Merge pull request open-webui#12524 from open-webui/dev

0.6.2

Author: tjbck

.github/dependabot.yml

@@ -1,12 +1,26 @@
 version: 2
 updates:
+  - package-ecosystem: uv
+    directory: '/'
+    schedule:
+      interval: monthly
+    target-branch: 'dev'
+
   - package-ecosystem: pip
     directory: '/backend'
     schedule:
       interval: monthly
     target-branch: 'dev'
+
+  - package-ecosystem: npm
+    directory: '/'
+    schedule:
+      interval: monthly
+    target-branch: 'dev'
+
   - package-ecosystem: 'github-actions'
     directory: '/'
     schedule:
       # Check for updates to GitHub Actions every week
       interval: monthly
+    target-branch: 'dev'

.github/workflows/format-backend.yaml

@@ -5,10 +5,18 @@ on:
     branches:
       - main
       - dev
+    paths:
+      - 'backend/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
   pull_request:
     branches:
       - main
       - dev
+    paths:
+      - 'backend/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
 
 jobs:
   build:
@@ -17,15 +25,17 @@ jobs:
 
     strategy:
       matrix:
-        python-version: [3.11]
+        python-version:
+          - 3.11.x
+          - 3.12.x
 
     steps:
       - uses: actions/checkout@v4
 
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: '${{ matrix.python-version }}'
 
       - name: Install dependencies
         run: |

.github/workflows/format-build-frontend.yaml

@@ -5,10 +5,18 @@ on:
     branches:
       - main
       - dev
+    paths-ignore:
+      - 'backend/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
   pull_request:
     branches:
       - main
       - dev
+    paths-ignore:
+      - 'backend/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
 
 jobs:
   build:
@@ -21,7 +29,7 @@ jobs:
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: '22' # Or specify any other version you want to use
+          node-version: '22'
 
       - name: Install Dependencies
         run: npm install

CHANGELOG.md

@@ -5,6 +5,23 @@ 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).
 
+## [0.6.2] - 2025-04-06
+
+### Added
+
+- 🌍 **Improved Global Language Support**: Expanded and refined translations across multiple languages to enhance clarity and consistency for international users.
+
+### Fixed
+
+- 🛠️ **Accurate Tool Descriptions from OpenAPI Servers**: External tools now use full endpoint descriptions instead of summaries when generating tool specifications—helping AI models understand tool purpose more precisely and choose the right tool more accurately in tool workflows.
+- 🔧 **Precise Web Results Source Attribution**: Fixed a key issue where all web search results showed the same source ID—now each result gets its correct and distinct source, ensuring accurate citations and traceability.
+- 🔍 **Clean Web Search Retrieval**: Web search now retains only results from URLs where real content was successfully fetched—improving accuracy and removing empty or broken links from citations.
+- 🎵 **Audio File Upload Response Restored**: Resolved an issue where uploading audio files did not return valid responses, restoring smooth file handling for transcription and audio-based workflows.
+
+### Changed
+
+- 🧰 **General Backend Refactoring**: Multiple behind-the-scenes improvements streamline backend performance, reduce complexity, and ensure a more stable, maintainable system overall—making everything smoother without changing your workflow.
+
 ## [0.6.1] - 2025-04-05
 
 ### Added

backend/open_webui/retrieval/utils.py

@@ -357,7 +357,7 @@ def get_embedding_function(
 ):
     if embedding_engine == "":
         return lambda query, prefix=None, user=None: embedding_function.encode(
-            query, prompt=prefix if prefix else None
+            query, **({"prompt": prefix} if prefix else {})
         ).tolist()
     elif embedding_engine in ["ollama", "openai"]:
         func = lambda query, prefix=None, user=None: generate_embeddings(

backend/open_webui/routers/files.py

@@ -122,14 +122,16 @@ def upload_file(
                 ]:
                     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"]:
                     process_file(request, ProcessFileForm(file_id=id), user=user)
-                    file_item = Files.get_file_by_id(id=id)
+
+                file_item = Files.get_file_by_id(id=id)
             except Exception as e:
                 log.exception(e)
                 log.error(f"Error processing file: {file_item.id}")
@@ -162,11 +164,16 @@ def upload_file(
 
 
 @router.get("/", response_model=list[FileModelResponse])
-async def list_files(user=Depends(get_verified_user)):
+async def list_files(user=Depends(get_verified_user), content: bool = Query(True)):
     if user.role == "admin":
         files = Files.get_files()
     else:
         files = Files.get_files_by_user_id(user.id)
+
+    if not content:
+        for file in files:
+            del file.data["content"]
+
     return files
 
