

backend/open_webui/retrieval/vector/factory.py

@@ -0,0 +1,55 @@
+from open_webui.retrieval.vector.main import VectorDBBase
+from open_webui.retrieval.vector.type import VectorType
+from open_webui.config import VECTOR_DB, ENABLE_QDRANT_MULTITENANCY_MODE
+
+
+class Vector:
+
+    @staticmethod
+    def get_vector(vector_type: str) -> VectorDBBase:
+        """
+        get vector db instance by vector type
+        """
+        match vector_type:
+            case VectorType.MILVUS:
+                from open_webui.retrieval.vector.dbs.milvus import MilvusClient
+
+                return MilvusClient()
+            case VectorType.QDRANT:
+                if ENABLE_QDRANT_MULTITENANCY_MODE:
+                    from open_webui.retrieval.vector.dbs.qdrant_multitenancy import (
+                        QdrantClient,
+                    )
+
+                    return QdrantClient()
+                else:
+                    from open_webui.retrieval.vector.dbs.qdrant import QdrantClient
+
+                    return QdrantClient()
+            case VectorType.PINECONE:
+                from open_webui.retrieval.vector.dbs.pinecone import PineconeClient
+
+                return PineconeClient()
+            case VectorType.OPENSEARCH:
+                from open_webui.retrieval.vector.dbs.opensearch import OpenSearchClient
+
+                return OpenSearchClient()
+            case VectorType.PGVECTOR:
+                from open_webui.retrieval.vector.dbs.pgvector import PgvectorClient
+
+                return PgvectorClient()
+            case VectorType.ELASTICSEARCH:
+                from open_webui.retrieval.vector.dbs.elasticsearch import (
+                    ElasticsearchClient,
+                )
+
+                return ElasticsearchClient()
+            case VectorType.CHROMA:
+                from open_webui.retrieval.vector.dbs.chroma import ChromaClient
+
+                return ChromaClient()
+            case _:
+                raise ValueError(f"Unsupported vector type: {vector_type}")
+
+
+VECTOR_DB_CLIENT = Vector.get_vector(VECTOR_DB)

backend/open_webui/retrieval/vector/type.py

@@ -0,0 +1,11 @@
+from enum import StrEnum
+
+
+class VectorType(StrEnum):
+    MILVUS = "milvus"
+    QDRANT = "qdrant"
+    CHROMA = "chroma"
+    PINECONE = "pinecone"
+    ELASTICSEARCH = "elasticsearch"
+    OPENSEARCH = "opensearch"
+    PGVECTOR = "pgvector"

backend/open_webui/retrieval/web/utils.py

@@ -25,7 +25,7 @@ from langchain_community.document_loaders.firecrawl import FireCrawlLoader
 from langchain_community.document_loaders.base import BaseLoader
 from langchain_core.documents import Document
 from open_webui.retrieval.loaders.tavily import TavilyLoader
-from open_webui.retrieval.loaders.external import ExternalLoader
+from open_webui.retrieval.loaders.external_web import ExternalWebLoader
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.config import (
     ENABLE_RAG_LOCAL_WEB_FETCH,
@@ -39,7 +39,7 @@ from open_webui.config import (
     EXTERNAL_WEB_LOADER_URL,
     EXTERNAL_WEB_LOADER_API_KEY,
 )
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.env import SRC_LOG_LEVELS, AIOHTTP_CLIENT_SESSION_SSL
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
@@ -515,7 +515,9 @@ class SafeWebBaseLoader(WebBaseLoader):
                         kwargs["ssl"] = False
 
                     async with session.get(
-                        url, **(self.requests_kwargs | kwargs)
+                        url,
+                        **(self.requests_kwargs | kwargs),
+                        ssl=AIOHTTP_CLIENT_SESSION_SSL,
                     ) as response:
                         if self.raise_for_status:
                             response.raise_for_status()
@@ -628,7 +630,7 @@ def get_web_loader(
         web_loader_args["extract_depth"] = TAVILY_EXTRACT_DEPTH.value
 
     if WEB_LOADER_ENGINE.value == "external":
-        WebLoaderClass = ExternalLoader
+        WebLoaderClass = ExternalWebLoader
         web_loader_args["external_url"] = EXTERNAL_WEB_LOADER_URL.value
         web_loader_args["external_api_key"] = EXTERNAL_WEB_LOADER_API_KEY.value
 

backend/open_webui/routers/audio.py

@@ -7,6 +7,7 @@ from functools import lru_cache
 from pathlib import Path
 from pydub import AudioSegment
 from pydub.silence import split_on_silence
+from concurrent.futures import ThreadPoolExecutor
 
 import aiohttp
 import aiofiles
@@ -38,6 +39,7 @@ from open_webui.config import (
 
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import (
+    AIOHTTP_CLIENT_SESSION_SSL,
     AIOHTTP_CLIENT_TIMEOUT,
     ENV,
     SRC_LOG_LEVELS,
@@ -49,7 +51,7 @@ from open_webui.env import (
 router = APIRouter()
 
 # Constants
-MAX_FILE_SIZE_MB = 25
+MAX_FILE_SIZE_MB = 20
 MAX_FILE_SIZE = MAX_FILE_SIZE_MB * 1024 * 1024  # Convert MB to bytes
 AZURE_MAX_FILE_SIZE_MB = 200
 AZURE_MAX_FILE_SIZE = AZURE_MAX_FILE_SIZE_MB * 1024 * 1024  # Convert MB to bytes
@@ -71,35 +73,50 @@ from pydub import AudioSegment
 from pydub.utils import mediainfo
 
 
-def get_audio_convert_format(file_path):
+def is_audio_conversion_required(file_path):
-    """Check if the given file needs to be converted to a different format."""
+    """
+    Check if the given audio file needs conversion to mp3.
+    """
+    SUPPORTED_FORMATS = {"flac", "m4a", "mp3", "mp4", "mpeg", "wav", "webm"}
+
     if not os.path.isfile(file_path):
         log.error(f"File not found: {file_path}")
         return False
 
     try:
         info = mediainfo(file_path)
+        codec_name = info.get("codec_name", "").lower()
+        codec_type = info.get("codec_type", "").lower()
+        codec_tag_string = info.get("codec_tag_string", "").lower()
 
+        if codec_name == "aac" and codec_type == "audio" and codec_tag_string == "mp4a":
+            # File is AAC/mp4a audio, recommend mp3 conversion
+            return True
+
+        # If the codec name or file extension is in the supported formats
         if (
-            info.get("codec_name") == "aac"
+            codec_name in SUPPORTED_FORMATS
-            and info.get("codec_type") == "audio"
+            or os.path.splitext(file_path)[1][1:].lower() in SUPPORTED_FORMATS
-            and info.get("codec_tag_string") == "mp4a"
         ):
-            return "mp4"
+            return False  # Already supported
-        elif info.get("format_name") == "ogg":
+
-            return "ogg"
+        return True
     except Exception as e:
         log.error(f"Error getting audio format: {e}")
         return False
 
-    return None
 
-
+def convert_audio_to_mp3(file_path):
-def convert_audio_to_wav(file_path, output_path, conversion_type):
+    """Convert audio file to mp3 format."""
-    """Convert MP4/OGG audio file to WAV format."""
+    try:
-    audio = AudioSegment.from_file(file_path, format=conversion_type)
+        output_path = os.path.splitext(file_path)[0] + ".mp3"
-    audio.export(output_path, format="wav")
+        audio = AudioSegment.from_file(file_path)
-    log.info(f"Converted {file_path} to {output_path}")
+        audio.export(output_path, format="mp3")
+        log.info(f"Converted {file_path} to {output_path}")
+        return output_path
+    except Exception as e:
+        log.error(f"Error converting audio file: {e}")
+        return None
 
 
 def set_faster_whisper_model(model: str, auto_update: bool = False):
@@ -326,6 +343,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                             else {}
                         ),
                     },
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
                 ) as r:
                     r.raise_for_status()
 
@@ -381,6 +399,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                         "Content-Type": "application/json",
                         "xi-api-key": request.app.state.config.TTS_API_KEY,
                     },
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
                 ) as r:
                     r.raise_for_status()
 
@@ -439,6 +458,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                         "X-Microsoft-OutputFormat": output_format,
                     },
                     data=data,
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
                 ) as r:
                     r.raise_for_status()
 
@@ -507,8 +527,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         return FileResponse(file_path)
 
 
-def transcribe(request: Request, file_path):
+def transcription_handler(request, file_path):
-    log.info(f"transcribe: {file_path}")
     filename = os.path.basename(file_path)
     file_dir = os.path.dirname(file_path)
     id = filename.split(".")[0]
@@ -542,19 +561,6 @@ def transcribe(request: Request, file_path):
         log.debug(data)
         return data
     elif request.app.state.config.STT_ENGINE == "openai":
-        convert_format = get_audio_convert_format(file_path)
-
-        if convert_format:
-            ext = convert_format.split(".")[-1]
-
-            os.rename(file_path, file_path.replace(".{ext}", f".{convert_format}"))
-            # Convert unsupported audio file to WAV format
-            convert_audio_to_wav(
-                file_path.replace(".{ext}", f".{convert_format}"),
-                file_path,
-                convert_format,
-            )
-
         r = None
         try:
             r = requests.post(
@@ -771,24 +777,122 @@ def transcribe(request: Request, file_path):
             )
 
 
+def transcribe(request: Request, file_path):
+    log.info(f"transcribe: {file_path}")
+
+    if is_audio_conversion_required(file_path):
+        file_path = convert_audio_to_mp3(file_path)
+
+    try:
+        file_path = compress_audio(file_path)
+    except Exception as e:
+        log.exception(e)
+
+    # Always produce a list of chunk paths (could be one entry if small)
+    try:
+        chunk_paths = split_audio(file_path, MAX_FILE_SIZE)
+        print(f"Chunk paths: {chunk_paths}")
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )
+
+    results = []
+    try:
+        with ThreadPoolExecutor() as executor:
+            # Submit tasks for each chunk_path
+            futures = [
+                executor.submit(transcription_handler, request, chunk_path)
+                for chunk_path in chunk_paths
+            ]
+            # Gather results as they complete
+            for future in futures:
+                try:
+                    results.append(future.result())
+                except Exception as transcribe_exc:
+                    log.exception(f"Error transcribing chunk: {transcribe_exc}")
+                    raise HTTPException(
+                        status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                        detail="Error during transcription.",
+                    )
+    finally:
+        # Clean up only the temporary chunks, never the original file
+        for chunk_path in chunk_paths:
+            if chunk_path != file_path and os.path.isfile(chunk_path):
+                try:
+                    os.remove(chunk_path)
+                except Exception:
+                    pass
+
+    return {
+        "text": " ".join([result["text"] for result in results]),
+    }
+
+
 def compress_audio(file_path):
     if os.path.getsize(file_path) > MAX_FILE_SIZE:
+        id = os.path.splitext(os.path.basename(file_path))[
+            0
+        ]  # Handles names with multiple dots
         file_dir = os.path.dirname(file_path)
+
         audio = AudioSegment.from_file(file_path)
         audio = audio.set_frame_rate(16000).set_channels(1)  # Compress audio
-        compressed_path = f"{file_dir}/{id}_compressed.opus"
-        audio.export(compressed_path, format="opus", bitrate="32k")
-        log.debug(f"Compressed audio to {compressed_path}")
 
-        if (
+        compressed_path = os.path.join(file_dir, f"{id}_compressed.mp3")
-            os.path.getsize(compressed_path) > MAX_FILE_SIZE
+        audio.export(compressed_path, format="mp3", bitrate="32k")
-        ):  # Still larger than MAX_FILE_SIZE after compression
+        # log.debug(f"Compressed audio to {compressed_path}")  # Uncomment if log is defined
-            raise Exception(ERROR_MESSAGES.FILE_TOO_LARGE(size=f"{MAX_FILE_SIZE_MB}MB"))
+
         return compressed_path
     else:
         return file_path
 
 
+def split_audio(file_path, max_bytes, format="mp3", bitrate="32k"):
+    """
+    Splits audio into chunks not exceeding max_bytes.
+    Returns a list of chunk file paths. If audio fits, returns list with original path.
+    """
+    file_size = os.path.getsize(file_path)
+    if file_size <= max_bytes:
+        return [file_path]  # Nothing to split
+
+    audio = AudioSegment.from_file(file_path)
+    duration_ms = len(audio)
+    orig_size = file_size
+
+    approx_chunk_ms = max(int(duration_ms * (max_bytes / orig_size)) - 1000, 1000)
+    chunks = []
+    start = 0
+    i = 0
+
+    base, _ = os.path.splitext(file_path)
+
+    while start < duration_ms:
+        end = min(start + approx_chunk_ms, duration_ms)
+        chunk = audio[start:end]
+        chunk_path = f"{base}_chunk_{i}.{format}"
+        chunk.export(chunk_path, format=format, bitrate=bitrate)
+
+        # Reduce chunk duration if still too large
+        while os.path.getsize(chunk_path) > max_bytes and (end - start) > 5000:
+            end = start + ((end - start) // 2)
+            chunk = audio[start:end]
+            chunk.export(chunk_path, format=format, bitrate=bitrate)
+
+        if os.path.getsize(chunk_path) > max_bytes:
+            os.remove(chunk_path)
+            raise Exception("Audio chunk cannot be reduced below max file size.")
+
+        chunks.append(chunk_path)
+        start = end
+        i += 1
+
+    return chunks
+
+
 @router.post("/transcriptions")
 def transcription(
     request: Request,
@@ -797,15 +901,11 @@ def transcription(
 ):
     log.info(f"file.content_type: {file.content_type}")
 
-    supported_filetypes = (
+    SUPPORTED_CONTENT_TYPES = {"video/webm"}  # Extend if you add more video types!
-        "audio/mpeg",
+    if not (
-        "audio/wav",
+        file.content_type.startswith("audio/")
-        "audio/ogg",
+        or file.content_type in SUPPORTED_CONTENT_TYPES
-        "audio/x-m4a",
+    ):
-        "audio/webm",
-    )
-
-    if not file.content_type.startswith(supported_filetypes):
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,
@@ -826,19 +926,13 @@ def transcription(
             f.write(contents)
 
         try:
-            try:
+            result = transcribe(request, file_path)
-                file_path = compress_audio(file_path)
-            except Exception as e:
-                log.exception(e)
 
-                raise HTTPException(
+            return {
-                    status_code=status.HTTP_400_BAD_REQUEST,
+                **result,
-                    detail=ERROR_MESSAGES.DEFAULT(e),
+                "filename": os.path.basename(file_path),
-                )
+            }
 
-            data = transcribe(request, file_path)
-            file_path = file_path.split("/")[-1]
-            return {**data, "filename": file_path}
         except Exception as e:
             log.exception(e)
 

backend/open_webui/routers/auths.py

@@ -31,7 +31,7 @@ from open_webui.env import (
     SRC_LOG_LEVELS,
 )
 from fastapi import APIRouter, Depends, HTTPException, Request, status
-from fastapi.responses import RedirectResponse, Response
+from fastapi.responses import RedirectResponse, Response, JSONResponse
 from open_webui.config import OPENID_PROVIDER_URL, ENABLE_OAUTH_SIGNUP, ENABLE_LDAP
 from pydantic import BaseModel
 
@@ -51,7 +51,7 @@ from open_webui.utils.access_control import get_permissions
 
 from typing import Optional, List
 
-from ssl import CERT_REQUIRED, PROTOCOL_TLS
+from ssl import CERT_NONE, CERT_REQUIRED, PROTOCOL_TLS
 
 if ENABLE_LDAP.value:
     from ldap3 import Server, Connection, NONE, Tls
@@ -186,6 +186,9 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
     LDAP_APP_PASSWORD = request.app.state.config.LDAP_APP_PASSWORD
     LDAP_USE_TLS = request.app.state.config.LDAP_USE_TLS
     LDAP_CA_CERT_FILE = request.app.state.config.LDAP_CA_CERT_FILE
+    LDAP_VALIDATE_CERT = (
+        CERT_REQUIRED if request.app.state.config.LDAP_VALIDATE_CERT else CERT_NONE
+    )
     LDAP_CIPHERS = (
         request.app.state.config.LDAP_CIPHERS
         if request.app.state.config.LDAP_CIPHERS
@@ -197,7 +200,7 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
 
     try:
         tls = Tls(
-            validate=CERT_REQUIRED,
+            validate=LDAP_VALIDATE_CERT,
             version=PROTOCOL_TLS,
             ca_certs_file=LDAP_CA_CERT_FILE,
             ciphers=LDAP_CIPHERS,
@@ -478,10 +481,6 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
             "admin" if user_count == 0 else request.app.state.config.DEFAULT_USER_ROLE
         )
 
-        if user_count == 0:
-            # Disable signup after the first user is created
-            request.app.state.config.ENABLE_SIGNUP = False
-
         # The password passed to bcrypt must be 72 bytes or fewer. If it is longer, it will be truncated before hashing.
         if len(form_data.password.encode("utf-8")) > 72:
             raise HTTPException(
@@ -541,6 +540,10 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
                 user.id, request.app.state.config.USER_PERMISSIONS
             )
 
+            if user_count == 0:
+                # Disable signup after the first user is created
+                request.app.state.config.ENABLE_SIGNUP = False
+
             return {
                 "token": token,
                 "token_type": "Bearer",
@@ -574,9 +577,14 @@ async def signout(request: Request, response: Response):
                             logout_url = openid_data.get("end_session_endpoint")
                             if logout_url:
                                 response.delete_cookie("oauth_id_token")
-                                return RedirectResponse(
+
+                                return JSONResponse(
+                                    status_code=200,
+                                    content={
+                                        "status": True,
+                                        "redirect_url": f"{logout_url}?id_token_hint={oauth_id_token}",
+                                    },
                                     headers=response.headers,
-                                    url=f"{logout_url}?id_token_hint={oauth_id_token}",
                                 )
                         else:
                             raise HTTPException(
@@ -591,12 +599,18 @@ async def signout(request: Request, response: Response):
                 )
 
     if WEBUI_AUTH_SIGNOUT_REDIRECT_URL:
-        return RedirectResponse(
+        return JSONResponse(
+            status_code=200,
+            content={
+                "status": True,
+                "redirect_url": WEBUI_AUTH_SIGNOUT_REDIRECT_URL,
+            },
             headers=response.headers,
-            url=WEBUI_AUTH_SIGNOUT_REDIRECT_URL,
         )
 
-    return {"status": True}
+    return JSONResponse(
+        status_code=200, content={"status": True}, headers=response.headers
+    )
 
 
 ############################
@@ -696,6 +710,9 @@ async def get_admin_config(request: Request, user=Depends(get_admin_user)):
         "ENABLE_CHANNELS": request.app.state.config.ENABLE_CHANNELS,
         "ENABLE_NOTES": request.app.state.config.ENABLE_NOTES,
         "ENABLE_USER_WEBHOOKS": request.app.state.config.ENABLE_USER_WEBHOOKS,
+        "PENDING_USER_OVERLAY_TITLE": request.app.state.config.PENDING_USER_OVERLAY_TITLE,
+        "PENDING_USER_OVERLAY_CONTENT": request.app.state.config.PENDING_USER_OVERLAY_CONTENT,
+        "RESPONSE_WATERMARK": request.app.state.config.RESPONSE_WATERMARK,
     }
 
 
@@ -713,6 +730,9 @@ class AdminConfig(BaseModel):
     ENABLE_CHANNELS: bool
     ENABLE_NOTES: bool
     ENABLE_USER_WEBHOOKS: bool
+    PENDING_USER_OVERLAY_TITLE: Optional[str] = None
+    PENDING_USER_OVERLAY_CONTENT: Optional[str] = None
+    RESPONSE_WATERMARK: Optional[str] = None
 
 
 @router.post("/admin/config")
@@ -750,6 +770,15 @@ async def update_admin_config(
 
     request.app.state.config.ENABLE_USER_WEBHOOKS = form_data.ENABLE_USER_WEBHOOKS
 
+    request.app.state.config.PENDING_USER_OVERLAY_TITLE = (
+        form_data.PENDING_USER_OVERLAY_TITLE
+    )
+    request.app.state.config.PENDING_USER_OVERLAY_CONTENT = (
+        form_data.PENDING_USER_OVERLAY_CONTENT
+    )
+
+    request.app.state.config.RESPONSE_WATERMARK = form_data.RESPONSE_WATERMARK
+
     return {
         "SHOW_ADMIN_DETAILS": request.app.state.config.SHOW_ADMIN_DETAILS,
         "WEBUI_URL": request.app.state.config.WEBUI_URL,
@@ -764,6 +793,9 @@ async def update_admin_config(
         "ENABLE_CHANNELS": request.app.state.config.ENABLE_CHANNELS,
         "ENABLE_NOTES": request.app.state.config.ENABLE_NOTES,
         "ENABLE_USER_WEBHOOKS": request.app.state.config.ENABLE_USER_WEBHOOKS,
+        "PENDING_USER_OVERLAY_TITLE": request.app.state.config.PENDING_USER_OVERLAY_TITLE,
+        "PENDING_USER_OVERLAY_CONTENT": request.app.state.config.PENDING_USER_OVERLAY_CONTENT,
+        "RESPONSE_WATERMARK": request.app.state.config.RESPONSE_WATERMARK,
     }
 
 
@@ -779,6 +811,7 @@ class LdapServerConfig(BaseModel):
     search_filters: str = ""
     use_tls: bool = True
     certificate_path: Optional[str] = None
+    validate_cert: bool = True
     ciphers: Optional[str] = "ALL"
 
 
@@ -796,6 +829,7 @@ async def get_ldap_server(request: Request, user=Depends(get_admin_user)):
         "search_filters": request.app.state.config.LDAP_SEARCH_FILTERS,
         "use_tls": request.app.state.config.LDAP_USE_TLS,
         "certificate_path": request.app.state.config.LDAP_CA_CERT_FILE,
+        "validate_cert": request.app.state.config.LDAP_VALIDATE_CERT,
         "ciphers": request.app.state.config.LDAP_CIPHERS,
     }
 
@@ -831,6 +865,7 @@ async def update_ldap_server(
     request.app.state.config.LDAP_SEARCH_FILTERS = form_data.search_filters
     request.app.state.config.LDAP_USE_TLS = form_data.use_tls
     request.app.state.config.LDAP_CA_CERT_FILE = form_data.certificate_path
+    request.app.state.config.LDAP_VALIDATE_CERT = form_data.validate_cert
     request.app.state.config.LDAP_CIPHERS = form_data.ciphers
 
     return {
@@ -845,6 +880,7 @@ async def update_ldap_server(
         "search_filters": request.app.state.config.LDAP_SEARCH_FILTERS,
         "use_tls": request.app.state.config.LDAP_USE_TLS,
         "certificate_path": request.app.state.config.LDAP_CA_CERT_FILE,
+        "validate_cert": request.app.state.config.LDAP_VALIDATE_CERT,
         "ciphers": request.app.state.config.LDAP_CIPHERS,
     }
 

backend/open_webui/routers/evaluations.py

@@ -74,13 +74,17 @@ class FeedbackUserResponse(FeedbackResponse):
 @router.get("/feedbacks/all", response_model=list[FeedbackUserResponse])
 async def get_all_feedbacks(user=Depends(get_admin_user)):
     feedbacks = Feedbacks.get_all_feedbacks()
-    return [
+
-        FeedbackUserResponse(
+    feedback_list = []
-            **feedback.model_dump(),
+    for feedback in feedbacks:
-            user=UserResponse(**Users.get_user_by_id(feedback.user_id).model_dump()),
+        user = Users.get_user_by_id(feedback.user_id)
+        feedback_list.append(
+            FeedbackUserResponse(
+                **feedback.model_dump(),
+                user=UserResponse(**user.model_dump()) if user else None,
+            )
         )
-        for feedback in feedbacks
+    return feedback_list
-    ]
 
 
 @router.delete("/feedbacks/all")
@@ -92,12 +96,7 @@ async def delete_all_feedbacks(user=Depends(get_admin_user)):
 @router.get("/feedbacks/all/export", response_model=list[FeedbackModel])
 async def get_all_feedbacks(user=Depends(get_admin_user)):
     feedbacks = Feedbacks.get_all_feedbacks()
-    return [
+    return feedbacks
-        FeedbackModel(
-            **feedback.model_dump(), user=Users.get_user_by_id(feedback.user_id)
-        )
-        for feedback in feedbacks
-    ]
 
 
 @router.get("/feedbacks/user", response_model=list[FeedbackUserResponse])

backend/open_webui/routers/files.py

@@ -95,6 +95,20 @@ def upload_file(
         unsanitized_filename = file.filename
         filename = os.path.basename(unsanitized_filename)
 
+        file_extension = os.path.splitext(filename)[1]
+        if request.app.state.config.ALLOWED_FILE_EXTENSIONS:
+            request.app.state.config.ALLOWED_FILE_EXTENSIONS = [
+                ext for ext in request.app.state.config.ALLOWED_FILE_EXTENSIONS if ext
+            ]
+
+            if file_extension not in request.app.state.config.ALLOWED_FILE_EXTENSIONS:
+                raise HTTPException(
+                    status_code=status.HTTP_400_BAD_REQUEST,
+                    detail=ERROR_MESSAGES.DEFAULT(
+                        f"File type {file_extension} is not allowed"
+                    ),
+                )
+
         # replace filename with uuid
         id = str(uuid.uuid4())
         name = filename
@@ -125,33 +139,31 @@ def upload_file(
         )
         if process:
             try:
+                if file.content_type:
+                    if file.content_type.startswith("audio/") or file.content_type in {
+                        "video/webm"
+                    }:
+                        file_path = Storage.get_file(file_path)
+                        result = transcribe(request, file_path)
 
