Merge branch 'dev' into k_reranker

backend/open_webui/routers/audio.py

@@ -625,7 +625,9 @@ def transcription(
 ):
     log.info(f"file.content_type: {file.content_type}")
 
-    if file.content_type not in ["audio/mpeg", "audio/wav", "audio/ogg", "audio/x-m4a"]:
+    supported_filetypes = ("audio/mpeg", "audio/wav", "audio/ogg", "audio/x-m4a")
+
+    if not file.content_type.startswith(supported_filetypes):
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,

backend/open_webui/routers/auths.py

@@ -210,7 +210,7 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
             LDAP_APP_DN,
             LDAP_APP_PASSWORD,
             auto_bind="NONE",
-            authentication="SIMPLE",
+            authentication="SIMPLE" if LDAP_APP_DN else "ANONYMOUS",
         )
         if not connection_app.bind():
             raise HTTPException(400, detail="Application account bind failed")

backend/open_webui/routers/chats.py

@@ -2,6 +2,8 @@ import json
 import logging
 from typing import Optional
 
+
+from open_webui.socket.main import get_event_emitter
 from open_webui.models.chats import (
     ChatForm,
     ChatImportForm,
@@ -372,6 +374,107 @@ async def update_chat_by_id(
         )
 
 
+############################
+# UpdateChatMessageById
+############################
+class MessageForm(BaseModel):
+    content: str
+
+
+@router.post("/{id}/messages/{message_id}", response_model=Optional[ChatResponse])
+async def update_chat_message_by_id(
+    id: str, message_id: str, form_data: MessageForm, user=Depends(get_verified_user)
+):
+    chat = Chats.get_chat_by_id(id)
+
+    if not chat:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    if chat.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    chat = Chats.upsert_message_to_chat_by_id_and_message_id(
+        id,
+        message_id,
+        {
+            "content": form_data.content,
+        },
+    )
+
+    event_emitter = get_event_emitter(
+        {
+            "user_id": user.id,
+            "chat_id": id,
+            "message_id": message_id,
+        },
+        False,
+    )
+
+    if event_emitter:
+        await event_emitter(
+            {
+                "type": "chat:message",
+                "data": {
+                    "chat_id": id,
+                    "message_id": message_id,
+                    "content": form_data.content,
+                },
+            }
+        )
+
+    return ChatResponse(**chat.model_dump())
+
+
+############################
+# SendChatMessageEventById
+############################
+class EventForm(BaseModel):
+    type: str
+    data: dict
+
+
+@router.post("/{id}/messages/{message_id}/event", response_model=Optional[bool])
+async def send_chat_message_event_by_id(
+    id: str, message_id: str, form_data: EventForm, user=Depends(get_verified_user)
+):
+    chat = Chats.get_chat_by_id(id)
+
+    if not chat:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    if chat.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    event_emitter = get_event_emitter(
+        {
+            "user_id": user.id,
+            "chat_id": id,
+            "message_id": message_id,
+        }
+    )
+
+    try:
+        if event_emitter:
+            await event_emitter(form_data.model_dump())
+        else:
+            return False
+        return True
+    except:
+        return False
+
+
 ############################
 # DeleteChatById
 ############################

backend/open_webui/routers/files.py

@@ -81,7 +81,7 @@ def upload_file(
                     ProcessFileForm(file_id=id, content=result.get("text", "")),
                     user=user,
                 )
-            else:
+            elif file.content_type not in ["image/png", "image/jpeg", "image/gif"]:
                 process_file(request, ProcessFileForm(file_id=id), user=user)
 
             file_item = Files.get_file_by_id(id=id)

backend/open_webui/routers/images.py

@@ -517,10 +517,8 @@ async def image_generations(
             images = []
 
             for image in res["data"]:
-                if "url" in image:
-                    image_data, content_type = load_url_image_data(
-                        image["url"], headers
-                    )
+                if image_url := image.get("url", None):
+                    image_data, content_type = load_url_image_data(image_url, headers)
                 else:
                     image_data, content_type = load_b64_image_data(image["b64_json"])
 

backend/open_webui/routers/knowledge.py

@@ -437,14 +437,24 @@ def remove_file_from_knowledge_by_id(
         )
 
     # Remove content from the vector database
-    VECTOR_DB_CLIENT.delete(
-        collection_name=knowledge.id, filter={"file_id": form_data.file_id}
-    )
+    try:
+        VECTOR_DB_CLIENT.delete(
+            collection_name=knowledge.id, filter={"file_id": form_data.file_id}
+        )
+    except Exception as e:
+        log.debug("This was most likely caused by bypassing embedding processing")
+        log.debug(e)
+        pass
 
