Merge branch 'open-webui:dev' into dev

backend/open_webui/functions.py

@@ -65,12 +65,12 @@ def get_function_module_by_id(request: Request, pipe_id: str):
     return function_module
 
 
-async def get_function_models():
+async def get_function_models(request):
     pipes = Functions.get_functions_by_type("pipe", active_only=True)
     pipe_models = []
 
     for pipe in pipes:
-        function_module = get_function_module_by_id(pipe.id)
+        function_module = get_function_module_by_id(request, pipe.id)
 
         # Check if function is a manifold
         if hasattr(function_module, "pipes"):
@@ -253,7 +253,7 @@ async def generate_function_chat_completion(
         form_data = apply_model_system_prompt_to_body(params, form_data, user)
 
     pipe_id = get_pipe_id(form_data)
-    function_module = get_function_module_by_id(pipe_id)
+    function_module = get_function_module_by_id(request, pipe_id)
 
     pipe = function_module.pipe
     params = get_function_params(function_module, form_data, user, extra_params)

backend/open_webui/retrieval/loaders/main.py

@@ -1,6 +1,7 @@
 import requests
 import logging
 import ftfy
+import sys
 
 from langchain_community.document_loaders import (
     BSHTMLLoader,
@@ -18,8 +19,9 @@ from langchain_community.document_loaders import (
     YoutubeLoader,
 )
 from langchain_core.documents import Document
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
 
+logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
@@ -106,7 +108,7 @@ class TikaLoader:
             if "Content-Type" in raw_metadata:
                 headers["Content-Type"] = raw_metadata["Content-Type"]
 
-            log.info("Tika extracted text: %s", text)
+            log.debug("Tika extracted text: %s", text)
 
             return [Document(page_content=text, metadata=headers)]
         else:

backend/open_webui/routers/files.py

@@ -5,6 +5,7 @@ from pathlib import Path
 from typing import Optional
 from pydantic import BaseModel
 import mimetypes
+from urllib.parse import quote
 
 from open_webui.storage.provider import Storage
 
@@ -222,11 +223,15 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
 
             # Check if the file already exists in the cache
             if file_path.is_file():
-                print(f"file_path: {file_path}")
+                # Handle Unicode filenames
+                filename = file.meta.get("name", file.filename)
+                encoded_filename = quote(filename)  # RFC5987 encoding
                 headers = {
-                    "Content-Disposition": f'attachment; filename="{file.meta.get("name", file.filename)}"'
+                    "Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"
                 }
+
                 return FileResponse(file_path, headers=headers)
+
             else:
                 raise HTTPException(
                     status_code=status.HTTP_404_NOT_FOUND,
@@ -283,16 +288,20 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
 
     if file and (file.user_id == user.id or user.role == "admin"):
         file_path = file.path
+
+        # Handle Unicode filenames
+        filename = file.meta.get("name", file.filename)
+        encoded_filename = quote(filename)  # RFC5987 encoding
+        headers = {
+            "Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"
+        }
+
         if file_path:
             file_path = Storage.get_file(file_path)
             file_path = Path(file_path)
 
             # Check if the file already exists in the cache
             if file_path.is_file():
-                print(f"file_path: {file_path}")
-                headers = {
-                    "Content-Disposition": f'attachment; filename="{file.meta.get("name", file.filename)}"'
-                }
                 return FileResponse(file_path, headers=headers)
             else:
                 raise HTTPException(
@@ -311,7 +320,7 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
             return StreamingResponse(
                 generator(),
                 media_type="text/plain",
-                headers={"Content-Disposition": f"attachment; filename={file_name}"},
+                headers=headers,
             )
     else:
         raise HTTPException(

backend/open_webui/routers/tasks.py

@@ -186,9 +186,10 @@ async def generate_title(
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:
+        log.error("Exception occurred", exc_info=True)
         return JSONResponse(
             status_code=status.HTTP_400_BAD_REQUEST,
-            content={"detail": str(e)},
+            content={"detail": "An internal error has occurred."},
         )
 
 
@@ -248,9 +249,10 @@ async def generate_chat_tags(
     try:
         return await generate_chat_completion(request, form_data=payload, user=user)
     except Exception as e:
+        log.error(f"Error generating chat completion: {e}")
         return JSONResponse(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            content={"detail": str(e)},
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            content={"detail": "An internal error has occurred."},
         )
 
 

backend/open_webui/socket/main.py

@@ -1,5 +1,3 @@
-# TODO: move socket to webui app
-
 import asyncio
 import socketio
 import logging

backend/open_webui/utils/middleware.py

@@ -362,7 +362,39 @@ async def chat_completion_files_handler(
     return body, {"sources": sources}
 
 
+def apply_params_to_form_data(form_data, model):
+    params = form_data.pop("params", {})
+    if model.get("ollama"):
+        form_data["options"] = params
+
+        if "format" in params:
+            form_data["format"] = params["format"]
+
+        if "keep_alive" in params:
+            form_data["keep_alive"] = params["keep_alive"]
+    else:
+        if "seed" in params:
+            form_data["seed"] = params["seed"]
+
+        if "stop" in params:
+            form_data["stop"] = params["stop"]
+
+        if "temperature" in params:
+            form_data["temperature"] = params["temperature"]
+
+        if "top_p" in params:
+            form_data["top_p"] = params["top_p"]
+
+        if "frequency_penalty" in params:
+            form_data["frequency_penalty"] = params["frequency_penalty"]
+
+    return form_data
+
+
 async def process_chat_payload(request, form_data, user, model):
+    form_data = apply_params_to_form_data(form_data, model)
+    log.debug(f"form_data: {form_data}")
+
     metadata = {
         "chat_id": form_data.pop("chat_id", None),
         "message_id": form_data.pop("id", None),

backend/open_webui/utils/models.py

@@ -52,7 +52,7 @@ async def get_all_base_models(request: Request):
             for model in ollama_models["models"]
         ]
 
-    function_models = await get_function_models()
+    function_models = await get_function_models(request)
     models = function_models + openai_models + ollama_models
 
     return models