-                if file.content_type.startswith(
+                        process_file(
-                    (
+                            request,
-                        "audio/mpeg",
+                            ProcessFileForm(file_id=id, content=result.get("text", "")),
-                        "audio/wav",
+                            user=user,
-                        "audio/ogg",
+                        )
-                        "audio/x-m4a",
+                    elif file.content_type not in [
-                        "audio/webm",
+                        "image/png",
-                        "video/webm",
+                        "image/jpeg",
+                        "image/gif",
+                        "video/mp4",
+                        "video/ogg",
+                        "video/quicktime",
+                    ]:
+                        process_file(request, ProcessFileForm(file_id=id), user=user)
+                else:
+                    log.info(
+                        f"File type {file.content_type} is not provided, but trying to process anyway"
                     )
-                ):
-                    file_path = Storage.get_file(file_path)
-                    result = transcribe(request, file_path)
-
-                    process_file(
-                        request,
-                        ProcessFileForm(file_id=id, content=result.get("text", "")),
-                        user=user,
-                    )
-                elif file.content_type not in [
-                    "image/png",
-                    "image/jpeg",
-                    "image/gif",
-                    "video/mp4",
-                    "video/ogg",
-                    "video/quicktime",
-                ]:
                     process_file(request, ProcessFileForm(file_id=id), user=user)
 
                 file_item = Files.get_file_by_id(id=id)

backend/open_webui/routers/knowledge.py

@@ -10,7 +10,7 @@ from open_webui.models.knowledge import (
     KnowledgeUserResponse,
 )
 from open_webui.models.files import Files, FileModel, FileMetadataResponse
-from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
+from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
 from open_webui.routers.retrieval import (
     process_file,
     ProcessFileForm,

backend/open_webui/routers/memories.py

@@ -4,7 +4,7 @@ import logging
 from typing import Optional
 
 from open_webui.models.memories import Memories, MemoryModel
-from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
+from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
 from open_webui.utils.auth import get_verified_user
 from open_webui.env import SRC_LOG_LEVELS
 

backend/open_webui/routers/ollama.py

@@ -340,6 +340,8 @@ async def get_all_models(request: Request, user: UserModel = None):
                     ),  # Legacy support
                 )
 
+                connection_type = api_config.get("connection_type", "local")
+
                 prefix_id = api_config.get("prefix_id", None)
                 tags = api_config.get("tags", [])
                 model_ids = api_config.get("model_ids", [])
@@ -352,14 +354,16 @@ async def get_all_models(request: Request, user: UserModel = None):
                         )
                     )
 
-                if prefix_id:
+                for model in response.get("models", []):
-                    for model in response.get("models", []):
+                    if prefix_id:
                         model["model"] = f"{prefix_id}.{model['model']}"
 
-                if tags:
+                    if tags:
-                    for model in response.get("models", []):
                         model["tags"] = tags
 
+                    if connection_type:
+                        model["connection_type"] = connection_type
+
         def merge_models_lists(model_lists):
             merged_models = {}
 
@@ -1585,7 +1589,9 @@ async def upload_model(
     if url_idx is None:
         url_idx = 0
     ollama_url = request.app.state.config.OLLAMA_BASE_URLS[url_idx]
-    file_path = os.path.join(UPLOAD_DIR, file.filename)
+
+    filename = os.path.basename(file.filename)
+    file_path = os.path.join(UPLOAD_DIR, filename)
     os.makedirs(UPLOAD_DIR, exist_ok=True)
 
     # --- P1: save file locally ---
@@ -1630,13 +1636,13 @@ async def upload_model(
                 os.remove(file_path)
 
                 # Create model in ollama
-                model_name, ext = os.path.splitext(file.filename)
+                model_name, ext = os.path.splitext(filename)
                 log.info(f"Created Model: {model_name}")  # DEBUG
 
                 create_payload = {
                     "model": model_name,
                     # Reference the file by its original name => the uploaded blob's digest
-                    "files": {file.filename: f"sha256:{file_hash}"},
+                    "files": {filename: f"sha256:{file_hash}"},
                 }
                 log.info(f"Model Payload: {create_payload}")  # DEBUG
 
@@ -1653,7 +1659,7 @@ async def upload_model(
                     done_msg = {
                         "done": True,
                         "blob": f"sha256:{file_hash}",
-                        "name": file.filename,
+                        "name": filename,
                         "model_created": model_name,
                     }
                     yield f"data: {json.dumps(done_msg)}\n\n"

backend/open_webui/routers/openai.py

@@ -353,21 +353,22 @@ async def get_all_models_responses(request: Request, user: UserModel) -> list:
                 ),  # Legacy support
             )
 
+            connection_type = api_config.get("connection_type", "external")
             prefix_id = api_config.get("prefix_id", None)
             tags = api_config.get("tags", [])
 
-            if prefix_id:
+            for model in (
-                for model in (
+                response if isinstance(response, list) else response.get("data", [])
-                    response if isinstance(response, list) else response.get("data", [])
+            ):
-                ):
+                if prefix_id:
                     model["id"] = f"{prefix_id}.{model['id']}"
 
-            if tags:
+                if tags:
-                for model in (
-                    response if isinstance(response, list) else response.get("data", [])
-                ):
                     model["tags"] = tags
 
+                if connection_type:
+                    model["connection_type"] = connection_type
+
     log.debug(f"get_all_models:responses() {responses}")
     return responses
 
@@ -415,6 +416,7 @@ async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
                             "name": model.get("name", model["id"]),
                             "owned_by": "openai",
                             "openai": model,
+                            "connection_type": model.get("connection_type", "external"),
                             "urlIdx": idx,
                         }
                         for model in models
@@ -461,60 +463,74 @@ async def get_models(
         url = request.app.state.config.OPENAI_API_BASE_URLS[url_idx]
         key = request.app.state.config.OPENAI_API_KEYS[url_idx]
 
+        api_config = request.app.state.config.OPENAI_API_CONFIGS.get(
+            str(url_idx),
+            request.app.state.config.OPENAI_API_CONFIGS.get(url, {}),  # Legacy support
+        )
+
         r = None
         async with aiohttp.ClientSession(
             trust_env=True,
             timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST),
         ) as session:
             try:
-                async with session.get(
+                headers = {
-                    f"{url}/models",
+                    "Content-Type": "application/json",
-                    headers={
+                    **(
-                        "Authorization": f"Bearer {key}",
+                        {
-                        "Content-Type": "application/json",
+                            "X-OpenWebUI-User-Name": user.name,
-                        **(
+                            "X-OpenWebUI-User-Id": user.id,
-                            {
+                            "X-OpenWebUI-User-Email": user.email,
-                                "X-OpenWebUI-User-Name": user.name,
+                            "X-OpenWebUI-User-Role": user.role,
-                                "X-OpenWebUI-User-Id": user.id,
+                        }
-                                "X-OpenWebUI-User-Email": user.email,
+                        if ENABLE_FORWARD_USER_INFO_HEADERS
-                                "X-OpenWebUI-User-Role": user.role,
+                        else {}
-                            }
+                    ),
-                            if ENABLE_FORWARD_USER_INFO_HEADERS
+                }
-                            else {}
-                        ),
-                    },
-                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
-                ) as r:
-                    if r.status != 200:
-                        # Extract response error details if available
-                        error_detail = f"HTTP Error: {r.status}"
-                        res = await r.json()
-                        if "error" in res:
-                            error_detail = f"External Error: {res['error']}"
-                        raise Exception(error_detail)
 
-                    response_data = await r.json()
+                if api_config.get("azure", False):
+                    models = {
+                        "data": api_config.get("model_ids", []) or [],
+                        "object": "list",
+                    }
+                else:
+                    headers["Authorization"] = f"Bearer {key}"
 
-                    # Check if we're calling OpenAI API based on the URL
+                    async with session.get(
-                    if "api.openai.com" in url:
+                        f"{url}/models",
-                        # Filter models according to the specified conditions
+                        headers=headers,
-                        response_data["data"] = [
+                        ssl=AIOHTTP_CLIENT_SESSION_SSL,
-                            model
+                    ) as r:
-                            for model in response_data.get("data", [])
+                        if r.status != 200:
-                            if not any(
+                            # Extract response error details if available
-                                name in model["id"]
+                            error_detail = f"HTTP Error: {r.status}"
-                                for name in [
+                            res = await r.json()
-                                    "babbage",
+                            if "error" in res:
-                                    "dall-e",
+                                error_detail = f"External Error: {res['error']}"
-                                    "davinci",
+                            raise Exception(error_detail)
-                                    "embedding",
-                                    "tts",
-                                    "whisper",
-                                ]
-                            )
-                        ]
 
-                    models = response_data
+                        response_data = await r.json()
+
+                        # Check if we're calling OpenAI API based on the URL
+                        if "api.openai.com" in url:
+                            # Filter models according to the specified conditions
+                            response_data["data"] = [
+                                model
+                                for model in response_data.get("data", [])
+                                if not any(
+                                    name in model["id"]
+                                    for name in [
+                                        "babbage",
+                                        "dall-e",
+                                        "davinci",
+                                        "embedding",
+                                        "tts",
+                                        "whisper",
+                                    ]
+                                )
+                            ]
+
+                        models = response_data
             except aiohttp.ClientError as e:
                 # ClientError covers all aiohttp requests issues
                 log.exception(f"Client error: {str(e)}")
@@ -536,6 +552,8 @@ class ConnectionVerificationForm(BaseModel):
     url: str
     key: str
 
+    config: Optional[dict] = None
+
 
 @router.post("/verify")
 async def verify_connection(
@@ -544,39 +562,64 @@ async def verify_connection(
     url = form_data.url
     key = form_data.key
 
+    api_config = form_data.config or {}
+
     async with aiohttp.ClientSession(
         trust_env=True,
         timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST),
     ) as session:
         try:
-            async with session.get(
+            headers = {
-                f"{url}/models",
+                "Content-Type": "application/json",
-                headers={
+                **(
-                    "Authorization": f"Bearer {key}",
+                    {
-                    "Content-Type": "application/json",
+                        "X-OpenWebUI-User-Name": user.name,
-                    **(
+                        "X-OpenWebUI-User-Id": user.id,
-                        {
+                        "X-OpenWebUI-User-Email": user.email,
-                            "X-OpenWebUI-User-Name": user.name,
+                        "X-OpenWebUI-User-Role": user.role,
-                            "X-OpenWebUI-User-Id": user.id,
+                    }
-                            "X-OpenWebUI-User-Email": user.email,
+                    if ENABLE_FORWARD_USER_INFO_HEADERS
-                            "X-OpenWebUI-User-Role": user.role,
+                    else {}
-                        }
+                ),
-                        if ENABLE_FORWARD_USER_INFO_HEADERS
+            }
-                        else {}
-                    ),
-                },
-                ssl=AIOHTTP_CLIENT_SESSION_SSL,
-            ) as r:
-                if r.status != 200:
-                    # Extract response error details if available
-                    error_detail = f"HTTP Error: {r.status}"
-                    res = await r.json()
-                    if "error" in res:
-                        error_detail = f"External Error: {res['error']}"
-                    raise Exception(error_detail)
 
-                response_data = await r.json()
+            if api_config.get("azure", False):
-                return response_data
+                headers["api-key"] = key
+                api_version = api_config.get("api_version", "") or "2023-03-15-preview"
+
+                async with session.get(
+                    url=f"{url}/openai/models?api-version={api_version}",
+                    headers=headers,
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
+                ) as r:
+                    if r.status != 200:
+                        # Extract response error details if available
+                        error_detail = f"HTTP Error: {r.status}"
+                        res = await r.json()
+                        if "error" in res:
+                            error_detail = f"External Error: {res['error']}"
+                        raise Exception(error_detail)
+
+                    response_data = await r.json()
+                    return response_data
+            else:
+                headers["Authorization"] = f"Bearer {key}"
+
+                async with session.get(
+                    f"{url}/models",
+                    headers=headers,
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
+                ) as r:
+                    if r.status != 200:
+                        # Extract response error details if available
+                        error_detail = f"HTTP Error: {r.status}"
+                        res = await r.json()
+                        if "error" in res:
+                            error_detail = f"External Error: {res['error']}"
+                        raise Exception(error_detail)
+
+                    response_data = await r.json()
+                    return response_data
 
         except aiohttp.ClientError as e:
             # ClientError covers all aiohttp requests issues
@@ -590,6 +633,63 @@ async def verify_connection(
             raise HTTPException(status_code=500, detail=error_detail)
 
 
+def convert_to_azure_payload(
+    url,
+    payload: dict,
+):
+    model = payload.get("model", "")
+
+    # Filter allowed parameters based on Azure OpenAI API
+    allowed_params = {
+        "messages",
+        "temperature",
+        "role",
+        "content",
+        "contentPart",
+        "contentPartImage",
+        "enhancements",
+        "dataSources",
+        "n",
+        "stream",
+        "stop",
+        "max_tokens",
+        "presence_penalty",
+        "frequency_penalty",
+        "logit_bias",
+        "user",
+        "function_call",
+        "functions",
+        "tools",
+        "tool_choice",
+        "top_p",
+        "log_probs",
+        "top_logprobs",
+        "response_format",
+        "seed",
+        "max_completion_tokens",
+    }
+
+    # Special handling for o-series models
+    if model.startswith("o") and model.endswith("-mini"):
+        # Convert max_tokens to max_completion_tokens for o-series models
+        if "max_tokens" in payload:
+            payload["max_completion_tokens"] = payload["max_tokens"]
+            del payload["max_tokens"]
+
+        # Remove temperature if not 1 for o-series models
+        if "temperature" in payload and payload["temperature"] != 1:
+            log.debug(
+                f"Removing temperature parameter for o-series model {model} as only default value (1) is supported"
+            )
+            del payload["temperature"]
+
+    # Filter out unsupported parameters
+    payload = {k: v for k, v in payload.items() if k in allowed_params}
+
+    url = f"{url}/openai/deployments/{model}"
+    return url, payload
+
+
 @router.post("/chat/completions")
 async def generate_chat_completion(
     request: Request,
@@ -690,6 +790,38 @@ async def generate_chat_completion(
             convert_logit_bias_input_to_json(payload["logit_bias"])
         )
 
+    headers = {
+        "Content-Type": "application/json",
+        **(
+            {
+                "HTTP-Referer": "https://openwebui.com/",
+                "X-Title": "Open WebUI",
+            }
+            if "openrouter.ai" in url
+            else {}
+        ),
+        **(
+            {
+                "X-OpenWebUI-User-Name": user.name,
+                "X-OpenWebUI-User-Id": user.id,
+                "X-OpenWebUI-User-Email": user.email,
+                "X-OpenWebUI-User-Role": user.role,
+            }
+            if ENABLE_FORWARD_USER_INFO_HEADERS
+            else {}
+        ),
+    }
+
+    if api_config.get("azure", False):
+        request_url, payload = convert_to_azure_payload(url, payload)
+        api_version = api_config.get("api_version", "") or "2023-03-15-preview"
+        headers["api-key"] = key
+        headers["api-version"] = api_version
+        request_url = f"{request_url}/chat/completions?api-version={api_version}"
+    else:
+        request_url = f"{url}/chat/completions"
+        headers["Authorization"] = f"Bearer {key}"
+
     payload = json.dumps(payload)
 
     r = None
@@ -704,30 +836,9 @@ async def generate_chat_completion(
 
         r = await session.request(
             method="POST",
-            url=f"{url}/chat/completions",
+            url=request_url,
             data=payload,
-            headers={
+            headers=headers,
-                "Authorization": f"Bearer {key}",
-                "Content-Type": "application/json",
-                **(
-                    {
-                        "HTTP-Referer": "https://openwebui.com/",
-                        "X-Title": "Open WebUI",
-                    }
-                    if "openrouter.ai" in url
-                    else {}
-                ),
-                **(
-                    {
-                        "X-OpenWebUI-User-Name": user.name,
-                        "X-OpenWebUI-User-Id": user.id,
-                        "X-OpenWebUI-User-Email": user.email,
-                        "X-OpenWebUI-User-Role": user.role,
-                    }
-                    if ENABLE_FORWARD_USER_INFO_HEADERS
-                    else {}
-                ),
-            },
             ssl=AIOHTTP_CLIENT_SESSION_SSL,
         )
 
@@ -783,31 +894,53 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
     idx = 0
     url = request.app.state.config.OPENAI_API_BASE_URLS[idx]
     key = request.app.state.config.OPENAI_API_KEYS[idx]
+    api_config = request.app.state.config.OPENAI_API_CONFIGS.get(
+        str(idx),
+        request.app.state.config.OPENAI_API_CONFIGS.get(
+            request.app.state.config.OPENAI_API_BASE_URLS[idx], {}
+        ),  # Legacy support
+    )
 
     r = None
     session = None
     streaming = False
 
     try:
+        headers = {
+            "Content-Type": "application/json",
+            **(
+                {
+                    "X-OpenWebUI-User-Name": user.name,
+                    "X-OpenWebUI-User-Id": user.id,
+                    "X-OpenWebUI-User-Email": user.email,
+                    "X-OpenWebUI-User-Role": user.role,
+                }
+                if ENABLE_FORWARD_USER_INFO_HEADERS
+                else {}
+            ),
+        }
+
+        if api_config.get("azure", False):
+            headers["api-key"] = key
+            headers["api-version"] = (
+                api_config.get("api_version", "") or "2023-03-15-preview"
+            )
+
+            payload = json.loads(body)
+            url, payload = convert_to_azure_payload(url, payload)
+            body = json.dumps(payload).encode()
+
+            request_url = f"{url}/{path}?api-version={api_config.get('api_version', '2023-03-15-preview')}"
+        else:
+            headers["Authorization"] = f"Bearer {key}"
+            request_url = f"{url}/{path}"
+
         session = aiohttp.ClientSession(trust_env=True)
         r = await session.request(
             method=request.method,
-            url=f"{url}/{path}",
+            url=request_url,
             data=body,
-            headers={
+            headers=headers,
-                "Authorization": f"Bearer {key}",
-                "Content-Type": "application/json",
-                **(
-                    {
-                        "X-OpenWebUI-User-Name": user.name,
-                        "X-OpenWebUI-User-Id": user.id,
-                        "X-OpenWebUI-User-Email": user.email,
-                        "X-OpenWebUI-User-Role": user.role,
-                    }
-                    if ENABLE_FORWARD_USER_INFO_HEADERS
-                    else {}
-                ),
-            },
             ssl=AIOHTTP_CLIENT_SESSION_SSL,
         )
         r.raise_for_status()

backend/open_webui/routers/pipelines.py

@@ -18,7 +18,7 @@ from pydantic import BaseModel
 from starlette.responses import FileResponse
 from typing import Optional
 
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.env import SRC_LOG_LEVELS, AIOHTTP_CLIENT_SESSION_SSL
 from open_webui.config import CACHE_DIR
 from open_webui.constants import ERROR_MESSAGES
 
@@ -69,7 +69,10 @@ async def process_pipeline_inlet_filter(request, payload, user, models):
     async with aiohttp.ClientSession(trust_env=True) as session:
         for filter in sorted_filters:
             urlIdx = filter.get("urlIdx")
-            if urlIdx is None:
+
+            try:
+                urlIdx = int(urlIdx)
+            except:
                 continue
 
             url = request.app.state.config.OPENAI_API_BASE_URLS[urlIdx]
@@ -89,6 +92,7 @@ async def process_pipeline_inlet_filter(request, payload, user, models):
                     f"{url}/{filter['id']}/filter/inlet",
                     headers=headers,
                     json=request_data,
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
                 ) as response:
                     payload = await response.json()
                     response.raise_for_status()
@@ -118,7 +122,10 @@ async def process_pipeline_outlet_filter(request, payload, user, models):
     async with aiohttp.ClientSession(trust_env=True) as session:
         for filter in sorted_filters:
             urlIdx = filter.get("urlIdx")
-            if urlIdx is None:
+
+            try:
+                urlIdx = int(urlIdx)
+            except:
                 continue
 
             url = request.app.state.config.OPENAI_API_BASE_URLS[urlIdx]
@@ -138,6 +145,7 @@ async def process_pipeline_outlet_filter(request, payload, user, models):
                     f"{url}/{filter['id']}/filter/outlet",
                     headers=headers,
                     json=request_data,
+                    ssl=AIOHTTP_CLIENT_SESSION_SSL,
                 ) as response:
                     payload = await response.json()
                     response.raise_for_status()
@@ -197,8 +205,10 @@ async def upload_pipeline(
     user=Depends(get_admin_user),
 ):
     log.info(f"upload_pipeline: urlIdx={urlIdx}, filename={file.filename}")
+    filename = os.path.basename(file.filename)
+
     # Check if the uploaded file is a python file
-    if not (file.filename and file.filename.endswith(".py")):
+    if not (filename and filename.endswith(".py")):
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail="Only Python (.py) files are allowed.",
@@ -206,7 +216,7 @@ async def upload_pipeline(
 
     upload_folder = f"{CACHE_DIR}/pipelines"
     os.makedirs(upload_folder, exist_ok=True)
-    file_path = os.path.join(upload_folder, file.filename)
+    file_path = os.path.join(upload_folder, filename)
 
     r = None
     try:

backend/open_webui/routers/retrieval.py

@@ -36,7 +36,7 @@ from open_webui.models.knowledge import Knowledges
 from open_webui.storage.provider import Storage
 
 
-from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
+from open_webui.retrieval.vector.factory import VECTOR_DB_CLIENT
 
 # Document loaders
 from open_webui.retrieval.loaders.main import Loader
@@ -352,10 +352,13 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         # Content extraction settings
         "CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
         "PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
+        "EXTERNAL_DOCUMENT_LOADER_URL": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_URL,
+        "EXTERNAL_DOCUMENT_LOADER_API_KEY": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
         "TIKA_SERVER_URL": request.app.state.config.TIKA_SERVER_URL,
         "DOCLING_SERVER_URL": request.app.state.config.DOCLING_SERVER_URL,
         "DOCLING_OCR_ENGINE": request.app.state.config.DOCLING_OCR_ENGINE,
         "DOCLING_OCR_LANG": request.app.state.config.DOCLING_OCR_LANG,
+        "DOCLING_DO_PICTURE_DESCRIPTION": request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION,
         "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
         "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
         "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY,
@@ -371,6 +374,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         # File upload settings
         "FILE_MAX_SIZE": request.app.state.config.FILE_MAX_SIZE,
         "FILE_MAX_COUNT": request.app.state.config.FILE_MAX_COUNT,
+        "ALLOWED_FILE_EXTENSIONS": request.app.state.config.ALLOWED_FILE_EXTENSIONS,
         # Integration settings
         "ENABLE_GOOGLE_DRIVE_INTEGRATION": request.app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION,
         "ENABLE_ONEDRIVE_INTEGRATION": request.app.state.config.ENABLE_ONEDRIVE_INTEGRATION,
@@ -492,10 +496,14 @@ class ConfigForm(BaseModel):
     # Content extraction settings
     CONTENT_EXTRACTION_ENGINE: Optional[str] = None
     PDF_EXTRACT_IMAGES: Optional[bool] = None
+    EXTERNAL_DOCUMENT_LOADER_URL: Optional[str] = None
+    EXTERNAL_DOCUMENT_LOADER_API_KEY: Optional[str] = None
+
     TIKA_SERVER_URL: Optional[str] = None
     DOCLING_SERVER_URL: Optional[str] = None
     DOCLING_OCR_ENGINE: Optional[str] = None
     DOCLING_OCR_LANG: Optional[str] = None
+    DOCLING_DO_PICTURE_DESCRIPTION: Optional[bool] = None
     DOCUMENT_INTELLIGENCE_ENDPOINT: Optional[str] = None
     DOCUMENT_INTELLIGENCE_KEY: Optional[str] = None
     MISTRAL_OCR_API_KEY: Optional[str] = None
@@ -514,6 +522,7 @@ class ConfigForm(BaseModel):
     # File upload settings
     FILE_MAX_SIZE: Optional[int] = None
     FILE_MAX_COUNT: Optional[int] = None
+    ALLOWED_FILE_EXTENSIONS: Optional[List[str]] = None
 
     # Integration settings
     ENABLE_GOOGLE_DRIVE_INTEGRATION: Optional[bool] = None
@@ -581,6 +590,16 @@ async def update_rag_config(
         if form_data.PDF_EXTRACT_IMAGES is not None
         else request.app.state.config.PDF_EXTRACT_IMAGES
     )
+    request.app.state.config.EXTERNAL_DOCUMENT_LOADER_URL = (
+        form_data.EXTERNAL_DOCUMENT_LOADER_URL
+        if form_data.EXTERNAL_DOCUMENT_LOADER_URL is not None
+        else request.app.state.config.EXTERNAL_DOCUMENT_LOADER_URL
+    )
+    request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY = (
+        form_data.EXTERNAL_DOCUMENT_LOADER_API_KEY
+        if form_data.EXTERNAL_DOCUMENT_LOADER_API_KEY is not None
+        else request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY
+    )
     request.app.state.config.TIKA_SERVER_URL = (
         form_data.TIKA_SERVER_URL
         if form_data.TIKA_SERVER_URL is not None
@@ -601,6 +620,13 @@ async def update_rag_config(
         if form_data.DOCLING_OCR_LANG is not None
         else request.app.state.config.DOCLING_OCR_LANG
     )
+
+    request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION = (
+        form_data.DOCLING_DO_PICTURE_DESCRIPTION
+        if form_data.DOCLING_DO_PICTURE_DESCRIPTION is not None
+        else request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION
+    )
+
     request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = (
         form_data.DOCUMENT_INTELLIGENCE_ENDPOINT
         if form_data.DOCUMENT_INTELLIGENCE_ENDPOINT is not None
@@ -688,6 +714,11 @@ async def update_rag_config(
         if form_data.FILE_MAX_COUNT is not None
         else request.app.state.config.FILE_MAX_COUNT
     )
+    request.app.state.config.ALLOWED_FILE_EXTENSIONS = (
+        form_data.ALLOWED_FILE_EXTENSIONS
+        if form_data.ALLOWED_FILE_EXTENSIONS is not None
+        else request.app.state.config.ALLOWED_FILE_EXTENSIONS
+    )
 