-    # Remove the file's collection from vector database
-    file_collection = f"file-{form_data.file_id}"
-    if VECTOR_DB_CLIENT.has_collection(collection_name=file_collection):
-        VECTOR_DB_CLIENT.delete_collection(collection_name=file_collection)
+    try:
+        # Remove the file's collection from vector database
+        file_collection = f"file-{form_data.file_id}"
+        if VECTOR_DB_CLIENT.has_collection(collection_name=file_collection):
+            VECTOR_DB_CLIENT.delete_collection(collection_name=file_collection)
+    except Exception as e:
+        log.debug("This was most likely caused by bypassing embedding processing")
+        log.debug(e)
+        pass
 
     # Delete file from database
     Files.delete_file_by_id(form_data.file_id)

backend/open_webui/routers/ollama.py

@@ -295,7 +295,7 @@ async def update_config(
     }
 
 
-@cached(ttl=3)
+@cached(ttl=1)
 async def get_all_models(request: Request, user: UserModel = None):
     log.info("get_all_models()")
     if request.app.state.config.ENABLE_OLLAMA_API:
@@ -336,6 +336,7 @@ async def get_all_models(request: Request, user: UserModel = None):
                 )
 
                 prefix_id = api_config.get("prefix_id", None)
+                tags = api_config.get("tags", [])
                 model_ids = api_config.get("model_ids", [])
 
                 if len(model_ids) != 0 and "models" in response:
@@ -350,6 +351,10 @@ async def get_all_models(request: Request, user: UserModel = None):
                     for model in response.get("models", []):
                         model["model"] = f"{prefix_id}.{model['model']}"
 
+                if tags:
+                    for model in response.get("models", []):
+                        model["tags"] = tags
+
         def merge_models_lists(model_lists):
             merged_models = {}
 
@@ -1164,7 +1169,7 @@ async def generate_chat_completion(
     prefix_id = api_config.get("prefix_id", None)
     if prefix_id:
         payload["model"] = payload["model"].replace(f"{prefix_id}.", "")
-
+    # payload["keep_alive"] = -1 # keep alive forever
     return await send_post_request(
         url=f"{url}/api/chat",
         payload=json.dumps(payload),

backend/open_webui/routers/openai.py

@@ -36,6 +36,9 @@ from open_webui.utils.payload import (
     apply_model_params_to_body_openai,
     apply_model_system_prompt_to_body,
 )
+from open_webui.utils.misc import (
+    convert_logit_bias_input_to_json,
+)
 
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.utils.access_control import has_access
@@ -350,6 +353,7 @@ async def get_all_models_responses(request: Request, user: UserModel) -> list:
             )
 
             prefix_id = api_config.get("prefix_id", None)
+            tags = api_config.get("tags", [])
 
             if prefix_id:
                 for model in (
@@ -357,6 +361,12 @@ async def get_all_models_responses(request: Request, user: UserModel) -> list:
                 ):
                     model["id"] = f"{prefix_id}.{model['id']}"
 
+            if tags:
+                for model in (
+                    response if isinstance(response, list) else response.get("data", [])
+                ):
+                    model["tags"] = tags
+
     log.debug(f"get_all_models:responses() {responses}")
     return responses
 
@@ -374,7 +384,7 @@ async def get_filtered_models(models, user):
     return filtered_models
 
 
-@cached(ttl=3)
+@cached(ttl=1)
 async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
     log.info("get_all_models()")
 
@@ -396,6 +406,7 @@ async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
 
         for idx, models in enumerate(model_lists):
             if models is not None and "error" not in models:
+
                 merged_list.extend(
                     [
                         {
@@ -406,18 +417,21 @@ async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
                             "urlIdx": idx,
                         }
                         for model in models
-                        if "api.openai.com"
-                        not in request.app.state.config.OPENAI_API_BASE_URLS[idx]
-                        or not any(
-                            name in model["id"]
-                            for name in [
-                                "babbage",
-                                "dall-e",
-                                "davinci",
-                                "embedding",
-                                "tts",
-                                "whisper",
-                            ]
+                        if (model.get("id") or model.get("name"))
+                        and (
+                            "api.openai.com"
+                            not in request.app.state.config.OPENAI_API_BASE_URLS[idx]
+                            or not any(
+                                name in model["id"]
+                                for name in [
+                                    "babbage",
+                                    "dall-e",
+                                    "davinci",
+                                    "embedding",
+                                    "tts",
+                                    "whisper",
+                                ]
+                            )
                         )
                     ]
                 )
@@ -666,6 +680,11 @@ async def generate_chat_completion(
         del payload["max_tokens"]
 