     # Integration settings
     request.app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION = (
@@ -809,10 +840,13 @@ async def update_rag_config(
         # Content extraction settings
         "CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
         "PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
+        "EXTERNAL_DOCUMENT_LOADER_URL": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_URL,
+        "EXTERNAL_DOCUMENT_LOADER_API_KEY": request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
         "TIKA_SERVER_URL": request.app.state.config.TIKA_SERVER_URL,
         "DOCLING_SERVER_URL": request.app.state.config.DOCLING_SERVER_URL,
         "DOCLING_OCR_ENGINE": request.app.state.config.DOCLING_OCR_ENGINE,
         "DOCLING_OCR_LANG": request.app.state.config.DOCLING_OCR_LANG,
+        "DOCLING_DO_PICTURE_DESCRIPTION": request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION,
         "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
         "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
         "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY,
@@ -828,6 +862,7 @@ async def update_rag_config(
         # File upload settings
         "FILE_MAX_SIZE": request.app.state.config.FILE_MAX_SIZE,
         "FILE_MAX_COUNT": request.app.state.config.FILE_MAX_COUNT,
+        "ALLOWED_FILE_EXTENSIONS": request.app.state.config.ALLOWED_FILE_EXTENSIONS,
         # Integration settings
         "ENABLE_GOOGLE_DRIVE_INTEGRATION": request.app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION,
         "ENABLE_ONEDRIVE_INTEGRATION": request.app.state.config.ENABLE_ONEDRIVE_INTEGRATION,
@@ -1129,10 +1164,13 @@ def process_file(
                 file_path = Storage.get_file(file_path)
                 loader = Loader(
                     engine=request.app.state.config.CONTENT_EXTRACTION_ENGINE,
+                    EXTERNAL_DOCUMENT_LOADER_URL=request.app.state.config.EXTERNAL_DOCUMENT_LOADER_URL,
+                    EXTERNAL_DOCUMENT_LOADER_API_KEY=request.app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY,
                     TIKA_SERVER_URL=request.app.state.config.TIKA_SERVER_URL,
                     DOCLING_SERVER_URL=request.app.state.config.DOCLING_SERVER_URL,
                     DOCLING_OCR_ENGINE=request.app.state.config.DOCLING_OCR_ENGINE,
                     DOCLING_OCR_LANG=request.app.state.config.DOCLING_OCR_LANG,
+                    DOCLING_DO_PICTURE_DESCRIPTION=request.app.state.config.DOCLING_DO_PICTURE_DESCRIPTION,
                     PDF_EXTRACT_IMAGES=request.app.state.config.PDF_EXTRACT_IMAGES,
                     DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
                     DOCUMENT_INTELLIGENCE_KEY=request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,

backend/open_webui/routers/tasks.py

@@ -20,10 +20,7 @@ from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.constants import TASKS
 
 from open_webui.routers.pipelines import process_pipeline_inlet_filter
-from open_webui.utils.filter import (
+
-    get_sorted_filter_ids,
-    process_filter_functions,
-)
 from open_webui.utils.task import get_task_model_id
 
 from open_webui.config import (
@@ -195,15 +192,19 @@ async def generate_title(
         },
     )
 
+    max_tokens = (
+        models[task_model_id].get("info", {}).get("params", {}).get("max_tokens", 1000)
+    )
+
     payload = {
         "model": task_model_id,
         "messages": [{"role": "user", "content": content}],
         "stream": False,
         **(
-            {"max_tokens": 1000}
+            {"max_tokens": max_tokens}
             if models[task_model_id].get("owned_by") == "ollama"
             else {
-                "max_completion_tokens": 1000,
+                "max_completion_tokens": max_tokens,
             }
         ),
         "metadata": {

backend/open_webui/utils/auth.py

@@ -13,6 +13,8 @@ import pytz
 from pytz import UTC
 from typing import Optional, Union, List, Dict
 
+from opentelemetry import trace
+
 from open_webui.models.users import Users
 
 from open_webui.constants import ERROR_MESSAGES
@@ -194,7 +196,17 @@ def get_current_user(
                     status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.API_KEY_NOT_ALLOWED
                 )
 
-        return get_current_user_by_api_key(token)
+        user = get_current_user_by_api_key(token)
+
+        # Add user info to current span
+        current_span = trace.get_current_span()
+        if current_span:
+            current_span.set_attribute("client.user.id", user.id)
+            current_span.set_attribute("client.user.email", user.email)
+            current_span.set_attribute("client.user.role", user.role)
+            current_span.set_attribute("client.auth.type", "api_key")
+
+        return user
 
     # auth by jwt token
     try:
@@ -213,6 +225,14 @@ def get_current_user(
                 detail=ERROR_MESSAGES.INVALID_TOKEN,
             )
         else:
+            # Add user info to current span
+            current_span = trace.get_current_span()
+            if current_span:
+                current_span.set_attribute("client.user.id", user.id)
+                current_span.set_attribute("client.user.email", user.email)
+                current_span.set_attribute("client.user.role", user.role)
+                current_span.set_attribute("client.auth.type", "jwt")
+
             # Refresh the user's last active timestamp asynchronously
             # to prevent blocking the request
             if background_tasks:
@@ -234,6 +254,14 @@ def get_current_user_by_api_key(api_key: str):
             detail=ERROR_MESSAGES.INVALID_TOKEN,
         )
     else:
+        # Add user info to current span
+        current_span = trace.get_current_span()
+        if current_span:
+            current_span.set_attribute("client.user.id", user.id)
+            current_span.set_attribute("client.user.email", user.email)
+            current_span.set_attribute("client.user.role", user.role)
+            current_span.set_attribute("client.auth.type", "api_key")
+
         Users.update_user_last_active_by_id(user.id)
 
     return user

backend/open_webui/utils/chat.py

@@ -309,6 +309,7 @@ async def chat_completed(request: Request, form_data: dict, user: Any):
     metadata = {
         "chat_id": data["chat_id"],
         "message_id": data["id"],
+        "filter_ids": data.get("filter_ids", []),
         "session_id": data["session_id"],
         "user_id": user.id,
     }
@@ -330,7 +331,9 @@ async def chat_completed(request: Request, form_data: dict, user: Any):
     try:
         filter_functions = [
             Functions.get_function_by_id(filter_id)
-            for filter_id in get_sorted_filter_ids(model)
+            for filter_id in get_sorted_filter_ids(
+                request, model, metadata.get("filter_ids", [])
+            )
         ]
 
         result, _ = await process_filter_functions(

backend/open_webui/utils/filter.py

@@ -9,7 +9,20 @@ log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
-def get_sorted_filter_ids(model: dict):
+def get_function_module(request, function_id):
+    """
+    Get the function module by its ID.
+    """
+    if function_id in request.app.state.FUNCTIONS:
+        function_module = request.app.state.FUNCTIONS[function_id]
+    else:
+        function_module, _, _ = load_function_module_by_id(function_id)
+        request.app.state.FUNCTIONS[function_id] = function_module
+
+    return function_module
+
+
+def get_sorted_filter_ids(request, model: dict, enabled_filter_ids: list = None):
     def get_priority(function_id):
         function = Functions.get_function_by_id(function_id)
         if function is not None:
@@ -21,14 +34,23 @@ def get_sorted_filter_ids(model: dict):
     if "info" in model and "meta" in model["info"]:
         filter_ids.extend(model["info"]["meta"].get("filterIds", []))
         filter_ids = list(set(filter_ids))
-
+    active_filter_ids = [
-    enabled_filter_ids = [
         function.id
         for function in Functions.get_functions_by_type("filter", active_only=True)
     ]
 
-    filter_ids = [fid for fid in filter_ids if fid in enabled_filter_ids]
+    for filter_id in active_filter_ids:
+        function_module = get_function_module(request, filter_id)
+
+        if getattr(function_module, "toggle", None) and (
+            filter_id not in enabled_filter_ids
+        ):
+            active_filter_ids.remove(filter_id)
+            continue
+
+    filter_ids = [fid for fid in filter_ids if fid in active_filter_ids]
     filter_ids.sort(key=get_priority)
+
     return filter_ids
 
 
@@ -43,12 +65,7 @@ async def process_filter_functions(
         if not filter:
             continue
 
-        if filter_id in request.app.state.FUNCTIONS:
+        function_module = get_function_module(request, filter_id)
-            function_module = request.app.state.FUNCTIONS[filter_id]
-        else:
-            function_module, _, _ = load_function_module_by_id(filter_id)
-            request.app.state.FUNCTIONS[filter_id] = function_module
-
         # Prepare handler function
         handler = getattr(function_module, filter_type, None)
         if not handler:

backend/open_webui/utils/middleware.py

@@ -340,6 +340,11 @@ async def chat_web_search_handler(
         log.exception(e)
         queries = [user_message]
 
+    # Check if generated queries are empty
+    if len(queries) == 1 and queries[0].strip() == "":
+        queries = [user_message]
+
+    # Check if queries are not found
     if len(queries) == 0:
         await event_emitter(
             {
@@ -651,7 +656,7 @@ def apply_params_to_form_data(form_data, model):
                     convert_logit_bias_input_to_json(params["logit_bias"])
                 )
             except Exception as e:
-                print(f"Error parsing logit_bias: {e}")
+                log.exception(f"Error parsing logit_bias: {e}")
 
     return form_data
 
@@ -749,9 +754,12 @@ async def process_chat_payload(request, form_data, user, metadata, model):
         raise e
 
     try:
+
         filter_functions = [
             Functions.get_function_by_id(filter_id)
-            for filter_id in get_sorted_filter_ids(model)
+            for filter_id in get_sorted_filter_ids(
+                request, model, metadata.get("filter_ids", [])
+            )
         ]
 
         form_data, flags = await process_filter_functions(
@@ -942,21 +950,35 @@ async def process_chat_response(
         message = message_map.get(metadata["message_id"]) if message_map else None
 
         if message:
-            messages = get_message_list(message_map, message.get("id"))
+            message_list = get_message_list(message_map, message.get("id"))
 
-            # Remove reasoning details and files from the messages.
+            # Remove details tags and files from the messages.
             # as get_message_list creates a new list, it does not affect
             # the original messages outside of this handler
-            for message in messages:
-                message["content"] = re.sub(
-                    r"<details\s+type=\"reasoning\"[^>]*>.*?<\/details>",
-                    "",
-                    message["content"],
-                    flags=re.S,
-                ).strip()
 
-                if message.get("files"):
+            messages = []
-                    message["files"] = []
+            for message in message_list:
+                content = message.get("content", "")
+                if isinstance(content, list):
+                    for item in content:
+                        if item.get("type") == "text":
+                            content = item["text"]
+                            break
+
+                if isinstance(content, str):
+                    content = re.sub(
+                        r"<details\b[^>]*>.*?<\/details>",
+                        "",
+                        content,
+                        flags=re.S | re.I,
+                    ).strip()
+
+                messages.append(
+                    {
+                        "role": message["role"],
+                        "content": content,
+                    }
+                )
 
             if tasks and messages:
                 if TASKS.TITLE_GENERATION in tasks:
@@ -1169,7 +1191,9 @@ async def process_chat_response(
     }
     filter_functions = [
         Functions.get_function_by_id(filter_id)
-        for filter_id in get_sorted_filter_ids(model)
+        for filter_id in get_sorted_filter_ids(
+            request, model, metadata.get("filter_ids", [])
+        )
     ]
 
     # Streaming response

backend/open_webui/utils/models.py

@@ -49,6 +49,7 @@ async def get_all_base_models(request: Request, user: UserModel = None):
                 "created": int(time.time()),
                 "owned_by": "ollama",
                 "ollama": model,
+                "connection_type": model.get("connection_type", "local"),
                 "tags": model.get("tags", []),
             }
             for model in ollama_models["models"]
@@ -110,6 +111,14 @@ async def get_all_models(request, user: UserModel = None):
         for function in Functions.get_functions_by_type("action", active_only=True)
     ]
 
+    global_filter_ids = [
+        function.id for function in Functions.get_global_filter_functions()
+    ]
+    enabled_filter_ids = [
+        function.id
+        for function in Functions.get_functions_by_type("filter", active_only=True)
+    ]
+
     custom_models = Models.get_all_models()
     for custom_model in custom_models:
         if custom_model.base_model_id is None:
@@ -125,13 +134,20 @@ async def get_all_models(request, user: UserModel = None):
                         model["name"] = custom_model.name
                         model["info"] = custom_model.model_dump()
 
+                        # Set action_ids and filter_ids
                         action_ids = []
+                        filter_ids = []
+
                         if "info" in model and "meta" in model["info"]:
                             action_ids.extend(
                                 model["info"]["meta"].get("actionIds", [])
                             )
+                            filter_ids.extend(
+                                model["info"]["meta"].get("filterIds", [])
+                            )
 
                         model["action_ids"] = action_ids
+                        model["filter_ids"] = filter_ids
                     else:
                         models.remove(model)
 
@@ -140,7 +156,9 @@ async def get_all_models(request, user: UserModel = None):
         ):
             owned_by = "openai"
             pipe = None
+
             action_ids = []
+            filter_ids = []
 
             for model in models:
                 if (
@@ -154,9 +172,13 @@ async def get_all_models(request, user: UserModel = None):
 
             if custom_model.meta:
                 meta = custom_model.meta.model_dump()
+
                 if "actionIds" in meta:
                     action_ids.extend(meta["actionIds"])
 
+                if "filterIds" in meta:
+                    filter_ids.extend(meta["filterIds"])
+
             models.append(
                 {
                     "id": f"{custom_model.id}",
@@ -168,6 +190,7 @@ async def get_all_models(request, user: UserModel = None):
                     "preset": True,
                     **({"pipe": pipe} if pipe is not None else {}),
                     "action_ids": action_ids,
+                    "filter_ids": filter_ids,
                 }
             )
 
@@ -181,8 +204,11 @@ async def get_all_models(request, user: UserModel = None):
                     "id": f"{function.id}.{action['id']}",
                     "name": action.get("name", f"{function.name} ({action['id']})"),
                     "description": function.meta.description,
-                    "icon_url": action.get(
+                    "icon": action.get(
-                        "icon_url", function.meta.manifest.get("icon_url", None)
+                        "icon_url",
+                        function.meta.manifest.get("icon_url", None)
+                        or getattr(module, "icon_url", None)
+                        or getattr(module, "icon", None),
                     ),
                 }
                 for action in actions
@@ -193,10 +219,25 @@ async def get_all_models(request, user: UserModel = None):
                     "id": function.id,
                     "name": function.name,
                     "description": function.meta.description,
-                    "icon_url": function.meta.manifest.get("icon_url", None),
+                    "icon": function.meta.manifest.get("icon_url", None)
+                    or getattr(module, "icon_url", None)
+                    or getattr(module, "icon", None),
                 }
             ]
 
+    # Process filter_ids to get the filters
+    def get_filter_items_from_module(function, module):
+        return [
+            {
+                "id": function.id,
+                "name": function.name,
+                "description": function.meta.description,
+                "icon": function.meta.manifest.get("icon_url", None)
+                or getattr(module, "icon_url", None)
+                or getattr(module, "icon", None),
+            }
+        ]
+
     def get_function_module_by_id(function_id):
         if function_id in request.app.state.FUNCTIONS:
             function_module = request.app.state.FUNCTIONS[function_id]
@@ -211,6 +252,11 @@ async def get_all_models(request, user: UserModel = None):
             for action_id in list(set(model.pop("action_ids", []) + global_action_ids))
             if action_id in enabled_action_ids
         ]
+        filter_ids = [
+            filter_id
+            for filter_id in list(set(model.pop("filter_ids", []) + global_filter_ids))
+            if filter_id in enabled_filter_ids
+        ]
 
         model["actions"] = []
         for action_id in action_ids:
@@ -222,6 +268,20 @@ async def get_all_models(request, user: UserModel = None):
             model["actions"].extend(
                 get_action_items_from_module(action_function, function_module)
             )
+
+        model["filters"] = []
+        for filter_id in filter_ids:
+            filter_function = Functions.get_function_by_id(filter_id)
+            if filter_function is None:
+                raise Exception(f"Filter not found: {filter_id}")
+
+            function_module = get_function_module_by_id(filter_id)
+
+            if getattr(function_module, "toggle", None):
+                model["filters"].extend(
+                    get_filter_items_from_module(filter_function, function_module)
+                )
+
     log.debug(f"get_all_models() returned {len(models)} models")
 
     request.app.state.MODELS = {model["id"]: model for model in models}

backend/open_webui/utils/oauth.py

@@ -41,6 +41,7 @@ from open_webui.config import (
 )
 from open_webui.constants import ERROR_MESSAGES, WEBHOOK_MESSAGES
 from open_webui.env import (
+    AIOHTTP_CLIENT_SESSION_SSL,
     WEBUI_NAME,
     WEBUI_AUTH_COOKIE_SAME_SITE,
     WEBUI_AUTH_COOKIE_SECURE,
@@ -305,8 +306,10 @@ class OAuthManager:
                 get_kwargs["headers"] = {
                     "Authorization": f"Bearer {access_token}",
                 }
-            async with aiohttp.ClientSession() as session:
+            async with aiohttp.ClientSession(trust_env=True) as session:
-                async with session.get(picture_url, **get_kwargs) as resp:
+                async with session.get(
+                    picture_url, **get_kwargs, ssl=AIOHTTP_CLIENT_SESSION_SSL
+                ) as resp:
                     if resp.ok:
                         picture = await resp.read()
                         base64_encoded_picture = base64.b64encode(picture).decode(
@@ -371,7 +374,9 @@ class OAuthManager:
                     headers = {"Authorization": f"Bearer {access_token}"}
                     async with aiohttp.ClientSession(trust_env=True) as session:
                         async with session.get(
-                            "https://api.github.com/user/emails", headers=headers
+                            "https://api.github.com/user/emails",
+                            headers=headers,
+                            ssl=AIOHTTP_CLIENT_SESSION_SSL,
                         ) as resp:
                             if resp.ok:
                                 emails = await resp.json()

backend/open_webui/utils/tools.py

@@ -37,6 +37,7 @@ from open_webui.models.tools import Tools
 from open_webui.models.users import UserModel
 from open_webui.utils.plugin import load_tool_module_by_id
 from open_webui.env import (
+    SRC_LOG_LEVELS,
     AIOHTTP_CLIENT_TIMEOUT_TOOL_SERVER_DATA,
     AIOHTTP_CLIENT_SESSION_TOOL_SERVER_SSL,
 )
@@ -44,6 +45,7 @@ from open_webui.env import (
 import copy
 
 log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 
 def get_async_tool_function_and_apply_extra_params(
@@ -477,7 +479,7 @@ async def get_tool_server_data(token: str, url: str) -> Dict[str, Any]:
         "specs": convert_openapi_to_tool_payload(res),
     }
 
-    print("Fetched data:", data)
+    log.info("Fetched data:", data)
     return data
 
 
@@ -510,7 +512,7 @@ async def get_tool_servers_data(
     results = []
     for (idx, server, url, _), response in zip(server_entries, responses):
         if isinstance(response, Exception):
-            print(f"Failed to connect to {url} OpenAPI tool server")
+            log.error(f"Failed to connect to {url} OpenAPI tool server")
             continue
 
         results.append(
@@ -620,5 +622,5 @@ async def execute_tool_server(
 
     except Exception as err:
         error = str(err)
-        print("API Request Error:", error)
+        log.exception("API Request Error:", error)
         return {"error": error}

backend/requirements.txt

@@ -37,7 +37,8 @@ asgiref==3.8.1
 # AI libraries
 openai
 anthropic
-google-generativeai==0.8.4
+google-genai==1.15.0
+google-generativeai==0.8.5
 tiktoken
 
 langchain==0.3.24
@@ -98,7 +99,7 @@ pytube==15.0.0
 
 extract_msg
 pydub
-duckduckgo-search~=8.0.0
+duckduckgo-search==8.0.2
 
 ## Google Drive
 google-api-python-client

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "open-webui",
-	"version": "0.6.8",
+	"version": "0.6.10",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.6.8",
+			"version": "0.6.10",
 			"dependencies": {
 				"@azure/msal-browser": "^4.5.0",
 				"@codemirror/lang-javascript": "^6.2.2",

package.json

@@ -1,11 +1,12 @@
 {
 	"name": "open-webui",
-	"version": "0.6.8",
+	"version": "0.6.10",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
 		"dev:5050": "npm run pyodide:fetch && vite dev --port 5050",
 		"build": "npm run pyodide:fetch && vite build",
+		"build:watch": "npm run pyodide:fetch && vite build --watch",
 		"preview": "vite preview",
 		"check": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json",
 		"check:watch": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json --watch",

pyproject.toml

@@ -45,7 +45,8 @@ dependencies = [
 
     "openai",
     "anthropic",
-    "google-generativeai==0.8.4",
+    "google-genai==1.15.0",
+    "google-generativeai==0.8.5",
     "tiktoken",
 
     "langchain==0.3.24",
@@ -105,7 +106,7 @@ dependencies = [
 
     "extract_msg",
     "pydub",
-    "duckduckgo-search~=8.0.0",
+    "duckduckgo-search==8.0.2",
 
     "google-api-python-client",
     "google-auth-httplib2",

src/app.css

@@ -81,7 +81,7 @@ textarea::placeholder {
 }
 
 .font-primary {
-	font-family: 'Archivo', sans-serif;
+	font-family: 'Archivo', 'Vazirmatn', sans-serif;
 }
 
 .drag-region {
@@ -314,12 +314,20 @@ input[type='number'] {
 .ProseMirror p.is-editor-empty:first-child::before {
 	content: attr(data-placeholder);
 	float: left;
-	color: #adb5bd;
+	/* Below color is from tailwind, and has the proper contrast
+	text-gray-600 from: https://tailwindcss.com/docs/color */
+	color: #676767;
 	pointer-events: none;
 
 	@apply line-clamp-1 absolute;
 }
 
+@media (prefers-color-scheme: dark) {
+	.ProseMirror p.is-editor-empty:first-child::before {
+		color: #757575;
+	}
+}
+
 .ai-autocompletion::after {
 	color: #a0a0a0;
 

src/lib/apis/audio/index.ts

@@ -15,7 +15,7 @@ export const getAudioConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -52,7 +52,7 @@ export const updateAudioConfig = async (token: string, payload: OpenAIConfigForm
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -83,7 +83,7 @@ export const transcribeAudio = async (token: string, file: File) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -120,7 +120,7 @@ export const synthesizeOpenAISpeech = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 
 			return null;
 		});
@@ -152,7 +152,7 @@ export const getModels = async (token: string = ''): Promise<AvailableModelsResp
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 
 			return null;
 		});
@@ -180,7 +180,7 @@ export const getVoices = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 
 			return null;
 		});

src/lib/apis/auths/index.ts

@@ -15,7 +15,7 @@ export const getAdminDetails = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -42,7 +42,7 @@ export const getAdminConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -70,7 +70,7 @@ export const updateAdminConfig = async (token: string, body: object) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -98,7 +98,7 @@ export const getSessionUser = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -129,7 +129,7 @@ export const ldapUserSignIn = async (user: string, password: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 
 			error = err.detail;
 			return null;
@@ -157,7 +157,7 @@ export const getLdapConfig = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -187,7 +187,7 @@ export const updateLdapConfig = async (token: string = '', enable_ldap: boolean)
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -214,7 +214,7 @@ export const getLdapServer = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -242,7 +242,7 @@ export const updateLdapServer = async (token: string = '', body: object) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -273,7 +273,7 @@ export const userSignIn = async (email: string, password: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 
 			error = err.detail;
 			return null;
@@ -312,7 +312,7 @@ export const userSignUp = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -339,7 +339,7 @@ export const userSignOut = async () => {
 			return res;
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -347,6 +347,7 @@ export const userSignOut = async () => {
 	if (error) {
 		throw error;
 	}
+	return res;
 };
 
 export const addUser = async (
@@ -378,7 +379,7 @@ export const addUser = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -409,7 +410,7 @@ export const updateUserProfile = async (token: string, name: string, profileImag
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -440,7 +441,7 @@ export const updateUserPassword = async (token: string, password: string, newPas
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -467,7 +468,7 @@ export const getSignUpEnabledStatus = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -494,7 +495,7 @@ export const getDefaultUserRole = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -524,7 +525,7 @@ export const updateDefaultUserRole = async (token: string, role: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -551,7 +552,7 @@ export const toggleSignUpEnabledStatus = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -578,7 +579,7 @@ export const getJWTExpiresDuration = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -608,7 +609,7 @@ export const updateJWTExpiresDuration = async (token: string, duration: string)
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -635,7 +636,7 @@ export const createAPIKey = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -660,7 +661,7 @@ export const getAPIKey = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -685,7 +686,7 @@ export const deleteAPIKey = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});

src/lib/apis/channels/index.ts

@@ -28,7 +28,7 @@ export const createNewChannel = async (token: string = '', channel: ChannelForm)
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -59,7 +59,7 @@ export const getChannels = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -90,7 +90,7 @@ export const getChannelById = async (token: string = '', channel_id: string) =>
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -126,7 +126,7 @@ export const updateChannelById = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -157,7 +157,7 @@ export const deleteChannelById = async (token: string = '', channel_id: string)
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -196,7 +196,7 @@ export const getChannelMessages = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -236,7 +236,7 @@ export const getChannelThreadMessages = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -275,7 +275,7 @@ export const sendMessage = async (token: string = '', channel_id: string, messag
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -315,7 +315,7 @@ export const updateMessage = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -355,7 +355,7 @@ export const addReaction = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -395,7 +395,7 @@ export const removeReaction = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -429,7 +429,7 @@ export const deleteMessage = async (token: string = '', channel_id: string, mess
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/chats/index.ts

@@ -21,7 +21,7 @@ export const createNewChat = async (token: string, chat: object) => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -61,7 +61,7 @@ export const importChat = async (
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -97,7 +97,7 @@ export const getChatList = async (token: string = '', page: number | null = null
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -131,7 +131,7 @@ export const getChatListByUserId = async (token: string = '', userId: string) =>
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -165,7 +165,7 @@ export const getArchivedChatList = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -196,7 +196,7 @@ export const getAllChats = async (token: string) => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -231,7 +231,7 @@ export const getChatListBySearchText = async (token: string, text: string, page:
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -265,7 +265,7 @@ export const getChatsByFolderId = async (token: string, folderId: string) => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -296,7 +296,7 @@ export const getAllArchivedChats = async (token: string) => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -327,7 +327,7 @@ export const getAllUserChats = async (token: string) => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -358,7 +358,7 @@ export const getAllTags = async (token: string) => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -389,7 +389,7 @@ export const getPinnedChatList = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -426,7 +426,7 @@ export const getChatListByTagName = async (token: string = '', tagName: string)
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -461,7 +461,7 @@ export const getChatById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -493,7 +493,7 @@ export const getChatByShareId = async (token: string, share_id: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -531,7 +531,7 @@ export const getChatPinnedStatusById = async (token: string, id: string) => {
 				error = err;
 			}
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -569,7 +569,7 @@ export const toggleChatPinnedStatusById = async (token: string, id: string) => {
 				error = err;
 			}
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -610,7 +610,7 @@ export const cloneChatById = async (token: string, id: string, title?: string) =
 				error = err;
 			}
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -648,7 +648,7 @@ export const cloneSharedChatById = async (token: string, id: string) => {
 				error = err;
 			}
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -680,7 +680,7 @@ export const shareChatById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -715,7 +715,7 @@ export const updateChatFolderIdById = async (token: string, id: string, folderId
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -747,7 +747,7 @@ export const archiveChatById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -779,7 +779,7 @@ export const deleteSharedChatById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -814,7 +814,7 @@ export const updateChatById = async (token: string, id: string, chat: object) =>
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -846,7 +846,7 @@ export const deleteChatById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -878,7 +878,7 @@ export const getTagsById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -912,7 +912,7 @@ export const addTagById = async (token: string, id: string, tagName: string) =>
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -947,7 +947,7 @@ export const deleteTagById = async (token: string, id: string, tagName: string)
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -978,7 +978,7 @@ export const deleteTagsById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -1010,7 +1010,7 @@ export const deleteAllChats = async (token: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -1042,7 +1042,7 @@ export const archiveAllChats = async (token: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/configs/index.ts

@@ -19,7 +19,7 @@ export const importConfig = async (token: string, config) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -46,7 +46,7 @@ export const exportConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -73,7 +73,7 @@ export const getDirectConnectionsConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -103,7 +103,7 @@ export const setDirectConnectionsConfig = async (token: string, config: object)
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -130,7 +130,7 @@ export const getToolServerConnections = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -160,7 +160,7 @@ export const setToolServerConnections = async (token: string, connections: objec
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -190,7 +190,7 @@ export const verifyToolServerConnection = async (token: string, connection: obje
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -217,7 +217,7 @@ export const getCodeExecutionConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -247,7 +247,7 @@ export const setCodeExecutionConfig = async (token: string, config: object) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -274,7 +274,7 @@ export const getModelsConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -304,7 +304,7 @@ export const setModelsConfig = async (token: string, config: object) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -334,7 +334,7 @@ export const setDefaultPromptSuggestions = async (token: string, promptSuggestio
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -361,7 +361,7 @@ export const getBanners = async (token: string): Promise<Banner[]> => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -391,7 +391,7 @@ export const setBanners = async (token: string, banners: Banner[]) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});

src/lib/apis/evaluations/index.ts

@@ -20,7 +20,7 @@ export const getConfig = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -51,7 +51,7 @@ export const updateConfig = async (token: string, config: object) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -82,7 +82,7 @@ export const getAllFeedbacks = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -113,7 +113,7 @@ export const exportAllFeedbacks = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -144,7 +144,7 @@ export const createNewFeedback = async (token: string, feedback: object) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -175,7 +175,7 @@ export const getFeedbackById = async (token: string, feedbackId: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -206,7 +206,7 @@ export const updateFeedbackById = async (token: string, feedbackId: string, feed
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -234,7 +234,7 @@ export const deleteFeedbackById = async (token: string, feedbackId: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/files/index.ts

@@ -19,7 +19,7 @@ export const uploadFile = async (token: string, file: File) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -76,7 +76,7 @@ export const getFiles = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -107,7 +107,7 @@ export const getFileById = async (token: string, id: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -141,7 +141,7 @@ export const updateFileDataContentById = async (token: string, id: string, conte
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -168,7 +168,7 @@ export const getFileContentById = async (id: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 
 			return null;
 		});
@@ -200,7 +200,7 @@ export const deleteFileById = async (token: string, id: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -231,7 +231,7 @@ export const deleteAllFiles = async (token: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/folders/index.ts

@@ -50,7 +50,7 @@ export const getFolders = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -81,7 +81,7 @@ export const getFolderById = async (token: string, id: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -115,7 +115,7 @@ export const updateFolderNameById = async (token: string, id: string, name: stri
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -153,7 +153,7 @@ export const updateFolderIsExpandedById = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -187,7 +187,7 @@ export const updateFolderParentIdById = async (token: string, id: string, parent
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -226,7 +226,7 @@ export const updateFolderItemsById = async (token: string, id: string, items: Fo
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -257,7 +257,7 @@ export const deleteFolderById = async (token: string, id: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/functions/index.ts

@@ -20,7 +20,7 @@ export const createNewFunction = async (token: string, func: object) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -51,7 +51,7 @@ export const getFunctions = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -82,7 +82,7 @@ export const exportFunctions = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -114,7 +114,7 @@ export const getFunctionById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -149,7 +149,7 @@ export const updateFunctionById = async (token: string, id: string, func: object
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -181,7 +181,7 @@ export const deleteFunctionById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -213,7 +213,7 @@ export const toggleFunctionById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -245,7 +245,7 @@ export const toggleGlobalById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -277,7 +277,7 @@ export const getFunctionValvesById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -309,7 +309,7 @@ export const getFunctionValvesSpecById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -344,7 +344,7 @@ export const updateFunctionValvesById = async (token: string, id: string, valves
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -376,7 +376,7 @@ export const getUserValvesById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -408,7 +408,7 @@ export const getUserValvesSpecById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -443,7 +443,7 @@ export const updateUserValvesById = async (token: string, id: string, valves: ob
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/groups/index.ts

@@ -20,7 +20,7 @@ export const createNewGroup = async (token: string, group: object) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -51,7 +51,7 @@ export const getGroups = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -83,7 +83,7 @@ export const getGroupById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -118,7 +118,7 @@ export const updateGroupById = async (token: string, id: string, group: object)
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -150,7 +150,7 @@ export const deleteGroupById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/images/index.ts

@@ -16,7 +16,7 @@ export const getConfig = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -51,7 +51,7 @@ export const updateConfig = async (token: string = '', config: object) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -83,7 +83,7 @@ export const verifyConfigUrl = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -115,7 +115,7 @@ export const getImageGenerationConfig = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -148,7 +148,7 @@ export const updateImageGenerationConfig = async (token: string = '', config: ob
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -180,7 +180,7 @@ export const getImageGenerationModels = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -215,7 +215,7 @@ export const imageGenerations = async (token: string = '', prompt: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {

src/lib/apis/index.ts

@@ -25,7 +25,7 @@ export const getModels = async (
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -173,7 +173,7 @@ export const chatCompleted = async (token: string, body: ChatCompletedForm) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -212,7 +212,7 @@ export const chatAction = async (token: string, action_id: string, body: ChatAct
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -244,7 +244,7 @@ export const stopTask = async (token: string, id: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -276,7 +276,7 @@ export const getTaskIdsByChatId = async (token: string, chat_id: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -315,7 +315,7 @@ export const getToolServerData = async (token: string, url: string) => {
 			}
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -491,7 +491,7 @@ export const getTaskConfig = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -520,7 +520,7 @@ export const updateTaskConfig = async (token: string, config: object) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -562,7 +562,7 @@ export const generateTitle = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			}
@@ -634,7 +634,7 @@ export const generateTags = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			}
@@ -706,7 +706,7 @@ export const generateEmoji = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			}
@@ -756,7 +756,7 @@ export const generateQueries = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			}
@@ -828,7 +828,7 @@ export const generateAutoCompletion = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			}
@@ -892,7 +892,7 @@ export const generateMoACompletion = async (
 			stream: true
 		})
 	}).catch((err) => {
-		console.log(err);
+		console.error(err);
 		error = err;
 		return null;
 	});
@@ -920,7 +920,7 @@ export const getPipelinesList = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -954,7 +954,7 @@ export const uploadPipeline = async (token: string, file: File, urlIdx: string)
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -990,7 +990,7 @@ export const downloadPipeline = async (token: string, url: string, urlIdx: strin
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -1026,7 +1026,7 @@ export const deletePipeline = async (token: string, id: string, urlIdx: string)
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -1063,7 +1063,7 @@ export const getPipelines = async (token: string, urlIdx?: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1100,7 +1100,7 @@ export const getPipelineValves = async (token: string, pipeline_id: string, urlI
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1136,7 +1136,7 @@ export const getPipelineValvesSpec = async (token: string, pipeline_id: string,
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1178,7 +1178,7 @@ export const updatePipelineValves = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 
 			if ('detail' in err) {
 				error = err.detail;
@@ -1210,7 +1210,7 @@ export const getBackendConfig = async () => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1236,7 +1236,7 @@ export const getChangelog = async () => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1263,7 +1263,7 @@ export const getVersionUpdates = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1290,7 +1290,7 @@ export const getModelFilterConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1325,7 +1325,7 @@ export const updateModelFilterConfig = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1352,7 +1352,7 @@ export const getWebhookUrl = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1382,7 +1382,7 @@ export const updateWebhookUrl = async (token: string, url: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1409,7 +1409,7 @@ export const getCommunitySharingEnabledStatus = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1436,7 +1436,7 @@ export const toggleCommunitySharingEnabledStatus = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -1463,7 +1463,7 @@ export const getModelConfig = async (token: string): Promise<GlobalModelConfig>
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -1511,7 +1511,7 @@ export const updateModelConfig = async (token: string, config: GlobalModelConfig
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});

src/lib/apis/knowledge/index.ts

@@ -27,7 +27,7 @@ export const createNewKnowledge = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -58,7 +58,7 @@ export const getKnowledgeBases = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -89,7 +89,7 @@ export const getKnowledgeBaseList = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -121,7 +121,7 @@ export const getKnowledgeById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -166,7 +166,7 @@ export const updateKnowledgeById = async (token: string, id: string, form: Knowl
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -201,7 +201,7 @@ export const addFileToKnowledgeById = async (token: string, id: string, fileId:
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -236,7 +236,7 @@ export const updateFileFromKnowledgeById = async (token: string, id: string, fil
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -271,7 +271,7 @@ export const removeFileFromKnowledgeById = async (token: string, id: string, fil
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -303,7 +303,7 @@ export const resetKnowledgeById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -335,7 +335,7 @@ export const deleteKnowledgeById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -363,7 +363,7 @@ export const reindexKnowledgeFiles = async (token: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/memories/index.ts

@@ -17,7 +17,7 @@ export const getMemories = async (token: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -48,7 +48,7 @@ export const addNewMemory = async (token: string, content: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -79,7 +79,7 @@ export const updateMemoryById = async (token: string, id: string, content: strin
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -110,7 +110,7 @@ export const queryMemory = async (token: string, content: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -142,7 +142,7 @@ export const deleteMemoryById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -174,7 +174,7 @@ export const deleteMemoriesByUserId = async (token: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/models/index.ts

@@ -20,7 +20,7 @@ export const getModels = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -51,7 +51,7 @@ export const getBaseModels = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -80,7 +80,7 @@ export const createNewModel = async (token: string, model: object) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -115,7 +115,7 @@ export const getModelById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -150,7 +150,7 @@ export const toggleModelById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -186,7 +186,7 @@ export const updateModelById = async (token: string, id: string, model: object)
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -221,7 +221,7 @@ export const deleteModelById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -253,7 +253,7 @@ export const deleteAllModels = async (token: string) => {
 		.catch((err) => {
 			error = err;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/notes/index.ts

@@ -28,7 +28,7 @@ export const createNewNote = async (token: string, note: NoteItem) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -59,7 +59,7 @@ export const getNotes = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -108,7 +108,7 @@ export const getNoteById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -143,7 +143,7 @@ export const updateNoteById = async (token: string, id: string, note: NoteItem)
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -175,7 +175,7 @@ export const deleteNoteById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/ollama/index.ts

@@ -1,10 +1,6 @@
 import { OLLAMA_API_BASE_URL } from '$lib/constants';
 
-export const verifyOllamaConnection = async (
+export const verifyOllamaConnection = async (token: string = '', connection: dict = {}) => {
-	token: string = '',
-	url: string = '',
-	key: string = ''
-) => {
 	let error = null;
 
 	const res = await fetch(`${OLLAMA_API_BASE_URL}/verify`, {
@@ -15,8 +11,7 @@ export const verifyOllamaConnection = async (
 			'Content-Type': 'application/json'
 		},
 		body: JSON.stringify({
-			url,
+			...connection
-			key
 		})
 	})
 		.then(async (res) => {
@@ -51,7 +46,7 @@ export const getOllamaConfig = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -92,7 +87,7 @@ export const updateOllamaConfig = async (token: string = '', config: OllamaConfi
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -124,7 +119,7 @@ export const getOllamaUrls = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -159,7 +154,7 @@ export const updateOllamaUrls = async (token: string = '', urls: string[]) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -191,7 +186,7 @@ export const getOllamaVersion = async (token: string, urlIdx?: number) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -223,7 +218,7 @@ export const getOllamaModels = async (token: string = '', urlIdx: null | number
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -268,7 +263,7 @@ export const generatePrompt = async (token: string = '', model: string, conversa
 			`
 		})
 	}).catch((err) => {
-		console.log(err);
+		console.error(err);
 		if ('detail' in err) {
 			error = err.detail;
 		}
@@ -408,11 +403,11 @@ export const deleteModel = async (token: string, tagName: string, urlIdx: string
 			return res.json();
 		})
 		.then((json) => {
-			console.log(json);
+			console.debug(json);
 			return true;
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 
 			if ('detail' in err) {
@@ -445,7 +440,7 @@ export const pullModel = async (token: string, tagName: string, urlIdx: number |
 			name: tagName
 		})
 	}).catch((err) => {
-		console.log(err);
+		console.error(err);
 		error = err;
 
 		if ('detail' in err) {
@@ -481,7 +476,7 @@ export const downloadModel = async (
 			})
 		}
 	).catch((err) => {
-		console.log(err);
+		console.error(err);
 		error = err;
 
 		if ('detail' in err) {
@@ -512,7 +507,7 @@ export const uploadModel = async (token: string, file: File, urlIdx: string | nu
 			body: formData
 		}
 	).catch((err) => {
-		console.log(err);
+		console.error(err);
 		error = err;
 
 		if ('detail' in err) {

src/lib/apis/openai/index.ts

@@ -16,7 +16,7 @@ export const getOpenAIConfig = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -58,7 +58,7 @@ export const updateOpenAIConfig = async (token: string = '', config: OpenAIConfi
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -90,7 +90,7 @@ export const getOpenAIUrls = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -125,7 +125,7 @@ export const updateOpenAIUrls = async (token: string = '', urls: string[]) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -157,7 +157,7 @@ export const getOpenAIKeys = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -192,7 +192,7 @@ export const updateOpenAIKeys = async (token: string = '', keys: string[]) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			if ('detail' in err) {
 				error = err.detail;
 			} else {
@@ -267,10 +267,10 @@ export const getOpenAIModels = async (token: string, urlIdx?: number) => {
 
 export const verifyOpenAIConnection = async (
 	token: string = '',
-	url: string = 'https://api.openai.com/v1',
+	connection: dict = {},
-	key: string = '',
 	direct: boolean = false
 ) => {
+	const { url, key, config } = connection;
 	if (!url) {
 		throw 'OpenAI: URL is required';
 	}
@@ -309,7 +309,8 @@ export const verifyOpenAIConnection = async (
 			},
 			body: JSON.stringify({
 				url,
-				key
+				key,
+				config
 			})
 		})
 			.then(async (res) => {
@@ -346,7 +347,7 @@ export const chatCompletion = async (
 		},
 		body: JSON.stringify(body)
 	}).catch((err) => {
-		console.log(err);
+		console.error(err);
 		error = err;
 		return null;
 	});
@@ -409,7 +410,7 @@ export const synthesizeOpenAISpeech = async (
 			voice: speaker
 		})
 	}).catch((err) => {
-		console.log(err);
+		console.error(err);
 		error = err;
 		return null;
 	});

src/lib/apis/prompts/index.ts

@@ -28,7 +28,7 @@ export const createNewPrompt = async (token: string, prompt: PromptItem) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -59,7 +59,7 @@ export const getPrompts = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -90,7 +90,7 @@ export const getPromptList = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -122,7 +122,7 @@ export const getPromptByCommand = async (token: string, command: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -158,7 +158,7 @@ export const updatePromptByCommand = async (token: string, prompt: PromptItem) =
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -192,7 +192,7 @@ export const deletePromptByCommand = async (token: string, command: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/retrieval/index.ts

@@ -15,7 +15,7 @@ export const getRAGConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -77,7 +77,7 @@ export const updateRAGConfig = async (token: string, payload: RAGConfigForm) =>
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -104,7 +104,7 @@ export const getQuerySettings = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -140,7 +140,7 @@ export const updateQuerySettings = async (token: string, settings: QuerySettings
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -167,7 +167,7 @@ export const getEmbeddingConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -209,7 +209,7 @@ export const updateEmbeddingConfig = async (token: string, payload: EmbeddingMod
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -236,7 +236,7 @@ export const getRerankingConfig = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -270,7 +270,7 @@ export const updateRerankingConfig = async (token: string, payload: RerankingMod
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -313,7 +313,7 @@ export const processFile = async (
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -344,7 +344,7 @@ export const processYoutubeVideo = async (token: string, url: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -376,7 +376,7 @@ export const processWeb = async (token: string, collection_name: string, url: st
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -410,7 +410,7 @@ export const processWebSearch = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});

src/lib/apis/tools/index.ts

@@ -20,7 +20,7 @@ export const createNewTool = async (token: string, tool: object) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -51,7 +51,7 @@ export const getTools = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -82,7 +82,7 @@ export const getToolList = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -113,7 +113,7 @@ export const exportTools = async (token: string = '') => {
 		})
 		.catch((err) => {
 			error = err.detail;
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -145,7 +145,7 @@ export const getToolById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -180,7 +180,7 @@ export const updateToolById = async (token: string, id: string, tool: object) =>
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -212,7 +212,7 @@ export const deleteToolById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -244,7 +244,7 @@ export const getToolValvesById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -276,7 +276,7 @@ export const getToolValvesSpecById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -311,7 +311,7 @@ export const updateToolValvesById = async (token: string, id: string, valves: ob
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -343,7 +343,7 @@ export const getUserValvesById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -375,7 +375,7 @@ export const getUserValvesSpecById = async (token: string, id: string) => {
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 
@@ -410,7 +410,7 @@ export const updateUserValvesById = async (token: string, id: string, valves: ob
 		.catch((err) => {
 			error = err.detail;
 
-			console.log(err);
+			console.error(err);
 			return null;
 		});
 

src/lib/apis/users/index.ts

@@ -16,7 +16,7 @@ export const getUserGroups = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -43,7 +43,7 @@ export const getUserDefaultPermissions = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -73,7 +73,7 @@ export const updateUserDefaultPermissions = async (token: string, permissions: o
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -104,7 +104,7 @@ export const updateUserRole = async (token: string, id: string, role: string) =>
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -154,7 +154,7 @@ export const getUsers = async (
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -182,7 +182,7 @@ export const getAllUsers = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -208,7 +208,7 @@ export const getUserSettings = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -238,7 +238,7 @@ export const updateUserSettings = async (token: string, settings: object) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -265,7 +265,7 @@ export const getUserById = async (token: string, userId: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -291,7 +291,7 @@ export const getUserInfo = async (token: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -321,7 +321,7 @@ export const updateUserInfo = async (token: string, info: object) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -335,7 +335,7 @@ export const updateUserInfo = async (token: string, info: object) => {
 
 export const getAndUpdateUserLocation = async (token: string) => {
 	const location = await getUserPosition().catch((err) => {
-		console.log(err);
+		console.error(err);
 		return null;
 	});
 
@@ -343,7 +343,7 @@ export const getAndUpdateUserLocation = async (token: string) => {
 		await updateUserInfo(token, { location: location });
 		return location;
 	} else {
-		console.log('Failed to get user location');
+		console.info('Failed to get user location');
 		return null;
 	}
 };
@@ -363,7 +363,7 @@ export const deleteUserById = async (token: string, userId: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -403,7 +403,7 @@ export const updateUserById = async (token: string, userId: string, user: UserUp
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});

src/lib/apis/utils/index.ts

@@ -15,7 +15,7 @@ export const getGravatarUrl = async (token: string, email: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -41,7 +41,7 @@ export const executeCode = async (token: string, code: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 
 			error = err;
 			if (err.detail) {
@@ -75,7 +75,7 @@ export const formatPythonCode = async (token: string, code: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 
 			error = err;
 			if (err.detail) {
@@ -110,7 +110,7 @@ export const downloadChatAsPDF = async (token: string, title: string, messages:
 			return res.blob();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -136,7 +136,7 @@ export const getHTMLFromMarkdown = async (token: string, md: string) => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err;
 			return null;
 		});
@@ -170,7 +170,7 @@ export const downloadDatabase = async (token: string) => {
 			window.URL.revokeObjectURL(url);
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});
@@ -206,7 +206,7 @@ export const downloadLiteLLMConfig = async (token: string) => {
 			window.URL.revokeObjectURL(url);
 		})
 		.catch((err) => {
-			console.log(err);
+			console.error(err);
 			error = err.detail;
 			return null;
 		});

src/lib/components/AddConnectionModal.svelte

@@ -30,8 +30,17 @@
 	let url = '';
 	let key = '';
 
+	let connectionType = 'external';
+	let azure = false;
+	$: azure =
+		(url.includes('azure.com') || url.includes('cognitive.microsoft.com')) && !direct
+			? true
+			: false;
+
 	let prefixId = '';
 	let enable = true;
+	let apiVersion = '';
+
 	let tags = [];
 
 	let modelId = '';
@@ -40,7 +49,10 @@
 	let loading = false;
 
 	const verifyOllamaHandler = async () => {
-		const res = await verifyOllamaConnection(localStorage.token, url, key).catch((error) => {
+		const res = await verifyOllamaConnection(localStorage.token, {
+			url,
+			key
+		}).catch((error) => {
 			toast.error(`${error}`);
 		});
 
@@ -50,11 +62,20 @@
 	};
 
 	const verifyOpenAIHandler = async () => {
-		const res = await verifyOpenAIConnection(localStorage.token, url, key, direct).catch(
+		const res = await verifyOpenAIConnection(
-			(error) => {
+			localStorage.token,
-				toast.error(`${error}`);
+			{
-			}
+				url,
-		);
+				key,
+				config: {
+					azure: azure,
+					api_version: apiVersion
+				}
+			},
+			direct
+		).catch((error) => {
+			toast.error(`${error}`);
+		});
 
 		if (res) {
 			toast.success($i18n.t('Server connection verified'));
@@ -85,6 +106,28 @@
 			return;
 		}
 
+		if (azure) {
+			if (!apiVersion) {
+				loading = false;
+
+				toast.error('API Version is required');
+				return;
+			}
+
+			if (!key) {
+				loading = false;
+
+				toast.error('Key is required');
+				return;
+			}
+
+			if (modelIds.length === 0) {
+				loading = false;
+				toast.error('Deployment names are required');
+				return;
+			}
+		}
+
 		// remove trailing slash from url
 		url = url.replace(/\/$/, '');
 
@@ -95,7 +138,9 @@
 				enable: enable,
 				tags: tags,
 				prefix_id: prefixId,
-				model_ids: modelIds
+				model_ids: modelIds,
+				connection_type: connectionType,
+				...(!ollama && azure ? { azure: true, api_version: apiVersion } : {})
 			}
 		};
 