     # Convert the modified body back to JSON
+    if "logit_bias" in payload:
+        payload["logit_bias"] = json.loads(
+            convert_logit_bias_input_to_json(payload["logit_bias"])
+        )
+
     payload = json.dumps(payload)
 
     r = None

backend/open_webui/routers/pipelines.py

@@ -90,8 +90,8 @@ async def process_pipeline_inlet_filter(request, payload, user, models):
                     headers=headers,
                     json=request_data,
                 ) as response:
-                    response.raise_for_status()
                     payload = await response.json()
+                    response.raise_for_status()
             except aiohttp.ClientResponseError as e:
                 res = (
                     await response.json()
@@ -139,8 +139,8 @@ async def process_pipeline_outlet_filter(request, payload, user, models):
                     headers=headers,
                     json=request_data,
                 ) as response:
-                    response.raise_for_status()
                     payload = await response.json()
+                    response.raise_for_status()
             except aiohttp.ClientResponseError as e:
                 try:
                     res = (

backend/open_webui/routers/retrieval.py

@@ -358,6 +358,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         "content_extraction": {
             "engine": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
             "tika_server_url": request.app.state.config.TIKA_SERVER_URL,
+            "docling_server_url": request.app.state.config.DOCLING_SERVER_URL,
             "document_intelligence_config": {
                 "endpoint": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
                 "key": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
@@ -428,6 +429,7 @@ class DocumentIntelligenceConfigForm(BaseModel):
 class ContentExtractionConfig(BaseModel):
     engine: str = ""
     tika_server_url: Optional[str] = None
+    docling_server_url: Optional[str] = None
     document_intelligence_config: Optional[DocumentIntelligenceConfigForm] = None
 
 
@@ -540,6 +542,9 @@ async def update_rag_config(
         request.app.state.config.TIKA_SERVER_URL = (
             form_data.content_extraction.tika_server_url
         )
+        request.app.state.config.DOCLING_SERVER_URL = (
+            form_data.content_extraction.docling_server_url
+        )
         if form_data.content_extraction.document_intelligence_config is not None:
             request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = (
                 form_data.content_extraction.document_intelligence_config.endpoint
@@ -648,6 +653,7 @@ async def update_rag_config(
         "content_extraction": {
             "engine": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
             "tika_server_url": request.app.state.config.TIKA_SERVER_URL,
+            "docling_server_url": request.app.state.config.DOCLING_SERVER_URL,
             "document_intelligence_config": {
                 "endpoint": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
                 "key": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
@@ -994,6 +1000,7 @@ def process_file(
                 loader = Loader(
                     engine=request.app.state.config.CONTENT_EXTRACTION_ENGINE,
                     TIKA_SERVER_URL=request.app.state.config.TIKA_SERVER_URL,
+                    DOCLING_SERVER_URL=request.app.state.config.DOCLING_SERVER_URL,
                     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/users.py

@@ -2,6 +2,7 @@ import logging
 from typing import Optional
 
 from open_webui.models.auths import Auths
+from open_webui.models.groups import Groups
 from open_webui.models.chats import Chats
 from open_webui.models.users import (
     UserModel,
@@ -17,7 +18,10 @@ from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import SRC_LOG_LEVELS
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from pydantic import BaseModel
+
 from open_webui.utils.auth import get_admin_user, get_password_hash, get_verified_user
+from open_webui.utils.access_control import get_permissions
+
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -45,7 +49,7 @@ async def get_users(
 
 @router.get("/groups")
 async def get_user_groups(user=Depends(get_verified_user)):
-    return Users.get_user_groups(user.id)
+    return Groups.get_groups_by_member_id(user.id)
 
 
 ############################
@@ -54,8 +58,12 @@ async def get_user_groups(user=Depends(get_verified_user)):
 
 
 @router.get("/permissions")
-async def get_user_permissisions(user=Depends(get_verified_user)):
-    return Users.get_user_groups(user.id)
+async def get_user_permissisions(request: Request, user=Depends(get_verified_user)):
+    user_permissions = get_permissions(
+        user.id, request.app.state.config.USER_PERMISSIONS
+    )
+
+    return user_permissions
 
 
 ############################
@@ -89,7 +97,7 @@ class UserPermissions(BaseModel):
 
 
 @router.get("/default/permissions", response_model=UserPermissions)
-async def get_user_permissions(request: Request, user=Depends(get_admin_user)):
+async def get_default_user_permissions(request: Request, user=Depends(get_admin_user)):
     return {
         "workspace": WorkspacePermissions(
             **request.app.state.config.USER_PERMISSIONS.get("workspace", {})
@@ -104,7 +112,7 @@ async def get_user_permissions(request: Request, user=Depends(get_admin_user)):
 
 
 @router.post("/default/permissions")
-async def update_user_permissions(
+async def update_default_user_permissions(
     request: Request, form_data: UserPermissions, user=Depends(get_admin_user)
 ):
     request.app.state.config.USER_PERMISSIONS = form_data.model_dump()