@@ -120,6 +165,14 @@
 			tags = connection.config?.tags ?? [];
 			prefixId = connection.config?.prefix_id ?? '';
 			modelIds = connection.config?.model_ids ?? [];
+
+			if (ollama) {
+				connectionType = connection.config?.connection_type ?? 'local';
+			} else {
+				connectionType = connection.config?.connection_type ?? 'external';
+				azure = connection.config?.azure ?? false;
+				apiVersion = connection.config?.api_version ?? '';
+			}
 		}
 	};
 
@@ -134,7 +187,7 @@
 
 <Modal size="sm" bind:show>
 	<div>
-		<div class=" flex justify-between dark:text-gray-100 px-5 pt-4 pb-2">
+		<div class=" flex justify-between dark:text-gray-100 px-5 pt-4 pb-1.5">
 			<div class=" text-lg font-medium self-center font-primary">
 				{#if edit}
 					{$i18n.t('Edit Connection')}
@@ -171,7 +224,31 @@
 					}}
 				>
 					<div class="px-1">
-						<div class="flex gap-2">
+						{#if !direct}
+							<div class="flex gap-2">
+								<div class="flex w-full justify-between items-center">
+									<div class=" text-xs text-gray-500">{$i18n.t('Connection Type')}</div>
+
+									<div class="">
+										<button
+											on:click={() => {
+												connectionType = connectionType === 'local' ? 'external' : 'local';
+											}}
+											type="button"
+											class=" text-xs text-gray-700 dark:text-gray-300"
+										>
+											{#if connectionType === 'local'}
+												{$i18n.t('Local')}
+											{:else}
+												{$i18n.t('External')}
+											{/if}
+										</button>
+									</div>
+								</div>
+							</div>
+						{/if}
+
+						<div class="flex gap-2 mt-1.5">
 							<div class="flex flex-col w-full">
 								<div class=" mb-0.5 text-xs text-gray-500">{$i18n.t('URL')}</div>
 
@@ -252,6 +329,25 @@
 							</div>
 						</div>
 
+						{#if azure}
+							<div class="flex gap-2 mt-2">
+								<div class="flex flex-col w-full">
+									<div class=" mb-1 text-xs text-gray-500">{$i18n.t('API Version')}</div>
+
+									<div class="flex-1">
+										<input
+											class="w-full text-sm bg-transparent placeholder:text-gray-300 dark:placeholder:text-gray-700 outline-hidden"
+											type="text"
+											bind:value={apiVersion}
+											placeholder={$i18n.t('API Version')}
+											autocomplete="off"
+											required
+										/>
+									</div>
+								</div>
+							</div>
+						{/if}
+
 						<div class="flex gap-2 mt-2">
 							<div class="flex flex-col w-full">
 								<div class=" mb-1.5 text-xs text-gray-500">{$i18n.t('Tags')}</div>
@@ -308,6 +404,11 @@
 										{$i18n.t('Leave empty to include all models from "{{url}}/api/tags" endpoint', {
 											url: url
 										})}
+									{:else if azure}
+										{$i18n.t('Deployment names are required for Azure OpenAI')}
+										<!-- {$i18n.t('Leave empty to include all models from "{{url}}" endpoint', {
+											url: `${url}/openai/deployments`
+										})} -->
 									{:else}
 										{$i18n.t('Leave empty to include all models from "{{url}}/models" endpoint', {
 											url: url
@@ -317,7 +418,7 @@
 							{/if}
 						</div>
 
-						<hr class=" border-gray-100 dark:border-gray-700/10 my-2.5 w-full" />
+						<hr class=" border-gray-100 dark:border-gray-700/10 my-1.5 w-full" />
 
 						<div class="flex items-center">
 							<input

src/lib/components/AddServerModal.svelte

@@ -3,10 +3,6 @@
 	import { getContext, onMount } from 'svelte';
 	const i18n = getContext('i18n');
 
-	import { models } from '$lib/stores';
-	import { verifyOpenAIConnection } from '$lib/apis/openai';
-	import { verifyOllamaConnection } from '$lib/apis/ollama';
-
 	import Modal from '$lib/components/common/Modal.svelte';
 	import Plus from '$lib/components/icons/Plus.svelte';
 	import Minus from '$lib/components/icons/Minus.svelte';

src/lib/components/admin/Functions.svelte

@@ -447,7 +447,9 @@
 					}
 				}}
 			>
-				<div class=" self-center mr-2 font-medium line-clamp-1">{$i18n.t('Export Functions')}</div>
+				<div class=" self-center mr-2 font-medium line-clamp-1">
+					{$i18n.t('Export Functions')} ({$functions.length})
+				</div>
 
 				<div class=" self-center">
 					<svg

src/lib/components/admin/Functions/FunctionEditor.svelte

@@ -277,7 +277,7 @@ class Pipe:
 			await tick();
 
 			if (res) {
-				console.log('Code formatted successfully');
+				console.info('Code formatted successfully');
 
 				saveHandler();
 			}

src/lib/components/admin/Settings/Connections/OpenAIConnection.svelte

@@ -62,7 +62,7 @@
 				class="absolute top-0 bottom-0 left-0 right-0 opacity-60 bg-white dark:bg-gray-900 z-10"
 			></div>
 		{/if}
-		<div class="flex w-full">
+		<div class="flex w-full gap-2">
 			<div class="flex-1 relative">
 				<input
 					class=" outline-hidden w-full bg-transparent {pipeline ? 'pr-8' : ''}"

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

@@ -91,7 +91,7 @@
 			return;
 		}
 
-		console.log('Update embedding model attempt:', embeddingModel);
+		console.debug('Update embedding model attempt:', embeddingModel);
 
 		updateEmbeddingModelLoading = true;
 		const res = await updateEmbeddingConfig(localStorage.token, {
@@ -114,7 +114,7 @@
 		updateEmbeddingModelLoading = false;
 
 		if (res) {
-			console.log('embeddingModelUpdateHandler:', res);
+			console.debug('embeddingModelUpdateHandler:', res);
 			if (res.status === true) {
 				toast.success($i18n.t('Embedding model set to "{{embedding_model}}"', res), {
 					duration: 1000 * 10
@@ -124,6 +124,13 @@
 	};
 
 	const submitHandler = async () => {
+		if (
+			RAGConfig.CONTENT_EXTRACTION_ENGINE === 'external' &&
+			RAGConfig.EXTERNAL_DOCUMENT_LOADER_URL === ''
+		) {
+			toast.error($i18n.t('External Document Loader URL required.'));
+			return;
+		}
 		if (RAGConfig.CONTENT_EXTRACTION_ENGINE === 'tika' && RAGConfig.TIKA_SERVER_URL === '') {
 			toast.error($i18n.t('Tika Server URL required.'));
 			return;
@@ -163,6 +170,10 @@
 			await embeddingModelUpdateHandler();
 		}
 
+		RAGConfig.ALLOWED_FILE_EXTENSIONS = RAGConfig.ALLOWED_FILE_EXTENSIONS.split(',')
+			.map((ext) => ext.trim())
+			.filter((ext) => ext !== '');
+
 		const res = await updateRAGConfig(localStorage.token, RAGConfig);
 		dispatch('save');
 	};
@@ -185,7 +196,10 @@
 	onMount(async () => {
 		await setEmbeddingConfig();
 
-		RAGConfig = await getRAGConfig(localStorage.token);
+		const config = await getRAGConfig(localStorage.token);
+		config.ALLOWED_FILE_EXTENSIONS = (config?.ALLOWED_FILE_EXTENSIONS ?? []).join(', ');
+
+		RAGConfig = config;
 	});
 </script>
 
@@ -246,7 +260,7 @@
 					<hr class=" border-gray-100 dark:border-gray-850 my-2" />
 
 					<div class="mb-2.5 flex flex-col w-full justify-between">
-						<div class="flex w-full justify-between">
+						<div class="flex w-full justify-between mb-1">
 							<div class="self-center text-xs font-medium">
 								{$i18n.t('Content Extraction Engine')}
 							</div>
@@ -256,6 +270,7 @@
 									bind:value={RAGConfig.CONTENT_EXTRACTION_ENGINE}
 								>
 									<option value="">{$i18n.t('Default')}</option>
+									<option value="external">{$i18n.t('External')}</option>
 									<option value="tika">{$i18n.t('Tika')}</option>
 									<option value="docling">{$i18n.t('Docling')}</option>
 									<option value="document_intelligence">{$i18n.t('Document Intelligence')}</option>
@@ -275,11 +290,24 @@
 									</div>
 								</div>
 							</div>
+						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'external'}
+							<div class="my-0.5 flex gap-2 pr-2">
+								<input
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
+									placeholder={$i18n.t('Enter External Document Loader URL')}
+									bind:value={RAGConfig.EXTERNAL_DOCUMENT_LOADER_URL}
+								/>
+								<SensitiveInput
+									placeholder={$i18n.t('Enter External Document Loader API Key')}
+									required={false}
+									bind:value={RAGConfig.EXTERNAL_DOCUMENT_LOADER_API_KEY}
+								/>
+							</div>
 						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'tika'}
 							<div class="flex w-full mt-1">
 								<div class="flex-1 mr-2">
 									<input
-										class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+										class="flex-1 w-full text-sm bg-transparent outline-hidden"
 										placeholder={$i18n.t('Enter Tika Server URL')}
 										bind:value={RAGConfig.TIKA_SERVER_URL}
 									/>
@@ -288,27 +316,38 @@
 						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'docling'}
 							<div class="flex w-full mt-1">
 								<input
-									class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
 									placeholder={$i18n.t('Enter Docling Server URL')}
 									bind:value={RAGConfig.DOCLING_SERVER_URL}
 								/>
 							</div>
 							<div class="flex w-full mt-2">
 								<input
-									class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
 									placeholder={$i18n.t('Enter Docling OCR Engine')}
 									bind:value={RAGConfig.DOCLING_OCR_ENGINE}
 								/>
 								<input
-									class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
 									placeholder={$i18n.t('Enter Docling OCR Language(s)')}
 									bind:value={RAGConfig.DOCLING_OCR_LANG}
 								/>
 							</div>
+
+							<div class="flex w-full mt-2">
+								<div class="flex-1 flex justify-between">
+									<div class=" self-center text-xs font-medium">
+										{$i18n.t('Describe Pictures in Documents')}
+									</div>
+									<div class="flex items-center relative">
+										<Switch bind:state={RAGConfig.DOCLING_DO_PICTURE_DESCRIPTION} />
+									</div>
+								</div>
+							</div>
 						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'document_intelligence'}
 							<div class="my-0.5 flex gap-2 pr-2">
 								<input
-									class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
 									placeholder={$i18n.t('Enter Document Intelligence Endpoint')}
 									bind:value={RAGConfig.DOCUMENT_INTELLIGENCE_ENDPOINT}
 								/>
@@ -437,7 +476,7 @@
 							{#if embeddingEngine === 'openai'}
 								<div class="my-0.5 flex gap-2 pr-2">
 									<input
-										class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+										class="flex-1 w-full text-sm bg-transparent outline-hidden"
 										placeholder={$i18n.t('API Base URL')}
 										bind:value={OpenAIUrl}
 										required
@@ -448,7 +487,7 @@
 							{:else if embeddingEngine === 'ollama'}
 								<div class="my-0.5 flex gap-2 pr-2">
 									<input
-										class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+										class="flex-1 w-full text-sm bg-transparent outline-hidden"
 										placeholder={$i18n.t('API Base URL')}
 										bind:value={OllamaUrl}
 										required
@@ -471,7 +510,7 @@
 									<div class="flex w-full">
 										<div class="flex-1 mr-2">
 											<input
-												class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+												class="flex-1 w-full text-sm bg-transparent outline-hidden"
 												bind:value={embeddingModel}
 												placeholder={$i18n.t('Set embedding model')}
 												required
@@ -482,7 +521,7 @@
 									<div class="flex w-full">
 										<div class="flex-1 mr-2">
 											<input
-												class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+												class="flex-1 w-full text-sm bg-transparent outline-hidden"
 												placeholder={$i18n.t('Set embedding model (e.g. {{model}})', {
 													model: embeddingModel.slice(-40)
 												})}
@@ -639,7 +678,7 @@
 									{#if RAGConfig.RAG_RERANKING_ENGINE === 'external'}
 										<div class="my-0.5 flex gap-2 pr-2">
 											<input
-												class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+												class="flex-1 w-full text-sm bg-transparent outline-hidden"
 												placeholder={$i18n.t('API Base URL')}
 												bind:value={RAGConfig.RAG_EXTERNAL_RERANKER_URL}
 												required
@@ -661,7 +700,7 @@
 										<div class="flex w-full">
 											<div class="flex-1 mr-2">
 												<input
-													class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+													class="flex-1 w-full text-sm bg-transparent outline-hidden"
 													placeholder={$i18n.t('Set reranking model (e.g. {{model}})', {
 														model: 'BAAI/bge-reranker-v2-m3'
 													})}
@@ -677,7 +716,7 @@
 								<div class=" self-center text-xs font-medium">{$i18n.t('Top K')}</div>
 								<div class="flex items-center relative">
 									<input
-										class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+										class="flex-1 w-full text-sm bg-transparent outline-hidden"
 										type="number"
 										placeholder={$i18n.t('Enter Top K')}
 										bind:value={RAGConfig.TOP_K}
@@ -692,7 +731,7 @@
 									<div class="self-center text-xs font-medium">{$i18n.t('Top K Reranker')}</div>
 									<div class="flex items-center relative">
 										<input
-											class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+											class="flex-1 w-full text-sm bg-transparent outline-hidden"
 											type="number"
 											placeholder={$i18n.t('Enter Top K Reranker')}
 											bind:value={RAGConfig.TOP_K_RERANKER}
@@ -711,7 +750,7 @@
 										</div>
 										<div class="flex items-center relative">
 											<input
-												class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+												class="flex-1 w-full text-sm bg-transparent outline-hidden"
 												type="number"
 												step="0.01"
 												placeholder={$i18n.t('Enter Score')}
@@ -760,6 +799,26 @@
 
 					<hr class=" border-gray-100 dark:border-gray-850 my-2" />
 
+					<div class="  mb-2.5 flex w-full justify-between">
+						<div class=" self-center text-xs font-medium">{$i18n.t('Allowed File Extensions')}</div>
+						<div class="flex items-center relative">
+							<Tooltip
+								content={$i18n.t(
+									'Allowed file extensions for upload. Separate multiple extensions with commas. Leave empty for all file types.'
+								)}
+								placement="top-start"
+							>
+								<input
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
+									type="text"
+									placeholder={$i18n.t('e.g. pdf, docx, txt')}
+									bind:value={RAGConfig.ALLOWED_FILE_EXTENSIONS}
+									autocomplete="off"
+								/>
+							</Tooltip>
+						</div>
+					</div>
+
 					<div class="  mb-2.5 flex w-full justify-between">
 						<div class=" self-center text-xs font-medium">{$i18n.t('Max Upload Size')}</div>
 						<div class="flex items-center relative">
@@ -770,7 +829,7 @@
 								placement="top-start"
 							>
 								<input
-									class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
 									type="number"
 									placeholder={$i18n.t('Leave empty for unlimited')}
 									bind:value={RAGConfig.FILE_MAX_SIZE}
@@ -791,7 +850,7 @@
 								placement="top-start"
 							>
 								<input
-									class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
 									type="number"
 									placeholder={$i18n.t('Leave empty for unlimited')}
 									bind:value={RAGConfig.FILE_MAX_COUNT}

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

@@ -18,6 +18,7 @@
 	import { compareVersion } from '$lib/utils';
 	import { onMount, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';
+	import Textarea from '$lib/components/common/Textarea.svelte';
 
 	const i18n = getContext('i18n');
 
@@ -58,10 +59,10 @@
 			};
 		});
 
-		console.log(version);
+		console.info(version);
 
 		updateAvailable = compareVersion(version.latest, version.current);
-		console.log(updateAvailable);
+		console.info(updateAvailable);
 	};
 
 	const updateLdapServerHandler = async () => {
@@ -305,6 +306,31 @@
 						<Switch bind:state={adminConfig.SHOW_ADMIN_DETAILS} />
 					</div>
 
+					<div class="mb-2.5">
+						<div class=" self-center text-xs font-medium mb-2">
+							{$i18n.t('Pending User Overlay Title')}
+						</div>
+						<Textarea
+							rows={2}
+							placeholder={$i18n.t(
+								'Enter a title for the pending user info overlay. Leave empty for default.'
+							)}
+							bind:value={adminConfig.PENDING_USER_OVERLAY_TITLE}
+						/>
+					</div>
+
+					<div class="mb-2.5">
+						<div class=" self-center text-xs font-medium mb-2">
+							{$i18n.t('Pending User Overlay Content')}
+						</div>
+						<Textarea
+							placeholder={$i18n.t(
+								'Enter content for the pending user info overlay. Leave empty for default.'
+							)}
+							bind:value={adminConfig.PENDING_USER_OVERLAY_CONTENT}
+						/>
+					</div>
+
 					<div class="mb-2.5 flex w-full justify-between pr-2">
 						<div class=" self-center text-xs font-medium">{$i18n.t('Enable API Key')}</div>
 
@@ -559,6 +585,13 @@
 													/>
 												</div>
 											</div>
+											<div class="flex justify-between items-center text-xs">
+												<div class=" font-medium">Validate certificate</div>
+
+												<div class="mt-1">
+													<Switch bind:state={LDAP_SERVER.validate_cert} />
+												</div>
+											</div>
 											<div class="flex w-full gap-2">
 												<div class="w-full">
 													<div class=" self-center text-xs font-medium min-w-fit mb-1">
@@ -625,6 +658,16 @@
 						<Switch bind:state={adminConfig.ENABLE_USER_WEBHOOKS} />
 					</div>
 
+					<div class="mb-2.5">
+						<div class=" self-center text-xs font-medium mb-2">
+							{$i18n.t('Response Watermark')}
+						</div>
+						<Textarea
+							placeholder={$i18n.t('Enter a watermark for the response. Leave empty for none.')}
+							bind:value={adminConfig.RESPONSE_WATERMARK}
+						/>
+					</div>
+
 					<div class="mb-2.5 w-full justify-between">
 						<div class="flex w-full justify-between">
 							<div class=" self-center text-xs font-medium">{$i18n.t('WebUI URL')}</div>

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

@@ -198,14 +198,14 @@
 						2
 					);
 				} catch (e) {
-					console.log(e);
+					console.error(e);
 				}
 			}
 
 			requiredWorkflowNodes = requiredWorkflowNodes.map((node) => {
 				const n = config.comfyui.COMFYUI_WORKFLOW_NODES.find((n) => n.type === node.type) ?? node;
 
-				console.log(n);
+				console.debug(n);
 
 				return {
 					type: n.type,

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

@@ -2,9 +2,9 @@
 	import { v4 as uuidv4 } from 'uuid';
 	import { toast } from 'svelte-sonner';
 
-	import { getBackendConfig, getTaskConfig, updateTaskConfig } from '$lib/apis';
+	import { getBackendConfig, getModels, getTaskConfig, updateTaskConfig } from '$lib/apis';
 	import { setDefaultPromptSuggestions } from '$lib/apis/configs';
-	import { config, models, settings, user } from '$lib/stores';
+	import { config, settings, user } from '$lib/stores';
 	import { createEventDispatcher, onMount, getContext } from 'svelte';
 
 	import { banners as _banners } from '$lib/stores';
@@ -15,6 +15,8 @@
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
 	import Switch from '$lib/components/common/Switch.svelte';
 	import Textarea from '$lib/components/common/Textarea.svelte';
+	import Spinner from '$lib/components/common/Spinner.svelte';
+	import { getBaseModels } from '$lib/apis/models';
 
 	const dispatch = createEventDispatcher();
 
@@ -49,6 +51,7 @@
 	};
 
 	onMount(async () => {
+		await init();
 		taskConfig = await getTaskConfig(localStorage.token);
 
 		promptSuggestions = $config?.default_prompt_suggestions ?? [];
@@ -58,9 +61,40 @@
 	const updateBanners = async () => {
 		_banners.set(await setBanners(localStorage.token, banners));
 	};
+
+	let workspaceModels = null;
+	let baseModels = null;
+
+	let models = null;
+
+	const init = async () => {
+		workspaceModels = await getBaseModels(localStorage.token);
+		baseModels = await getModels(localStorage.token, null, false);
+
+		models = baseModels.map((m) => {
+			const workspaceModel = workspaceModels.find((wm) => wm.id === m.id);
+
+			if (workspaceModel) {
+				return {
+					...m,
+					...workspaceModel
+				};
+			} else {
+				return {
+					...m,
+					id: m.id,
+					name: m.name,
+
+					is_active: true
+				};
+			}
+		});
+
+		console.debug('models', models);
+	};
 </script>
 
-{#if taskConfig}
+{#if models !== null && taskConfig}
 	<form
 		class="flex flex-col h-full justify-between space-y-3 text-sm"
 		on:submit|preventDefault={() => {
@@ -74,8 +108,8 @@
 
 				<hr class=" border-gray-100 dark:border-gray-850 my-2" />
 
-				<div class=" mb-1 font-medium flex items-center">
+				<div class=" mb-2 font-medium flex items-center">
-					<div class=" text-xs mr-1">{$i18n.t('Set Task Model')}</div>
+					<div class=" text-xs mr-1">{$i18n.t('Task Model')}</div>
 					<Tooltip
 						content={$i18n.t(
 							'A task model is used when performing tasks such as generating titles for chats and web search queries'
@@ -100,32 +134,70 @@
 
 				<div class=" mb-2.5 flex w-full gap-2">
 					<div class="flex-1">
-						<div class=" text-xs mb-1">{$i18n.t('Local Models')}</div>
+						<div class=" text-xs mb-1">{$i18n.t('Local Task Model')}</div>
 						<select
 							class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
 							bind:value={taskConfig.TASK_MODEL}
 							placeholder={$i18n.t('Select a model')}
+							on:change={() => {
+								if (taskConfig.TASK_MODEL) {
+									const model = models.find((m) => m.id === taskConfig.TASK_MODEL);
+									if (model) {
+										if (model?.access_control !== null) {
+											toast.error(
+												$i18n.t(
+													'This model is not publicly available. Please select another model.'
+												)
+											);
+										}
+
+										taskConfig.TASK_MODEL = model.id;
+									} else {
+										taskConfig.TASK_MODEL = '';
+									}
+								}
+							}}
 						>
 							<option value="" selected>{$i18n.t('Current Model')}</option>
-							{#each $models.filter((m) => m.owned_by === 'ollama') as model}
+							{#each models as model}
 								<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
 									{model.name}
+									{model?.connection_type === 'local' ? `(${$i18n.t('Local')})` : ''}
 								</option>
 							{/each}
 						</select>
 					</div>
 
 					<div class="flex-1">
-						<div class=" text-xs mb-1">{$i18n.t('External Models')}</div>
+						<div class=" text-xs mb-1">{$i18n.t('External Task Model')}</div>
 						<select
 							class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
 							bind:value={taskConfig.TASK_MODEL_EXTERNAL}
 							placeholder={$i18n.t('Select a model')}
+							on:change={() => {
+								if (taskConfig.TASK_MODEL_EXTERNAL) {
+									const model = models.find((m) => m.id === taskConfig.TASK_MODEL_EXTERNAL);
+									if (model) {
+										if (model?.access_control !== null) {
+											toast.error(
+												$i18n.t(
+													'This model is not publicly available. Please select another model.'
+												)
+											);
+										}
+
+										taskConfig.TASK_MODEL_EXTERNAL = model.id;
+									} else {
+										taskConfig.TASK_MODEL_EXTERNAL = '';
+									}
+								}
+							}}
 						>
 							<option value="" selected>{$i18n.t('Current Model')}</option>
-							{#each $models as model}
+							{#each models as model}
 								<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
 									{model.name}
+									{model?.connection_type === 'local' ? `(${$i18n.t('Local')})` : ''}
 								</option>
 							{/each}
 						</select>
@@ -480,4 +552,8 @@
 			</button>
 		</div>
 	</form>
+{:else}
+	<div class=" h-full w-full flex justify-center items-center">
+		<Spinner />
+	</div>
 {/if}

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

@@ -166,7 +166,7 @@
 			hidden: !(model?.meta?.hidden ?? false)
 		};
 
-		console.log(model);
+		console.debug(model);
 
 		toast.success(
 			model.meta.hidden
@@ -495,7 +495,7 @@
 						}}
 					>
 						<div class=" self-center mr-2 font-medium line-clamp-1">
-							{$i18n.t('Export Presets')}
+							{$i18n.t('Export Presets')} ({models.length})
 						</div>
 
 						<div class=" self-center">

src/lib/components/admin/Settings/Models/Manage/ManageOllama.svelte

@@ -66,7 +66,7 @@
 
 	const updateModelsHandler = async () => {
 		for (const model of ollamaModels) {
-			console.log(model);
+			console.debug(model);
 
 			updateModelId = model.id;
 			const [res, controller] = await pullModel(localStorage.token, model.id, urlIdx).catch(
@@ -114,8 +114,8 @@
 								}
 							}
 						}
-					} catch (error) {
+					} catch (err) {
-						console.log(error);
+						console.error(err);
 					}
 				}
 			}
@@ -215,13 +215,13 @@
 							}
 						}
 					}
-				} catch (error) {
+				} catch (err) {
-					console.log(error);
+					console.error(err);
-					if (typeof error !== 'string') {
+					if (typeof err !== 'string') {
-						error = error.message;
+						err = err.message;
 					}
 
-					toast.error(`${error}`);
+					toast.error(`${err}`);
 					// opts.callback({ success: false, error, modelName: opts.modelName });
 				}
 			}
@@ -319,8 +319,8 @@
 							}
 						}
 					}
-				} catch (error) {
+				} catch (err) {
-					console.log(error);
+					console.error(err);
 				}
 			}
 		} else {
@@ -382,9 +382,9 @@
 								}
 							}
 						}
-					} catch (error) {
+					} catch (err) {
-						console.log(error);
+						console.error(err);
-						toast.error(`${error}`);
+						toast.error(`${err}`);
 					}
 				}
 			}
@@ -514,9 +514,9 @@
 							}
 						}
 					}
-				} catch (error) {
+				} catch (err) {
-					console.log(error);
+					console.error(err);
-					toast.error(`${error}`);
+					toast.error(`${err}`);
 				}
 			}
 		}

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

@@ -104,7 +104,7 @@
 		valves_spec = null;
 
 		if (PIPELINES_LIST.length > 0) {
-			console.log(selectedPipelinesUrlIdx);
+			console.debug(selectedPipelinesUrlIdx);
 			pipelines = await getPipelines(localStorage.token, selectedPipelinesUrlIdx);
 
 			if (pipelines.length > 0) {
@@ -151,7 +151,7 @@
 
 			const res = await uploadPipeline(localStorage.token, file, selectedPipelinesUrlIdx).catch(
 				(error) => {
-					console.log(error);
+					console.error(error);
 					toast.error('Something went wrong :/');
 					return null;
 				}

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

@@ -106,7 +106,7 @@
 	};
 
 	const updateDefaultPermissionsHandler = async (group) => {
-		console.log(group.permissions);
+		console.debug(group.permissions);
 
 		const res = await updateUserDefaultPermissions(localStorage.token, group.permissions).catch(
 			(error) => {

src/lib/components/admin/Users/Groups/AddGroupModal.svelte

@@ -31,10 +31,6 @@
 		description = '';
 		userIds = [];
 	};
-
-	onMount(() => {
-		console.log('mounted');
-	});
 </script>
 
 <Modal size="sm" bind:show>

src/lib/components/admin/Users/Groups/EditGroupModal.svelte

@@ -91,7 +91,6 @@
 	}
 
 	onMount(() => {
-		console.log(tabs);
 		selectedTab = tabs[0];
 		init();
 	});

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

@@ -167,7 +167,7 @@
 />
 <UserChatsModal bind:show={showUserChatsModal} user={selectedUser} />
 
-{#if ($config?.license_metadata?.seats ?? null) !== null && users.length > $config?.license_metadata?.seats}
+{#if ($config?.license_metadata?.seats ?? null) !== null && total && total > $config?.license_metadata?.seats}
 	<div class=" mt-1 mb-2 text-xs text-red-500">
 		<Banner
 			className="mx-0"

src/lib/components/admin/Users/UserList/AddUserModal.svelte

@@ -73,7 +73,7 @@
 
 					for (const [idx, row] of rows.entries()) {
 						const columns = row.split(',').map((col) => col.trim());
-						console.log(idx, columns);
+						console.debug(idx, columns);
 
 						if (idx > 0) {
 							if (

src/lib/components/channel/MessageInput.svelte

@@ -80,7 +80,7 @@
 
 	const inputFilesHandler = async (inputFiles) => {
 		inputFiles.forEach((file) => {
-			console.log('Processing file:', {
+			console.info('Processing file:', {
 				name: file.name,
 				type: file.type,
 				size: file.size,
@@ -91,7 +91,7 @@
 				($config?.file?.max_size ?? null) !== null &&
 				file.size > ($config?.file?.max_size ?? 0) * 1024 * 1024
 			) {
-				console.log('File exceeds max size limit:', {
+				console.error('File exceeds max size limit:', {
 					fileSize: file.size,
 					maxSize: ($config?.file?.max_size ?? 0) * 1024 * 1024
 				});
@@ -163,14 +163,14 @@
 			const uploadedFile = await uploadFile(localStorage.token, file);
 
 			if (uploadedFile) {
-				console.log('File upload completed:', {
+				console.info('File upload completed:', {
 					id: uploadedFile.id,
 					name: fileItem.name,
 					collection: uploadedFile?.meta?.collection_name
 				});
 
 				if (uploadedFile.error) {
-					console.warn('File upload warning:', uploadedFile.error);
+					console.error('File upload warning:', uploadedFile.error);
 					toast.warning(uploadedFile.error);
 				}
 
@@ -193,7 +193,6 @@
 
 	const handleKeyDown = (event: KeyboardEvent) => {
 		if (event.key === 'Escape') {
-			console.log('Escape');
 			draggedOver = false;
 		}
 	};
@@ -215,7 +214,6 @@
 
 	const onDrop = async (e) => {
 		e.preventDefault();
-		console.log(e);
 
 		if (e.dataTransfer?.files) {
 			const inputFiles = Array.from(e.dataTransfer?.files);
@@ -270,7 +268,6 @@
 	});
 
 	onDestroy(() => {
-		console.log('destroy');
 		window.removeEventListener('keydown', handleKeyDown);
 
 		const dropzoneElement = document.getElementById('channel-container');
@@ -479,12 +476,12 @@
 										}
 
 										if (e.key === 'Escape') {
-											console.log('Escape');
+											console.info('Escape');
 										}
 									}}
 									on:paste={async (e) => {
 										e = e.detail.event;
-										console.log(e);
+										console.info(e);
 									}}
 								/>
 							</div>

src/lib/components/channel/Messages.svelte

@@ -51,7 +51,7 @@
 		{#if !top}
 			<Loader
 				on:visible={(e) => {
-					console.log('visible');
+					console.info('visible');
 					if (!messagesLoading) {
 						loadMoreMessages();
 					}

src/lib/components/channel/Thread.svelte

@@ -54,7 +54,7 @@
 	};
 
 	const channelEventHandler = async (event) => {
-		console.log(event);
+		console.debug(event);
 		if (event.channel_id === channel.id) {
 			const type = event?.data?.type ?? null;
 			const data = event?.data?.data ?? null;

src/lib/components/chat/Artifacts.svelte

@@ -4,13 +4,15 @@
 	const i18n = getContext('i18n');
 	const dispatch = createEventDispatcher();
 
-	import { chatId, settings, showArtifacts, showControls } from '$lib/stores';
+	import { artifactCode, chatId, settings, showArtifacts, showControls } from '$lib/stores';
-	import XMark from '../icons/XMark.svelte';
 	import { copyToClipboard, createMessagesList } from '$lib/utils';
+
+	import XMark from '../icons/XMark.svelte';
 	import ArrowsPointingOut from '../icons/ArrowsPointingOut.svelte';
 	import Tooltip from '../common/Tooltip.svelte';
 	import SvgPanZoom from '../common/SVGPanZoom.svelte';
 	import ArrowLeft from '../icons/ArrowLeft.svelte';
+	import ArrowDownTray from '../icons/ArrowDownTray.svelte';
 
 	export let overlay = false;
 	export let history;
@@ -154,7 +156,7 @@
 							url.pathname + url.search + url.hash
 						);
 					} else {
-						console.log('External navigation blocked:', url.href);
+						console.info('External navigation blocked:', url.href);
 					}
 				}
 			},
@@ -180,7 +182,26 @@
 		}
 	};
 
-	onMount(() => {});
+	const downloadArtifact = () => {
+		const blob = new Blob([contents[selectedContentIdx].content], { type: 'text/html' });
+		const url = URL.createObjectURL(blob);
+		const a = document.createElement('a');
+		a.href = url;
+		a.download = `artifact-${$chatId}-${selectedContentIdx}.html`;
+		document.body.appendChild(a);
+		a.click();
+		document.body.removeChild(a);
+		URL.revokeObjectURL(url);
+	};
+
+	onMount(() => {
+		artifactCode.subscribe((value) => {
+			if (contents) {
+				const codeIdx = contents.findIndex((content) => content.content.includes(value));
+				selectedContentIdx = codeIdx !== -1 ? codeIdx : 0;
+			}
+		});
+	});
 </script>
 
 <div class=" w-full h-full relative flex flex-col bg-gray-50 dark:bg-gray-850">
@@ -198,7 +219,7 @@
 					<ArrowLeft className="size-3.5  text-gray-900 dark:text-white" />
 				</button>
 
-				<div class="flex-1 flex items-center justify-between">
+				<div class="flex-1 flex items-center justify-between pr-1">
 					<div class="flex items-center space-x-2">
 						<div class="flex items-center gap-0.5 self-center min-w-fit" dir="ltr">
 							<button
@@ -252,7 +273,7 @@
 						</div>
 					</div>
 
-					<div class="flex items-center gap-1">
+					<div class="flex items-center gap-1.5">
 						<button
 							class="copy-code-button bg-none border-none text-xs bg-gray-50 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition rounded-md px-1.5 py-0.5"
 							on:click={() => {
@@ -265,6 +286,15 @@
 							}}>{copied ? $i18n.t('Copied') : $i18n.t('Copy')}</button
 						>
 
+						<Tooltip content={$i18n.t('Download')}>
+							<button
+								class=" bg-none border-none text-xs bg-gray-50 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition rounded-md p-0.5"
+								on:click={downloadArtifact}
+							>
+								<ArrowDownTray className="size-3.5" />
+							</button>
+						</Tooltip>
+
 						{#if contents[selectedContentIdx].type === 'iframe'}
 							<Tooltip content={$i18n.t('Open in full screen')}>
 								<button

src/lib/components/chat/Chat.svelte

@@ -119,6 +119,7 @@
 	$: selectedModelIds = atSelectedModel !== undefined ? [atSelectedModel.id] : selectedModels;
 
 	let selectedToolIds = [];
+	let selectedFilterIds = [];
 	let imageGenerationEnabled = false;
 	let webSearchEnabled = false;
 	let codeInterpreterEnabled = false;
@@ -146,6 +147,7 @@
 			prompt = '';
 			files = [];
 			selectedToolIds = [];
+			selectedFilterIds = [];
 			webSearchEnabled = false;
 			imageGenerationEnabled = false;
 
@@ -155,12 +157,15 @@
 						localStorage.getItem(`chat-input${chatIdProp ? `-${chatIdProp}` : ''}`)
 					);
 
-					prompt = input.prompt;
+					if (!$temporaryChatEnabled) {
-					files = input.files;
+						prompt = input.prompt;
-					selectedToolIds = input.selectedToolIds;
+						files = input.files;
-					webSearchEnabled = input.webSearchEnabled;
+						selectedToolIds = input.selectedToolIds;
-					imageGenerationEnabled = input.imageGenerationEnabled;
+						selectedFilterIds = input.selectedFilterIds;
-					codeInterpreterEnabled = input.codeInterpreterEnabled;
+						webSearchEnabled = input.webSearchEnabled;
+						imageGenerationEnabled = input.imageGenerationEnabled;
+						codeInterpreterEnabled = input.codeInterpreterEnabled;
+					}
 				} catch (e) {}
 			}
 
@@ -190,10 +195,12 @@
 
 	$: if (selectedModels) {
 		setToolIds();
+		setFilterIds();
 	}
 
 	$: if (atSelectedModel || selectedModels) {
 		setToolIds();
+		setFilterIds();
 	}
 
 	const setToolIds = async () => {
@@ -207,9 +214,19 @@
 
 		const model = atSelectedModel ?? $models.find((m) => m.id === selectedModels[0]);
 		if (model) {
-			selectedToolIds = (model?.info?.meta?.toolIds ?? []).filter((id) =>
+			selectedToolIds = [
-				$tools.find((t) => t.id === id)
+				...new Set(
-			);
+					[...selectedToolIds, ...(model?.info?.meta?.toolIds ?? [])].filter((id) =>
+						$tools.find((t) => t.id === id)
+					)
+				)
+			];
+		}
+	};
+
+	const setFilterIds = async () => {
+		if (selectedModels.length !== 1 && !atSelectedModel) {
+			selectedFilterIds = [];
 		}
 	};
 
@@ -419,25 +436,29 @@
 		}
 
 		if (localStorage.getItem(`chat-input${chatIdProp ? `-${chatIdProp}` : ''}`)) {
+			prompt = '';
+			files = [];
+			selectedToolIds = [];
+			selectedFilterIds = [];
+			webSearchEnabled = false;
+			imageGenerationEnabled = false;
+			codeInterpreterEnabled = false;
+
 			try {
 				const input = JSON.parse(
 					localStorage.getItem(`chat-input${chatIdProp ? `-${chatIdProp}` : ''}`)
 				);
-				console.log('chat-input', input);
+
-				prompt = input.prompt;
+				if (!$temporaryChatEnabled) {
-				files = input.files;
+					prompt = input.prompt;
-				selectedToolIds = input.selectedToolIds;
+					files = input.files;
-				webSearchEnabled = input.webSearchEnabled;
+					selectedToolIds = input.selectedToolIds;
-				imageGenerationEnabled = input.imageGenerationEnabled;
+					selectedFilterIds = input.selectedFilterIds;
-				codeInterpreterEnabled = input.codeInterpreterEnabled;
+					webSearchEnabled = input.webSearchEnabled;
-			} catch (e) {
+					imageGenerationEnabled = input.imageGenerationEnabled;
-				prompt = '';
+					codeInterpreterEnabled = input.codeInterpreterEnabled;
-				files = [];
+				}
-				selectedToolIds = [];
+			} catch (e) {}
-				webSearchEnabled = false;
-				imageGenerationEnabled = false;
-				codeInterpreterEnabled = false;
-			}
 		}
 
 		if (!chatIdProp) {
@@ -664,10 +685,16 @@
 	//////////////////////////
 
 	const initNewChat = async () => {
-		if ($page.url.searchParams.get('models')) {
+		const availableModels = $models
-			selectedModels = $page.url.searchParams.get('models')?.split(',');
+			.filter((m) => !(m?.info?.meta?.hidden ?? false))
-		} else if ($page.url.searchParams.get('model')) {
+			.map((m) => m.id);
-			const urlModels = $page.url.searchParams.get('model')?.split(',');
+
+		if ($page.url.searchParams.get('models') || $page.url.searchParams.get('model')) {
+			const urlModels = (
+				$page.url.searchParams.get('models') ||
+				$page.url.searchParams.get('model') ||
+				''
+			)?.split(',');
 
 			if (urlModels.length === 1) {
 				const m = $models.find((m) => m.id === urlModels[0]);
@@ -690,6 +717,10 @@
 			} else {
 				selectedModels = urlModels;
 			}
+
+			selectedModels = selectedModels.filter((modelId) =>
+				$models.map((m) => m.id).includes(modelId)
+			);
 		} else {
 			if (sessionStorage.selectedModels) {
 				selectedModels = JSON.parse(sessionStorage.selectedModels);
@@ -702,12 +733,12 @@
 					selectedModels = $config?.default_models.split(',');
 				}
 			}
+			selectedModels = selectedModels.filter((modelId) => availableModels.includes(modelId));
 		}
 
-		selectedModels = selectedModels.filter((modelId) => $models.map((m) => m.id).includes(modelId));
 		if (selectedModels.length === 0 || (selectedModels.length === 1 && selectedModels[0] === '')) {
-			if ($models.length > 0) {
+			if (availableModels.length > 0) {
-				selectedModels = [$models[0].id];
+				selectedModels = [availableModels?.at(0) ?? ''];
 			} else {
 				selectedModels = [''];
 			}
@@ -877,6 +908,7 @@
 				...(m.usage ? { usage: m.usage } : {}),
 				...(m.sources ? { sources: m.sources } : {})
 			})),
+			filter_ids: selectedFilterIds.length > 0 ? selectedFilterIds : undefined,
 			model_item: $models.find((m) => m.id === modelId),
 			chat_id: chatId,
 			session_id: $socket?.id,
@@ -1496,9 +1528,20 @@
 	};
 
 	const sendPromptSocket = async (_history, model, responseMessageId, _chatId) => {
+		const chatMessages = createMessagesList(history, history.currentId);
 		const responseMessage = _history.messages[responseMessageId];
 		const userMessage = _history.messages[responseMessage.parentId];
 
+		const chatMessageFiles = chatMessages
+			.filter((message) => message.files)
+			.flatMap((message) => message.files);
+
+		// Filter chatFiles to only include files that are in the chatMessageFiles
+		chatFiles = chatFiles.filter((item) => {
+			const fileExists = chatMessageFiles.some((messageFile) => messageFile.id === item.id);
+			return fileExists;
+		});
+
 		let files = JSON.parse(JSON.stringify(chatFiles));
 		files.push(
 			...(userMessage?.files ?? []).filter((item) =>
@@ -1602,6 +1645,8 @@
 				},
 
 				files: (files?.length ?? 0) > 0 ? files : undefined,
+
+				filter_ids: selectedFilterIds.length > 0 ? selectedFilterIds : undefined,
 				tool_ids: selectedToolIds.length > 0 ? selectedToolIds : undefined,
 				tool_servers: $toolServers,
 
@@ -2043,6 +2088,7 @@
 								bind:prompt
 								bind:autoScroll
 								bind:selectedToolIds
+								bind:selectedFilterIds
 								bind:imageGenerationEnabled
 								bind:codeInterpreterEnabled
 								bind:webSearchEnabled
@@ -2099,6 +2145,7 @@
 								bind:prompt
 								bind:autoScroll
 								bind:selectedToolIds
+								bind:selectedFilterIds
 								bind:imageGenerationEnabled
 								bind:codeInterpreterEnabled
 								bind:webSearchEnabled

src/lib/components/chat/MessageInput.svelte

@@ -38,6 +38,7 @@
 	import VoiceRecording from './MessageInput/VoiceRecording.svelte';
 	import FilesOverlay from './MessageInput/FilesOverlay.svelte';
 	import Commands from './MessageInput/Commands.svelte';
+	import ToolServersModal from './ToolServersModal.svelte';
 
 	import RichTextInput from '../common/RichTextInput.svelte';
 	import Tooltip from '../common/Tooltip.svelte';
@@ -47,12 +48,12 @@
 	import XMark from '../icons/XMark.svelte';
 	import Headphone from '../icons/Headphone.svelte';
 	import GlobeAlt from '../icons/GlobeAlt.svelte';
-	import PhotoSolid from '../icons/PhotoSolid.svelte';
 	import Photo from '../icons/Photo.svelte';
-	import CommandLine from '../icons/CommandLine.svelte';
-	import { KokoroWorker } from '$lib/workers/KokoroWorker';
-	import ToolServersModal from './ToolServersModal.svelte';
 	import Wrench from '../icons/Wrench.svelte';
+	import CommandLine from '../icons/CommandLine.svelte';
+	import Sparkles from '../icons/Sparkles.svelte';
+
+	import { KokoroWorker } from '$lib/workers/KokoroWorker';
 
 	const i18n = getContext('i18n');
 
@@ -79,6 +80,7 @@
 	export let toolServers = [];
 
 	export let selectedToolIds = [];
+	export let selectedFilterIds = [];
 
 	export let imageGenerationEnabled = false;
 	export let webSearchEnabled = false;
@@ -88,6 +90,7 @@
 		prompt,
 		files: files.filter((file) => file.type !== 'image'),
 		selectedToolIds,
+		selectedFilterIds,
 		imageGenerationEnabled,
 		webSearchEnabled,
 		codeInterpreterEnabled
@@ -113,10 +116,41 @@
 	export let placeholder = '';
 
 	let visionCapableModels = [];
-	$: visionCapableModels = [...(atSelectedModel ? [atSelectedModel] : selectedModels)].filter(
+	$: visionCapableModels = (atSelectedModel?.id ? [atSelectedModel.id] : selectedModels).filter(
 		(model) => $models.find((m) => m.id === model)?.info?.meta?.capabilities?.vision ?? true
 	);
 
+	let fileUploadCapableModels = [];
+	$: fileUploadCapableModels = (atSelectedModel?.id ? [atSelectedModel.id] : selectedModels).filter(
+		(model) => $models.find((m) => m.id === model)?.info?.meta?.capabilities?.file_upload ?? true
+	);
+
+	let webSearchCapableModels = [];
+	$: webSearchCapableModels = (atSelectedModel?.id ? [atSelectedModel.id] : selectedModels).filter(
+		(model) => $models.find((m) => m.id === model)?.info?.meta?.capabilities?.web_search ?? true
+	);
+
+	let imageGenerationCapableModels = [];
+	$: imageGenerationCapableModels = (
+		atSelectedModel?.id ? [atSelectedModel.id] : selectedModels
+	).filter(
+		(model) =>
+			$models.find((m) => m.id === model)?.info?.meta?.capabilities?.image_generation ?? true
+	);
+
+	let codeInterpreterCapableModels = [];
+	$: codeInterpreterCapableModels = (
+		atSelectedModel?.id ? [atSelectedModel.id] : selectedModels
+	).filter(
+		(model) =>
+			$models.find((m) => m.id === model)?.info?.meta?.capabilities?.code_interpreter ?? true
+	);
+
+	let toggleFilters = [];
+	$: toggleFilters = (atSelectedModel?.id ? [atSelectedModel.id] : selectedModels)
+		.map((id) => ($models.find((model) => model.id === id) || {})?.filters ?? [])
+		.reduce((acc, filters) => acc.filter((f1) => filters.some((f2) => f2.id === f1.id)));
+
 	const scrollToBottom = () => {
 		const element = document.getElementById('messages-container');
 		element.scrollTo({
@@ -355,7 +389,6 @@
 </script>
 
 <FilesOverlay show={dragged} />
-
 <ToolServersModal bind:show={showTools} {selectedToolIds} />
 
 {#if loaded}
@@ -581,11 +614,15 @@
 													dismissible={true}
 													edit={true}
 													on:dismiss={async () => {
-														if (file.type !== 'collection' && !file?.collection) {
+														try {
-															if (file.id) {
+															if (file.type !== 'collection' && !file?.collection) {
-																// This will handle both file deletion and Chroma cleanup
+																if (file.id) {
-																await deleteFileById(localStorage.token, file.id);
+																	// This will handle both file deletion and Chroma cleanup
+																	await deleteFileById(localStorage.token, file.id);
+																}
 															}
+														} catch (error) {
+															console.error('Error deleting file:', error);
 														}
 
 														// Remove from UI state
@@ -771,8 +808,11 @@
 														console.log('Escape');
 														atSelectedModel = undefined;
 														selectedToolIds = [];
+														selectedFilterIds = [];
+
 														webSearchEnabled = false;
 														imageGenerationEnabled = false;
+														codeInterpreterEnabled = false;
 													}
 												}}
 												on:paste={async (e) => {
@@ -821,9 +861,9 @@
 									{:else}
 										<textarea
 											id="chat-input"
-											dir="auto"
+											dir={$settings?.chatDirection ?? 'auto'}
 											bind:this={chatInputElement}
-											class="scrollbar-hidden bg-transparent dark:text-gray-100 outline-hidden w-full pt-3 px-1 resize-none"
+											class="scrollbar-hidden bg-transparent dark:text-gray-200 outline-hidden w-full pt-3 px-1 resize-none"
 											placeholder={placeholder ? placeholder : $i18n.t('Send a Message')}
 											bind:value={prompt}
 											on:compositionstart={() => (isComposing = true)}
@@ -869,7 +909,7 @@
 
 													console.log(userMessageElement);
 
-													userMessageElement.scrollIntoView({ block: 'center' });
+													userMessageElement?.scrollIntoView({ block: 'center' });
 													editButton?.click();
 												}
 
@@ -878,20 +918,38 @@
 														e.preventDefault();
 														commandsElement.selectUp();
 
+														const container = document.getElementById('command-options-container');
 														const commandOptionButton = [
 															...document.getElementsByClassName('selected-command-option-button')
 														]?.at(-1);
-														commandOptionButton.scrollIntoView({ block: 'center' });
+
+														if (commandOptionButton && container) {
+															const elTop = commandOptionButton.offsetTop;
+															const elHeight = commandOptionButton.offsetHeight;
+															const containerHeight = container.clientHeight;
+
+															// Center the selected button in the container
+															container.scrollTop = elTop - containerHeight / 2 + elHeight / 2;
+														}
 													}
 
 													if (commandsContainerElement && e.key === 'ArrowDown') {
 														e.preventDefault();
 														commandsElement.selectDown();
 
+														const container = document.getElementById('command-options-container');
 														const commandOptionButton = [
 															...document.getElementsByClassName('selected-command-option-button')
 														]?.at(-1);
-														commandOptionButton.scrollIntoView({ block: 'center' });
+
+														if (commandOptionButton && container) {
+															const elTop = commandOptionButton.offsetTop;
+															const elHeight = commandOptionButton.offsetHeight;
+															const containerHeight = container.clientHeight;
+
+															// Center the selected button in the container
+															container.scrollTop = elTop - containerHeight / 2 + elHeight / 2;
+														}
 													}
 
 													if (commandsContainerElement && e.key === 'Enter') {
@@ -939,8 +997,6 @@
 																? (e.key === 'Enter' || e.keyCode === 13) && isCtrlPressed
 																: (e.key === 'Enter' || e.keyCode === 13) && !e.shiftKey;
 
-														console.log('Enter pressed:', enterPressed);
-
 														if (enterPressed) {
 															e.preventDefault();
 														}
@@ -978,8 +1034,10 @@
 													console.log('Escape');
 													atSelectedModel = undefined;
 													selectedToolIds = [];
+													selectedFilterIds = [];
 													webSearchEnabled = false;
 													imageGenerationEnabled = false;
+													codeInterpreterEnabled = false;
 												}
 											}}
 											rows="1"
@@ -1037,6 +1095,8 @@
 									<div class="ml-1 self-end flex items-center flex-1 max-w-[80%] gap-0.5">
 										<InputMenu
 											bind:selectedToolIds
+											selectedModels={atSelectedModel ? [atSelectedModel.id] : selectedModels}
+											{fileUploadCapableModels}
 											{screenCaptureHandler}
 											{inputFilesHandler}
 											uploadFilesHandler={() => {
@@ -1127,7 +1187,48 @@
 											{/if}
 
 											{#if $_user}
-												{#if $config?.features?.enable_web_search && ($_user.role === 'admin' || $_user?.permissions?.features?.web_search)}
+												{#each toggleFilters as filter, filterIdx (filter.id)}
+													<Tooltip content={filter?.description} placement="top">
+														<button
+															on:click|preventDefault={() => {
+																if (selectedFilterIds.includes(filter.id)) {
+																	selectedFilterIds = selectedFilterIds.filter(
+																		(id) => id !== filter.id
+																	);
+																} else {
+																	selectedFilterIds = [...selectedFilterIds, filter.id];
+																}
+															}}
+															type="button"
+															class="px-1.5 @xl:px-2.5 py-1.5 flex gap-1.5 items-center text-sm rounded-full font-medium transition-colors duration-300 focus:outline-hidden max-w-full overflow-hidden border {selectedFilterIds.includes(
+																filter.id
+															)
+																? 'bg-gray-50 dark:bg-gray-400/10 border-gray-100 dark:border-gray-700 text-gray-600 dark:text-gray-400'
+																: 'bg-transparent border-transparent text-gray-600 dark:text-gray-300  hover:bg-gray-50 dark:hover:bg-gray-800 '} capitalize"
+														>
+															{#if filter?.icon}
+																<div class="size-5 items-center flex justify-center">
+																	<img
+																		src={filter.icon}
+																		class="size-4.5 {filter.icon.includes('svg')
+																			? 'dark:invert-[80%]'
+																			: ''}"
+																		style="fill: currentColor;"
+																		alt={filter.name}
+																	/>
+																</div>
+															{:else}
+																<Sparkles className="size-5" strokeWidth="1.75" />
+															{/if}
+															<span
+																class="hidden @xl:block whitespace-nowrap overflow-hidden text-ellipsis translate-y-[0.5px]"
+																>{filter?.name}</span
+															>
+														</button>
+													</Tooltip>
+												{/each}
+
+												{#if (atSelectedModel?.id ? [atSelectedModel.id] : selectedModels).length === webSearchCapableModels.length && $config?.features?.enable_web_search && ($_user.role === 'admin' || $_user?.permissions?.features?.web_search)}
 													<Tooltip content={$i18n.t('Search the internet')} placement="top">
 														<button
 															on:click|preventDefault={() => (webSearchEnabled = !webSearchEnabled)}
@@ -1135,7 +1236,7 @@
 															class="px-1.5 @xl:px-2.5 py-1.5 flex gap-1.5 items-center text-sm rounded-full font-medium transition-colors duration-300 focus:outline-hidden max-w-full overflow-hidden border {webSearchEnabled ||
 															($settings?.webSearch ?? false) === 'always'
 																? 'bg-blue-100 dark:bg-blue-500/20 border-blue-400/20 text-blue-500 dark:text-blue-400'
-																: 'bg-transparent border-transparent text-gray-600 dark:text-gray-300 border-gray-200 hover:bg-gray-100 dark:hover:bg-gray-800'}"
+																: 'bg-transparent border-transparent text-gray-600 dark:text-gray-300 border-gray-200 hover:bg-gray-50 dark:hover:bg-gray-800'}"
 														>
 															<GlobeAlt className="size-5" strokeWidth="1.75" />
 															<span
@@ -1146,7 +1247,7 @@
 													</Tooltip>
 												{/if}
 
-												{#if $config?.features?.enable_image_generation && ($_user.role === 'admin' || $_user?.permissions?.features?.image_generation)}
+												{#if (atSelectedModel?.id ? [atSelectedModel.id] : selectedModels).length === imageGenerationCapableModels.length && $config?.features?.enable_image_generation && ($_user.role === 'admin' || $_user?.permissions?.features?.image_generation)}
 													<Tooltip content={$i18n.t('Generate an image')} placement="top">
 														<button
 															on:click|preventDefault={() =>
@@ -1154,7 +1255,7 @@
 															type="button"
 															class="px-1.5 @xl:px-2.5 py-1.5 flex gap-1.5 items-center text-sm rounded-full font-medium transition-colors duration-300 focus:outline-hidden max-w-full overflow-hidden border {imageGenerationEnabled
 																? 'bg-gray-50 dark:bg-gray-400/10 border-gray-100 dark:border-gray-700 text-gray-600 dark:text-gray-400'
-																: 'bg-transparent border-transparent text-gray-600 dark:text-gray-300  hover:bg-gray-100 dark:hover:bg-gray-800 '}"
+																: 'bg-transparent border-transparent text-gray-600 dark:text-gray-300  hover:bg-gray-50 dark:hover:bg-gray-800 '}"
 														>
 															<Photo className="size-5" strokeWidth="1.75" />
 															<span
@@ -1165,7 +1266,7 @@
 													</Tooltip>
 												{/if}
 
-												{#if $config?.features?.enable_code_interpreter && ($_user.role === 'admin' || $_user?.permissions?.features?.code_interpreter)}
+												{#if (atSelectedModel?.id ? [atSelectedModel.id] : selectedModels).length === codeInterpreterCapableModels.length && $config?.features?.enable_code_interpreter && ($_user.role === 'admin' || $_user?.permissions?.features?.code_interpreter)}
 													<Tooltip content={$i18n.t('Execute code for analysis')} placement="top">
 														<button
 															on:click|preventDefault={() =>
@@ -1173,7 +1274,7 @@
 															type="button"
 															class="px-1.5 @xl:px-2.5 py-1.5 flex gap-1.5 items-center text-sm rounded-full font-medium transition-colors duration-300 focus:outline-hidden max-w-full overflow-hidden border {codeInterpreterEnabled
 																? 'bg-gray-50 dark:bg-gray-400/10 border-gray-100  dark:border-gray-700 text-gray-600 dark:text-gray-400  '
-																: 'bg-transparent border-transparent text-gray-600 dark:text-gray-300  hover:bg-gray-100 dark:hover:bg-gray-800 '}"
+																: 'bg-transparent border-transparent text-gray-600 dark:text-gray-300  hover:bg-gray-50 dark:hover:bg-gray-800 '}"
 														>
 															<CommandLine className="size-5" strokeWidth="1.75" />
 															<span

src/lib/components/chat/MessageInput/Commands/Knowledge.svelte

@@ -170,10 +170,11 @@
 		class="px-2 mb-2 text-left w-full absolute bottom-0 left-0 right-0 z-10"
 	>
 		<div class="flex w-full rounded-xl border border-gray-100 dark:border-gray-850">
-			<div
+			<div class="flex flex-col w-full rounded-xl bg-white dark:bg-gray-900 dark:text-gray-100">
-				class="max-h-60 flex flex-col w-full rounded-xl bg-white dark:bg-gray-900 dark:text-gray-100"
+				<div
-			>
+					class="m-1 overflow-y-auto p-1 rounded-r-xl space-y-0.5 scrollbar-hidden max-h-60"
-				<div class="m-1 overflow-y-auto p-1 rounded-r-xl space-y-0.5 scrollbar-hidden">
+					id="command-options-container"
+				>
 					{#each filteredItems as item, idx}
 						<button
 							class=" px-3 py-1.5 rounded-xl w-full text-left flex justify-between items-center {idx ===

src/lib/components/chat/MessageInput/Commands/Models.svelte

@@ -71,10 +71,11 @@
 		class="px-2 mb-2 text-left w-full absolute bottom-0 left-0 right-0 z-10"
 	>
 		<div class="flex w-full rounded-xl border border-gray-100 dark:border-gray-850">
-			<div
+			<div class="flex flex-col w-full rounded-xl bg-white dark:bg-gray-900 dark:text-gray-100">
-				class="max-h-60 flex flex-col w-full rounded-xl bg-white dark:bg-gray-900 dark:text-gray-100"
+				<div
-			>
+					class="m-1 overflow-y-auto p-1 rounded-r-lg space-y-0.5 scrollbar-hidden max-h-60"
-				<div class="m-1 overflow-y-auto p-1 rounded-r-lg space-y-0.5 scrollbar-hidden">
+					id="command-options-container"
+				>
 					{#each filteredItems as model, modelIdx}
 						<button
 							class="px-3 py-1.5 rounded-xl w-full text-left {modelIdx === selectedIdx

src/lib/components/chat/MessageInput/Commands/Prompts.svelte

@@ -180,10 +180,11 @@
 		class="px-2 mb-2 text-left w-full absolute bottom-0 left-0 right-0 z-10"
 	>
 		<div class="flex w-full rounded-xl border border-gray-100 dark:border-gray-850">
-			<div
+			<div class="flex flex-col w-full rounded-xl bg-white dark:bg-gray-900 dark:text-gray-100">
-				class="max-h-60 flex flex-col w-full rounded-xl bg-white dark:bg-gray-900 dark:text-gray-100"
+				<div
-			>
+					class="m-1 overflow-y-auto p-1 space-y-0.5 scrollbar-hidden max-h-60"
-				<div class="m-1 overflow-y-auto p-1 space-y-0.5 scrollbar-hidden">
+					id="command-options-container"
+				>
 					{#each filteredPrompts as prompt, promptIdx}
 						<button
 							class=" px-3 py-1.5 rounded-xl w-full text-left {promptIdx === selectedPromptIdx

src/lib/components/chat/MessageInput/InputMenu.svelte

@@ -20,6 +20,11 @@
 
 	const i18n = getContext('i18n');
 
+	export let selectedToolIds: string[] = [];
+
+	export let selectedModels: string[] = [];
+	export let fileUploadCapableModels: string[] = [];
+
 	export let screenCaptureHandler: Function;
 	export let uploadFilesHandler: Function;
 	export let inputFilesHandler: Function;
@@ -27,8 +32,6 @@
 	export let uploadGoogleDriveHandler: Function;
 	export let uploadOneDriveHandler: Function;
 
-	export let selectedToolIds: string[] = [];
-
 	export let onClose: Function;
 
 	let tools = {};
@@ -40,7 +43,9 @@
 	}
 
 	let fileUploadEnabled = true;
-	$: fileUploadEnabled = $user?.role === 'admin' || $user?.permissions?.chat?.file_upload;
+	$: fileUploadEnabled =
+		fileUploadCapableModels.length === selectedModels.length &&
+		($user?.role === 'admin' || $user?.permissions?.chat?.file_upload);
 
 	const init = async () => {
 		if ($_tools === null) {
@@ -169,7 +174,11 @@
 			{/if}
 
 			<Tooltip
-				content={!fileUploadEnabled ? $i18n.t('You do not have permission to upload files.') : ''}
+				content={fileUploadCapableModels.length !== selectedModels.length
+					? $i18n.t('Model(s) do not support file upload')
+					: !fileUploadEnabled
+						? $i18n.t('You do not have permission to upload files.')
+						: ''}
 				className="w-full"
 			>
 				<DropdownMenu.Item
@@ -196,7 +205,11 @@
 			</Tooltip>
 
 			<Tooltip
-				content={!fileUploadEnabled ? $i18n.t('You do not have permission to upload files.') : ''}
+				content={fileUploadCapableModels.length !== selectedModels.length
+					? $i18n.t('Model(s) do not support file upload')
+					: !fileUploadEnabled
+						? $i18n.t('You do not have permission to upload files.')
+						: ''}
 				className="w-full"
 			>
 				<DropdownMenu.Item
@@ -214,157 +227,164 @@
 				</DropdownMenu.Item>
 			</Tooltip>
 
-			{#if $config?.features?.enable_google_drive_integration}
+			{#if fileUploadEnabled}
-				<DropdownMenu.Item
+				{#if $config?.features?.enable_google_drive_integration}
-					class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl"
+					<DropdownMenu.Item
-					on:click={() => {
+						class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl"
-						uploadGoogleDriveHandler();
+						on:click={() => {
-					}}
+							uploadGoogleDriveHandler();
-				>
+						}}
-					<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 87.3 78" class="w-5 h-5">
-						<path
-							d="m6.6 66.85 3.85 6.65c.8 1.4 1.95 2.5 3.3 3.3l13.75-23.8h-27.5c0 1.55.4 3.1 1.2 4.5z"
-							fill="#0066da"
-						/>
-						<path
-							d="m43.65 25-13.75-23.8c-1.35.8-2.5 1.9-3.3 3.3l-25.4 44a9.06 9.06 0 0 0 -1.2 4.5h27.5z"
-							fill="#00ac47"
-						/>
-						<path
-							d="m73.55 76.8c1.35-.8 2.5-1.9 3.3-3.3l1.6-2.75 7.65-13.25c.8-1.4 1.2-2.95 1.2-4.5h-27.502l5.852 11.5z"
-							fill="#ea4335"
-						/>
-						<path
-							d="m43.65 25 13.75-23.8c-1.35-.8-2.9-1.2-4.5-1.2h-18.5c-1.6 0-3.15.45-4.5 1.2z"
-							fill="#00832d"
-						/>
-						<path
-							d="m59.8 53h-32.3l-13.75 23.8c1.35.8 2.9 1.2 4.5 1.2h50.8c1.6 0 3.15-.45 4.5-1.2z"
-							fill="#2684fc"
-						/>
-						<path
-							d="m73.4 26.5-12.7-22c-.8-1.4-1.95-2.5-3.3-3.3l-13.75 23.8 16.15 28h27.45c0-1.55-.4-3.1-1.2-4.5z"
-							fill="#ffba00"
-						/>
-					</svg>
-					<div class="line-clamp-1">{$i18n.t('Google Drive')}</div>
-				</DropdownMenu.Item>
-			{/if}
-
-			{#if $config?.features?.enable_onedrive_integration}
-				<DropdownMenu.Sub>
-					<DropdownMenu.SubTrigger
-						class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl w-full"
 					>
-						<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32" class="w-5 h-5" fill="none">
+						<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 87.3 78" class="w-5 h-5">
-							<mask
+							<path
-								id="mask0_87_7796"
+								d="m6.6 66.85 3.85 6.65c.8 1.4 1.95 2.5 3.3 3.3l13.75-23.8h-27.5c0 1.55.4 3.1 1.2 4.5z"
-								style="mask-type:alpha"
+								fill="#0066da"
-								maskUnits="userSpaceOnUse"
+							/>
-								x="0"
+							<path
-								y="6"
+								d="m43.65 25-13.75-23.8c-1.35.8-2.5 1.9-3.3 3.3l-25.4 44a9.06 9.06 0 0 0 -1.2 4.5h27.5z"
-								width="32"
+								fill="#00ac47"
-								height="20"
+							/>
-							>
+							<path
-								<path
+								d="m73.55 76.8c1.35-.8 2.5-1.9 3.3-3.3l1.6-2.75 7.65-13.25c.8-1.4 1.2-2.95 1.2-4.5h-27.502l5.852 11.5z"
-									d="M7.82979 26C3.50549 26 0 22.5675 0 18.3333C0 14.1921 3.35322 10.8179 7.54613 10.6716C9.27535 7.87166 12.4144 6 16 6C20.6308 6 24.5169 9.12183 25.5829 13.3335C29.1316 13.3603 32 16.1855 32 19.6667C32 23.0527 29 26 25.8723 25.9914L7.82979 26Z"
+								fill="#ea4335"
-									fill="#C4C4C4"
+							/>
-								/>
+							<path
-							</mask>
+								d="m43.65 25 13.75-23.8c-1.35-.8-2.9-1.2-4.5-1.2h-18.5c-1.6 0-3.15.45-4.5 1.2z"
-							<g mask="url(#mask0_87_7796)">
+								fill="#00832d"
-								<path
+							/>
-									d="M7.83017 26.0001C5.37824 26.0001 3.18957 24.8966 1.75391 23.1691L18.0429 16.3335L30.7089 23.4647C29.5926 24.9211 27.9066 26.0001 26.0004 25.9915C23.1254 26.0001 12.0629 26.0001 7.83017 26.0001Z"
+							<path
-									fill="url(#paint0_linear_87_7796)"
+								d="m59.8 53h-32.3l-13.75 23.8c1.35.8 2.9 1.2 4.5 1.2h50.8c1.6 0 3.15-.45 4.5-1.2z"
-								/>
+								fill="#2684fc"
-								<path
+							/>
-									d="M25.5785 13.3149L18.043 16.3334L30.709 23.4647C31.5199 22.4065 32.0004 21.0916 32.0004 19.6669C32.0004 16.1857 29.1321 13.3605 25.5833 13.3337C25.5817 13.3274 25.5801 13.3212 25.5785 13.3149Z"
+							<path
-									fill="url(#paint1_linear_87_7796)"
+								d="m73.4 26.5-12.7-22c-.8-1.4-1.95-2.5-3.3-3.3l-13.75 23.8 16.15 28h27.45c0-1.55-.4-3.1-1.2-4.5z"
-								/>
+								fill="#ffba00"
-								<path
+							/>
-									d="M7.06445 10.7028L18.0423 16.3333L25.5779 13.3148C24.5051 9.11261 20.6237 6 15.9997 6C12.4141 6 9.27508 7.87166 7.54586 10.6716C7.3841 10.6773 7.22358 10.6877 7.06445 10.7028Z"
-									fill="url(#paint2_linear_87_7796)"
-								/>
-								<path
-									d="M1.7535 23.1687L18.0425 16.3331L7.06471 10.7026C3.09947 11.0792 0 14.3517 0 18.3331C0 20.1665 0.657197 21.8495 1.7535 23.1687Z"
-									fill="url(#paint3_linear_87_7796)"
-								/>
-							</g>
-							<defs>
-								<linearGradient
-									id="paint0_linear_87_7796"
-									x1="4.42591"
-									y1="24.6668"
-									x2="27.2309"
-									y2="23.2764"
-									gradientUnits="userSpaceOnUse"
-								>
-									<stop stop-color="#2086B8" />
-									<stop offset="1" stop-color="#46D3F6" />
-								</linearGradient>
-								<linearGradient
-									id="paint1_linear_87_7796"
-									x1="23.8302"
-									y1="19.6668"
-									x2="30.2108"
-									y2="15.2082"
-									gradientUnits="userSpaceOnUse"
-								>
-									<stop stop-color="#1694DB" />
-									<stop offset="1" stop-color="#62C3FE" />
-								</linearGradient>
-								<linearGradient
-									id="paint2_linear_87_7796"
-									x1="8.51037"
-									y1="7.33333"
-									x2="23.3335"
-									y2="15.9348"
-									gradientUnits="userSpaceOnUse"
-								>
-									<stop stop-color="#0D3D78" />
-									<stop offset="1" stop-color="#063B83" />
-								</linearGradient>
-								<linearGradient
-									id="paint3_linear_87_7796"
-									x1="-0.340429"
-									y1="19.9998"
-									x2="14.5634"
-									y2="14.4649"
-									gradientUnits="userSpaceOnUse"
-								>
-									<stop stop-color="#16589B" />
-									<stop offset="1" stop-color="#1464B7" />
-								</linearGradient>
-							</defs>
 						</svg>
-						<div class="line-clamp-1">{$i18n.t('Microsoft OneDrive')}</div>
+						<div class="line-clamp-1">{$i18n.t('Google Drive')}</div>
-					</DropdownMenu.SubTrigger>
+					</DropdownMenu.Item>
-					<DropdownMenu.SubContent
+				{/if}
-						class="w-[calc(100vw-2rem)] max-w-[280px] rounded-xl px-1 py-1 border border-gray-300/30 dark:border-gray-700/50 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-sm"
+
-						side={$mobile ? 'bottom' : 'right'}
+				{#if $config?.features?.enable_onedrive_integration}
-						sideOffset={$mobile ? 5 : 0}
+					<DropdownMenu.Sub>
-						alignOffset={$mobile ? 0 : -8}
+						<DropdownMenu.SubTrigger
-					>
+							class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl w-full"
-						<DropdownMenu.Item
-							class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl"
-							on:click={() => {
-								uploadOneDriveHandler('personal');
-							}}
 						>
-							<div class="line-clamp-1">{$i18n.t('Microsoft OneDrive (personal)')}</div>
+							<svg
-						</DropdownMenu.Item>
+								xmlns="http://www.w3.org/2000/svg"
-						<DropdownMenu.Item
+								viewBox="0 0 32 32"
-							class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl"
+								class="w-5 h-5"
-							on:click={() => {
+								fill="none"
-								uploadOneDriveHandler('organizations');
+							>
-							}}
+								<mask
+									id="mask0_87_7796"
+									style="mask-type:alpha"
+									maskUnits="userSpaceOnUse"
+									x="0"
+									y="6"
+									width="32"
+									height="20"
+								>
+									<path
+										d="M7.82979 26C3.50549 26 0 22.5675 0 18.3333C0 14.1921 3.35322 10.8179 7.54613 10.6716C9.27535 7.87166 12.4144 6 16 6C20.6308 6 24.5169 9.12183 25.5829 13.3335C29.1316 13.3603 32 16.1855 32 19.6667C32 23.0527 29 26 25.8723 25.9914L7.82979 26Z"
+										fill="#C4C4C4"
+									/>
+								</mask>
+								<g mask="url(#mask0_87_7796)">
+									<path
+										d="M7.83017 26.0001C5.37824 26.0001 3.18957 24.8966 1.75391 23.1691L18.0429 16.3335L30.7089 23.4647C29.5926 24.9211 27.9066 26.0001 26.0004 25.9915C23.1254 26.0001 12.0629 26.0001 7.83017 26.0001Z"
+										fill="url(#paint0_linear_87_7796)"
+									/>
+									<path
+										d="M25.5785 13.3149L18.043 16.3334L30.709 23.4647C31.5199 22.4065 32.0004 21.0916 32.0004 19.6669C32.0004 16.1857 29.1321 13.3605 25.5833 13.3337C25.5817 13.3274 25.5801 13.3212 25.5785 13.3149Z"
+										fill="url(#paint1_linear_87_7796)"
+									/>
+									<path
+										d="M7.06445 10.7028L18.0423 16.3333L25.5779 13.3148C24.5051 9.11261 20.6237 6 15.9997 6C12.4141 6 9.27508 7.87166 7.54586 10.6716C7.3841 10.6773 7.22358 10.6877 7.06445 10.7028Z"
+										fill="url(#paint2_linear_87_7796)"
+									/>
+									<path
+										d="M1.7535 23.1687L18.0425 16.3331L7.06471 10.7026C3.09947 11.0792 0 14.3517 0 18.3331C0 20.1665 0.657197 21.8495 1.7535 23.1687Z"
+										fill="url(#paint3_linear_87_7796)"
+									/>
+								</g>
+								<defs>
+									<linearGradient
+										id="paint0_linear_87_7796"
+										x1="4.42591"
+										y1="24.6668"
+										x2="27.2309"
+										y2="23.2764"
+										gradientUnits="userSpaceOnUse"
+									>
+										<stop stop-color="#2086B8" />
+										<stop offset="1" stop-color="#46D3F6" />
+									</linearGradient>
+									<linearGradient
+										id="paint1_linear_87_7796"
+										x1="23.8302"
+										y1="19.6668"
+										x2="30.2108"
+										y2="15.2082"
+										gradientUnits="userSpaceOnUse"
+									>
+										<stop stop-color="#1694DB" />
+										<stop offset="1" stop-color="#62C3FE" />
+									</linearGradient>
+									<linearGradient
+										id="paint2_linear_87_7796"
+										x1="8.51037"
+										y1="7.33333"
+										x2="23.3335"
+										y2="15.9348"
+										gradientUnits="userSpaceOnUse"
+									>
+										<stop stop-color="#0D3D78" />
+										<stop offset="1" stop-color="#063B83" />
+									</linearGradient>
+									<linearGradient
+										id="paint3_linear_87_7796"
+										x1="-0.340429"
+										y1="19.9998"
+										x2="14.5634"
+										y2="14.4649"
+										gradientUnits="userSpaceOnUse"
+									>
+										<stop stop-color="#16589B" />
+										<stop offset="1" stop-color="#1464B7" />
+									</linearGradient>
+								</defs>
+							</svg>
+							<div class="line-clamp-1">{$i18n.t('Microsoft OneDrive')}</div>
+						</DropdownMenu.SubTrigger>
+						<DropdownMenu.SubContent
+							class="w-[calc(100vw-2rem)] max-w-[280px] rounded-xl px-1 py-1 border border-gray-300/30 dark:border-gray-700/50 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-sm"
+							side={$mobile ? 'bottom' : 'right'}
+							sideOffset={$mobile ? 5 : 0}
+							alignOffset={$mobile ? 0 : -8}
 						>
-							<div class="flex flex-col">
+							<DropdownMenu.Item
-								<div class="line-clamp-1">{$i18n.t('Microsoft OneDrive (work/school)')}</div>
+								class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl"
-								<div class="text-xs text-gray-500">Includes SharePoint</div>
+								on:click={() => {
-							</div>
+									uploadOneDriveHandler('personal');
-						</DropdownMenu.Item>
+								}}
-					</DropdownMenu.SubContent>
+							>
-				</DropdownMenu.Sub>
+								<div class="line-clamp-1">{$i18n.t('Microsoft OneDrive (personal)')}</div>
+							</DropdownMenu.Item>
+							<DropdownMenu.Item
+								class="flex gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-xl"
+								on:click={() => {
+									uploadOneDriveHandler('organizations');
+								}}
+							>
+								<div class="flex flex-col">
+									<div class="line-clamp-1">{$i18n.t('Microsoft OneDrive (work/school)')}</div>
+									<div class="text-xs text-gray-500">Includes SharePoint</div>
+								</div>
+							</DropdownMenu.Item>
+						</DropdownMenu.SubContent>
+					</DropdownMenu.Sub>
+				{/if}
 			{/if}
 		</DropdownMenu.Content>
 	</div>

src/lib/components/chat/Messages.svelte

@@ -255,7 +255,7 @@
 		await updateChat();
 	};
 
-	const editMessage = async (messageId, content, submit = true) => {
+	const editMessage = async (messageId, { content, files }, submit = true) => {
 		if (history.messages[messageId].role === 'user') {
 			if (submit) {
 				// New user message
@@ -268,7 +268,7 @@
 					childrenIds: [],
 					role: 'user',
 					content: userPrompt,
-					...(history.messages[messageId].files && { files: history.messages[messageId].files }),
+					...(files && { files: files }),
 					models: selectedModels,
 					timestamp: Math.floor(Date.now() / 1000) // Unix epoch
 				};
@@ -290,6 +290,7 @@
 			} else {
 				// Edit user message
 				history.messages[messageId].content = content;
+				history.messages[messageId].files = files;
 				await updateChat();
 			}
 		} else {

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

@@ -17,16 +17,19 @@
 	import ChevronUp from '$lib/components/icons/ChevronUp.svelte';
 	import ChevronUpDown from '$lib/components/icons/ChevronUpDown.svelte';
 	import CommandLine from '$lib/components/icons/CommandLine.svelte';
+	import Cube from '$lib/components/icons/Cube.svelte';
 
 	const i18n = getContext('i18n');
 
 	export let id = '';
 
 	export let onSave = (e) => {};
-	export let onCode = (e) => {};
+	export let onUpdate = (e) => {};
+	export let onPreview = (e) => {};
 
 	export let save = false;
 	export let run = true;
+	export let preview = false;
 	export let collapsed = false;
 
 	export let token;
@@ -88,6 +91,10 @@
 		}, 1000);
 	};
 
+	const previewCode = () => {
+		onPreview(code);
+	};
+
 	const checkPythonCode = (str) => {
 		// Check if the string contains typical Python syntax characters
 		const pythonSyntax = [
@@ -333,6 +340,8 @@
 				await drawMermaidDiagram();
 			})();
 		}
+
+		onUpdate(token);
 	};
 
 	$: if (token) {
@@ -345,8 +354,6 @@
 		render();
 	}
 
-	$: onCode({ lang, code });
-
 	$: if (attributes) {
 		onAttributesUpdate();
 	}
@@ -379,10 +386,10 @@
 
 	onMount(async () => {
 		console.log('codeblock', lang, code);
-
+		if (token) {
-		if (lang) {
+			onUpdate(token);
-			onCode({ lang, code });
 		}
+
 		if (document.documentElement.classList.contains('dark')) {
 			mermaid.initialize({
 				startOnLoad: true,
@@ -430,7 +437,7 @@
 						class="flex gap-1 items-center bg-none border-none bg-gray-50 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition rounded-md px-1.5 py-0.5"
 						on:click={collapseCodeBlock}
 					>
-						<div>
+						<div class=" -translate-y-[0.5px]">
 							<ChevronUpDown className="size-3" />
 						</div>
 
@@ -439,6 +446,21 @@
 						</div>
 					</button>
 
+					{#if preview && ['html', 'svg'].includes(lang)}
+						<button
+							class="flex gap-1 items-center run-code-button bg-none border-none bg-gray-50 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition rounded-md px-1.5 py-0.5"
+							on:click={previewCode}
+						>
+							<div class=" -translate-y-[0.5px]">
+								<Cube className="size-3" />
+							</div>
+
+							<div>
+								{$i18n.t('Preview')}
+							</div>
+						</button>
+					{/if}
+
 					{#if ($config?.features?.enable_code_execution ?? true) && (lang.toLowerCase() === 'python' || lang.toLowerCase() === 'py' || (lang === '' && checkPythonCode(code)))}
 						{#if executing}
 							<div class="run-code-button bg-none border-none p-1 cursor-not-allowed">
@@ -453,7 +475,7 @@
 									executePython(code);
 								}}
 							>
-								<div>
+								<div class=" -translate-y-[0.5px]">
 									<CommandLine className="size-3" />
 								</div>
 

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

@@ -1,10 +1,17 @@
 <script>
-	import { onDestroy, onMount, tick, getContext, createEventDispatcher } from 'svelte';
+	import { onDestroy, onMount, tick, getContext } from 'svelte';
 	const i18n = getContext('i18n');
-	const dispatch = createEventDispatcher();
 
 	import Markdown from './Markdown.svelte';
-	import { chatId, mobile, settings, showArtifacts, showControls, showOverview } from '$lib/stores';
+	import {
+		artifactCode,
+		chatId,
+		mobile,
+		settings,
+		showArtifacts,
+		showControls,
+		showOverview
+	} from '$lib/stores';
 	import FloatingButtons from '../ContentRenderer/FloatingButtons.svelte';
 	import { createMessagesList } from '$lib/utils';
 
@@ -15,8 +22,10 @@
 	export let sources = null;
 
 	export let save = false;
+	export let preview = false;
 	export let floatingButtons = true;
 
+	export let onSave = () => {};
 	export let onSourceClick = () => {};
 	export let onTaskClick = () => {};
 
@@ -122,6 +131,7 @@
 		{content}
 		{model}
 		{save}
+		{preview}
 		sourceIds={(sources ?? []).reduce((acc, s) => {
 			let ids = [];
 			s.document.forEach((document, index) => {
@@ -154,11 +164,9 @@
 		}, [])}
 		{onSourceClick}
 		{onTaskClick}
-		onUpdate={(value) => {
+		{onSave}
-			dispatch('update', value);
+		onUpdate={(token) => {
-		}}
+			const { lang, text: code } = token;
-		onCode={(value) => {
-			const { lang, code } = value;
 
 			if (
 				($settings?.detectArtifacts ?? true) &&
@@ -170,6 +178,13 @@
 				showControls.set(true);
 			}
 		}}
+		onPreview={async (value) => {
+			console.log('Preview', value);
+			await artifactCode.set(value);
+			await showControls.set(true);
+			await showArtifacts.set(true);
+			await showOverview.set(false);
+		}}
 	/>
 </div>
 

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

@@ -12,11 +12,14 @@
 	export let content;
 	export let model = null;
 	export let save = false;
+	export let preview = false;
 
 	export let sourceIds = [];
 
+	export let onSave = () => {};
 	export let onUpdate = () => {};
-	export let onCode = () => {};
+
+	export let onPreview = () => {};
 
 	export let onSourceClick = () => {};
 	export let onTaskClick = () => {};
@@ -40,5 +43,15 @@
 </script>
 
 {#key id}
-	<MarkdownTokens {tokens} {id} {save} {onTaskClick} {onSourceClick} {onUpdate} {onCode} />
+	<MarkdownTokens
+		{tokens}
+		{id}
+		{save}
+		{preview}
+		{onTaskClick}
+		{onSourceClick}
+		{onSave}
+		{onUpdate}
+		{onPreview}
+	/>
 {/key}

src/lib/components/chat/Messages/Markdown/MarkdownTokens.svelte

@@ -29,9 +29,11 @@
 	export let attributes = {};
 
 	export let save = false;
+	export let preview = false;
 
+	export let onSave: Function = () => {};
 	export let onUpdate: Function = () => {};
-	export let onCode: Function = () => {};
+	export let onPreview: Function = () => {};
 
 	export let onTaskClick: Function = () => {};
 	export let onSourceClick: Function = () => {};
@@ -95,14 +97,16 @@
 				code={token?.text ?? ''}
 				{attributes}
 				{save}
-				{onCode}
+				{preview}
 				onSave={(value) => {
-					onUpdate({
+					onSave({
 						raw: token.raw,
 						oldContent: token.text,
 						newContent: value
 					});
 				}}
+				{onUpdate}
+				{onPreview}
 			/>
 		{:else}
 			{token.text}

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

@@ -157,6 +157,10 @@
 	const copyToClipboard = async (text) => {
 		text = removeAllDetails(text);
 
+		if (($config?.ui?.response_watermark ?? '').trim() !== '') {
+			text = `${text}\n\n${$config?.ui?.response_watermark}`;
+		}
+
 		const res = await _copyToClipboard(text, $settings?.copyFormatted ?? false);
 		if (res) {
 			toast.success($i18n.t('Copying to clipboard was successful!'));
@@ -377,7 +381,7 @@
 
 	const editMessageConfirmHandler = async () => {
 		const messageContent = postprocessAfterEditing(editedContent ? editedContent : '');
-		editMessage(message.id, messageContent, false);
+		editMessage(message.id, { content: messageContent }, false);
 
 		edit = false;
 		editedContent = '';
@@ -388,7 +392,7 @@
 	const saveAsCopyHandler = async () => {
 		const messageContent = postprocessAfterEditing(editedContent ? editedContent : '');
 
-		editMessage(message.id, messageContent);
+		editMessage(message.id, { content: messageContent });
 
 		edit = false;
 		editedContent = '';
@@ -560,17 +564,30 @@
 		await tick();
 		if (buttonsContainerElement) {
 			console.log(buttonsContainerElement);
-			buttonsContainerElement.addEventListener('wheel', function (event) {
-				// console.log(event.deltaY);
 
-				event.preventDefault();
+			buttonsContainerElement.addEventListener('wheel', function (event) {
-				if (event.deltaY !== 0) {
+				if (buttonsContainerElement.scrollWidth <= buttonsContainerElement.clientWidth) {
-					// Adjust horizontal scroll position based on vertical scroll
+					// If the container is not scrollable, horizontal scroll
-					buttonsContainerElement.scrollLeft += event.deltaY;
+					return;
+				} else {
+					event.preventDefault();
+
+					if (event.deltaY !== 0) {
+						// Adjust horizontal scroll position based on vertical scroll
+						buttonsContainerElement.scrollLeft += event.deltaY;
+					}
 				}
 			});
 		}
 	});
+
+	let screenReaderDiv: HTMLDivElement;
+
+	$: if (message.done) {
+		if (screenReaderDiv) {
+			screenReaderDiv.textContent = message.content;
+		}
+	}
 </script>
 
 <DeleteConfirmDialog
@@ -581,6 +598,10 @@
 	}}
 />
 
+<div bind:this={screenReaderDiv} aria-live="polite" class="sr-only">
+	{message.done ? message.content : ''}
+</div>
+
 {#key message.id}
 	<div
 		class=" flex w-full message-{message.id}"
@@ -785,6 +806,7 @@
 										sources={message.sources}
 										floatingButtons={message?.done && !readOnly}
 										save={!readOnly}
+										preview={!readOnly}
 										{model}
 										onTaskClick={async (e) => {
 											console.log(e);
@@ -819,28 +841,13 @@
 										onAddMessages={({ modelId, parentId, messages }) => {
 											addMessages({ modelId, parentId, messages });
 										}}
-										on:update={(e) => {
+										onSave={({ raw, oldContent, newContent }) => {
-											const { raw, oldContent, newContent } = e.detail;
-
 											history.messages[message.id].content = history.messages[
 												message.id
 											].content.replace(raw, raw.replace(oldContent, newContent));
 
 											updateChat();
 										}}
-										on:select={(e) => {
-											const { type, content } = e.detail;
-
-											if (type === 'explain') {
-												submitMessage(
-													message.id,
-													`Explain this section to me in more detail\n\n\`\`\`\n${content}\n\`\`\``
-												);
-											} else if (type === 'ask') {
-												const input = e.detail?.input ?? '';
-												submitMessage(message.id, `\`\`\`\n${content}\n\`\`\`\n${input}`);
-											}
-										}}
 									/>
 								{/if}
 
@@ -1394,11 +1401,11 @@
 														actionMessage(action.id, message);
 													}}
 												>
-													{#if action.icon_url}
+													{#if action?.icon}
 														<div class="size-4">
 															<img
-																src={action.icon_url}
+																src={action.icon}
-																class="w-4 h-4 {action.icon_url.includes('svg')
+																class="w-4 h-4 {action.icon.includes('svg')
 																	? 'dark:invert-[80%]'
 																	: ''}"
 																style="fill: currentColor;"

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

@@ -43,6 +43,8 @@
 
 	let edit = false;
 	let editedContent = '';
+	let editedFiles = [];
+
 	let messageEditTextAreaElement: HTMLTextAreaElement;
 
 	let message = JSON.parse(JSON.stringify(history.messages[messageId]));
@@ -62,6 +64,7 @@
 	const editMessageHandler = async () => {
 		edit = true;
 		editedContent = message.content;
+		editedFiles = message.files;
 
 		await tick();
 
@@ -74,15 +77,17 @@
 	};
 
 	const editMessageConfirmHandler = async (submit = true) => {
-		editMessage(message.id, editedContent, submit);
+		editMessage(message.id, { content: editedContent, files: editedFiles }, submit);
 
 		edit = false;
 		editedContent = '';
+		editedFiles = [];
 	};
 
 	const cancelEditMessage = () => {
 		edit = false;
 		editedContent = '';
+		editedFiles = [];
 	};
 
 	const deleteMessageHandler = async () => {
@@ -141,30 +146,90 @@
 		{/if}
 
 		<div class="chat-{message.role} w-full min-w-full markdown-prose">
-			{#if message.files}
+			{#if edit !== true}
-				<div class="mt-2.5 mb-1 w-full flex flex-col justify-end overflow-x-auto gap-1 flex-wrap">
+				{#if message.files}
-					{#each message.files as file}
+					<div class="mt-2.5 mb-1 w-full flex flex-col justify-end overflow-x-auto gap-1 flex-wrap">
-						<div class={($settings?.chatBubble ?? true) ? 'self-end' : ''}>
+						{#each message.files as file}
-							{#if file.type === 'image'}
+							<div class={($settings?.chatBubble ?? true) ? 'self-end' : ''}>
-								<Image src={file.url} imageClassName=" max-h-96 rounded-lg" />
+								{#if file.type === 'image'}
-							{:else}
+									<Image src={file.url} imageClassName=" max-h-96 rounded-lg" />
-								<FileItem
+								{:else}
-									item={file}
+									<FileItem
-									url={file.url}
+										item={file}
-									name={file.name}
+										url={file.url}
-									type={file.type}
+										name={file.name}
-									size={file?.size}
+										type={file.type}
-									colorClassName="bg-white dark:bg-gray-850 "
+										size={file?.size}
-								/>
+										colorClassName="bg-white dark:bg-gray-850 "
-							{/if}
+									/>
-						</div>
+								{/if}
-					{/each}
+							</div>
-				</div>
+						{/each}
+					</div>
+				{/if}
 			{/if}
 
 			{#if message.content !== ''}
 				{#if edit === true}
 					<div class=" w-full bg-gray-50 dark:bg-gray-800 rounded-3xl px-5 py-3 mb-2">
+						{#if (editedFiles ?? []).length > 0}
+							<div class="flex items-center flex-wrap gap-2 -mx-2 mb-1">
+								{#each editedFiles as file, fileIdx}
+									{#if file.type === 'image'}
+										<div class=" relative group">
+											<div class="relative flex items-center">
+												<Image
+													src={file.url}
+													alt="input"
+													imageClassName=" size-14 rounded-xl object-cover"
+												/>
+											</div>
+											<div class=" absolute -top-1 -right-1">
+												<button
+													class=" bg-white text-black border border-white rounded-full group-hover:visible invisible transition"
+													type="button"
+													on:click={() => {
+														editedFiles.splice(fileIdx, 1);
+
+														editedFiles = editedFiles;
+													}}
+												>
+													<svg
+														xmlns="http://www.w3.org/2000/svg"
+														viewBox="0 0 20 20"
+														fill="currentColor"
+														class="size-4"
+													>
+														<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>
+										</div>
+									{:else}
+										<FileItem
+											item={file}
+											name={file.name}
+											type={file.type}
+											size={file?.size}
+											loading={file.status === 'uploading'}
+											dismissible={true}
+											edit={true}
+											on:dismiss={async () => {
+												editedFiles.splice(fileIdx, 1);
+
+												editedFiles = editedFiles;
+											}}
+											on:click={() => {
+												console.log(file);
+											}}
+										/>
+									{/if}
+								{/each}
+							</div>
+						{/if}
+
 						<div class="max-h-96 overflow-auto">
 							<textarea
 								id="message-edit-{message.id}"

src/lib/components/chat/ModelSelector.svelte

@@ -114,7 +114,9 @@
 </div>
 
 {#if showSetDefault}
-	<div class=" absolute text-left mt-[1px] ml-1 text-[0.7rem] text-gray-500 font-primary">
+	<div
+		class="absolute text-left mt-[1px] ml-1 text-[0.7rem] text-gray-600 dark:text-gray-400 font-primary"
+	>
 		<button on:click={saveDefaultModel}> {$i18n.t('Set as default')}</button>
 	</div>
 {/if}

src/lib/components/chat/ModelSelector/Selector.svelte

@@ -100,10 +100,10 @@
 					.filter((item) => {
 						if (selectedConnectionType === '') {
 							return true;
-						} else if (selectedConnectionType === 'ollama') {
+						} else if (selectedConnectionType === 'local') {
-							return item.model?.owned_by === 'ollama';
+							return item.model?.connection_type === 'local';
-						} else if (selectedConnectionType === 'openai') {
+						} else if (selectedConnectionType === 'external') {
-							return item.model?.owned_by === 'openai';
+							return item.model?.connection_type === 'external';
 						} else if (selectedConnectionType === 'direct') {
 							return item.model?.direct;
 						}
@@ -118,10 +118,10 @@
 					.filter((item) => {
 						if (selectedConnectionType === '') {
 							return true;
-						} else if (selectedConnectionType === 'ollama') {
+						} else if (selectedConnectionType === 'local') {
-							return item.model?.owned_by === 'ollama';
+							return item.model?.connection_type === 'local';
-						} else if (selectedConnectionType === 'openai') {
+						} else if (selectedConnectionType === 'external') {
-							return item.model?.owned_by === 'openai';
+							return item.model?.connection_type === 'external';
 						} else if (selectedConnectionType === 'direct') {
 							return item.model?.direct;
 						}
@@ -393,7 +393,7 @@
 							class="flex gap-1 w-fit text-center text-sm font-medium rounded-full bg-transparent px-1.5 pb-0.5"
 							bind:this={tagsContainerElement}
 						>
-							{#if (items.find((item) => item.model?.owned_by === 'ollama') && items.find((item) => item.model?.owned_by === 'openai')) || items.find((item) => item.model?.direct) || tags.length > 0}
+							{#if (items.find((item) => item.model?.connection_type === 'local') && items.find((item) => item.model?.connection_type === 'external')) || items.find((item) => item.model?.direct) || tags.length > 0}
 								<button
 									class="min-w-fit outline-none p-1.5 {selectedTag === '' &&
 									selectedConnectionType === ''
@@ -408,25 +408,25 @@
 								</button>
 							{/if}
 
-							{#if items.find((item) => item.model?.owned_by === 'ollama') && items.find((item) => item.model?.owned_by === 'openai')}
+							{#if items.find((item) => item.model?.connection_type === 'local') && items.find((item) => item.model?.connection_type === 'external')}
 								<button
-									class="min-w-fit outline-none p-1.5 {selectedConnectionType === 'ollama'
+									class="min-w-fit outline-none p-1.5 {selectedConnectionType === 'local'
 										? ''
 										: 'text-gray-300 dark:text-gray-600 hover:text-gray-700 dark:hover:text-white'} transition capitalize"
 									on:click={() => {
 										selectedTag = '';
-										selectedConnectionType = 'ollama';
+										selectedConnectionType = 'local';
 									}}
 								>
 									{$i18n.t('Local')}
 								</button>
 								<button
-									class="min-w-fit outline-none p-1.5 {selectedConnectionType === 'openai'
+									class="min-w-fit outline-none p-1.5 {selectedConnectionType === 'external'
 										? ''
 										: 'text-gray-300 dark:text-gray-600 hover:text-gray-700 dark:hover:text-white'} transition capitalize"
 									on:click={() => {
 										selectedTag = '';
-										selectedConnectionType = 'openai';
+										selectedConnectionType = 'external';
 									}}
 								>
 									{$i18n.t('External')}

src/lib/components/chat/Placeholder.svelte

@@ -34,6 +34,8 @@
 	export let files = [];
 
 	export let selectedToolIds = [];
+	export let selectedFilterIds = [];
+
 	export let imageGenerationEnabled = false;
 	export let codeInterpreterEnabled = false;
 	export let webSearchEnabled = false;
@@ -192,6 +194,7 @@
 					bind:prompt
 					bind:autoScroll
 					bind:selectedToolIds
+					bind:selectedFilterIds
 					bind:imageGenerationEnabled
 					bind:codeInterpreterEnabled
 					bind:webSearchEnabled

src/lib/components/chat/Settings/Connections/Connection.svelte

@@ -62,7 +62,7 @@
 				class="absolute top-0 bottom-0 left-0 right-0 opacity-60 bg-white dark:bg-gray-900 z-10"
 			></div>
 		{/if}
-		<div class="flex w-full">
+		<div class="flex w-full gap-2">
 			<div class="flex-1 relative">
 				<input
 					class=" outline-hidden w-full bg-transparent {pipeline ? 'pr-8' : ''}"

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

@@ -32,6 +32,8 @@
 	let notificationSound = true;
 	let notificationSoundAlways = false;
 
+	let highContrastMode = false;
+
 	let detectArtifacts = true;
 
 	let richTextInput = true;
@@ -85,6 +87,11 @@
 		saveSettings({ splitLargeChunks: splitLargeChunks });
 	};
 
+	const toggleHighContrastMode = async () => {
+		highContrastMode = !highContrastMode;
+		saveSettings({ highContrastMode: highContrastMode });
+	};
+
 	const togglePromptAutocomplete = async () => {
 		promptAutocomplete = !promptAutocomplete;
 		saveSettings({ promptAutocomplete: promptAutocomplete });
@@ -281,6 +288,8 @@
 		titleAutoGenerate = $settings?.title?.auto ?? true;
 		autoTags = $settings.autoTags ?? true;
 
+		highContrastMode = $settings.highContrastMode ?? false;
+
 		detectArtifacts = $settings.detectArtifacts ?? true;
 		responseAutoCopy = $settings.responseAutoCopy ?? false;
 
@@ -370,6 +379,28 @@
 		<div>
 			<div class=" mb-1.5 text-sm font-medium">{$i18n.t('UI')}</div>
 
+			<div>
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs">
+						{$i18n.t('High Contrast Mode')} ({$i18n.t('Beta')})
+					</div>
+
+					<button
+						class="p-1 px-3 text-xs flex rounded-sm transition"
+						on:click={() => {
+							toggleHighContrastMode();
+						}}
+						type="button"
+					>
+						{#if highContrastMode === 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>
+
 			<div>
 				<div class=" py-0.5 flex w-full justify-between">
 					<div class=" self-center text-xs">{$i18n.t('Landing Page Mode')}</div>

src/lib/components/chat/ShortcutsModal.svelte

@@ -149,6 +149,23 @@
 				</div>
 
 				<div class="flex flex-col space-y-3 w-full self-start">
+					<div class="w-full flex justify-between items-center">
+						<div class=" text-sm">{$i18n.t('Toggle search')}</div>
+
+						<div class="flex space-x-1 text-xs">
+							<div
+								class=" h-fit py-1 px-2 flex items-center justify-center rounded-sm border border-black/10 capitalize text-gray-600 dark:border-white/10 dark:text-gray-300"
+							>
+								Ctrl/⌘
+							</div>
+							<div
+								class=" h-fit py-1 px-2 flex items-center justify-center rounded-sm border border-black/10 capitalize text-gray-600 dark:border-white/10 dark:text-gray-300"
+							>
+								K
+							</div>
+						</div>
+					</div>
+
 					<div class="w-full flex justify-between items-center">
 						<div class=" text-sm">{$i18n.t('Toggle settings')}</div>
 

src/lib/components/chat/Suggestions.svelte

@@ -64,7 +64,7 @@
 	}
 </script>
 
-<div class="mb-1 flex gap-1 text-xs font-medium items-center text-gray-400 dark:text-gray-600">
+<div class="mb-1 flex gap-1 text-xs font-medium items-center text-gray-600 dark:text-gray-400">
 	{#if filteredPrompts.length > 0}
 		<Bolt />
 		{$i18n.t('Suggested')}
@@ -74,7 +74,7 @@
 		<div
 			class="flex w-full {$settings?.landingPageMode === 'chat'
 				? ' -mt-1'
-				: 'text-center items-center justify-center'}  self-start text-gray-400 dark:text-gray-600"
+				: 'text-center items-center justify-center'}  self-start text-gray-600 dark:text-gray-400"
 		>
 			{$WEBUI_NAME} ‧ v{WEBUI_VERSION}
 		</div>
@@ -98,7 +98,7 @@
 						>
 							{prompt.title[0]}
 						</div>
-						<div class="text-xs text-gray-500 font-normal line-clamp-1">
+						<div class="text-xs text-gray-600 dark:text-gray-400 font-normal line-clamp-1">
 							{prompt.title[1]}
 						</div>
 					{:else}
@@ -107,7 +107,9 @@
 						>
 							{prompt.content}
 						</div>
-						<div class="text-xs text-gray-500 font-normal line-clamp-1">{$i18n.t('Prompt')}</div>
+						<div class="text-xs text-gray-600 dark:text-gray-400 font-normal line-clamp-1">
+							{$i18n.t('Prompt')}
+						</div>
 					{/if}
 				</div>
 			</button>