 

backend/open_webui/routers/retrieval.py

@@ -150,8 +150,8 @@ def get_rf(
                     device=DEVICE_TYPE,
                     trust_remote_code=RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
                 )
-            except:
-                log.error("CrossEncoder error")
+            except Exception as e:
+                log.error(f"CrossEncoder: {e}")
                 raise Exception(ERROR_MESSAGES.DEFAULT("CrossEncoder error"))
     return rf
 
@@ -174,7 +174,7 @@ class ProcessUrlForm(CollectionNameForm):
     url: str
 
 
-class SearchForm(CollectionNameForm):
+class SearchForm(BaseModel):
     query: str
 
 
@@ -958,7 +958,7 @@ def process_file(
 
         if form_data.content:
             # Update the content in the file
-            # Usage: /files/{file_id}/data/content/update
+            # Usage: /files/{file_id}/data/content/update, /files/ (audio file upload pipeline)
 
             try:
                 # /files/{file_id}/data/content/update
@@ -1464,12 +1464,6 @@ async def process_web_search(
     log.debug(f"web_results: {web_results}")
 
     try:
-        collection_name = form_data.collection_name
-        if collection_name == "" or collection_name is None:
-            collection_name = f"web-search-{calculate_sha256_string(form_data.query)}"[
-                :63
-            ]
-
         urls = [result.link for result in web_results]
         loader = get_web_loader(
             urls,
@@ -1478,6 +1472,9 @@ async def process_web_search(
             trust_env=request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV,
         )
         docs = await loader.aload()
+        urls = [
+            doc.metadata["source"] for doc in docs
+        ]  # only keep URLs which could be retrieved
 
         if request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL:
             return {
@@ -1494,18 +1491,26 @@ async def process_web_search(
                 "loaded_count": len(docs),
             }
         else:
-            await run_in_threadpool(
-                save_docs_to_vector_db,
-                request,
-                docs,
-                collection_name,
-                overwrite=True,
-                user=user,
-            )
+            collection_names = []
+            for doc_idx, doc in enumerate(docs):
+                collection_name = f"web-search-{calculate_sha256_string(form_data.query + '-' + urls[doc_idx])}"[
+                    :63
+                ]
+
+                collection_names.append(collection_name)
+
+                await run_in_threadpool(
+                    save_docs_to_vector_db,
+                    request,
+                    [doc],
+                    collection_name,
+                    overwrite=True,
+                    user=user,
+                )
 
             return {
                 "status": True,
-                "collection_name": collection_name,
+                "collection_names": collection_names,
                 "filenames": urls,
                 "loaded_count": len(docs),
             }

backend/open_webui/utils/middleware.py

@@ -399,24 +399,44 @@ async def chat_web_search_handler(
                 all_results.append(results)
                 files = form_data.get("files", [])
 
-                if results.get("collection_name"):
-                    files.append(
-                        {
-                            "collection_name": results["collection_name"],
-                            "name": searchQuery,
-                            "type": "web_search",
-                            "urls": results["filenames"],
-                        }
-                    )
+                if results.get("collection_names"):
+                    for col_idx, collection_name in enumerate(
+                        results.get("collection_names")
+                    ):
+                        files.append(
+                            {
+                                "collection_name": collection_name,
+                                "name": searchQuery,
+                                "type": "web_search",
+                                "urls": [results["filenames"][col_idx]],
+                            }
+                        )
                 elif results.get("docs"):
-                    files.append(
-                        {
-                            "docs": results.get("docs", []),
-                            "name": searchQuery,
-                            "type": "web_search",
-                            "urls": results["filenames"],
-                        }
-                    )
+                    # Invoked when bypass embedding and retrieval is set to True
+                    docs = results["docs"]
+
+                    if len(docs) == len(results["filenames"]):
+                        # the number of docs and filenames (urls) should be the same
+                        for doc_idx, doc in enumerate(docs):
+                            files.append(
+                                {
+                                    "docs": [doc],
+                                    "name": searchQuery,
+                                    "type": "web_search",
+                                    "urls": [results["filenames"][doc_idx]],
+                                }
+                            )
+                    else:
+                        # edge case when the number of docs and filenames (urls) are not the same
+                        # this should not happen, but if it does, we will just append the docs
+                        files.append(
+                            {
+                                "docs": results.get("docs", []),
+                                "name": searchQuery,
+                                "type": "web_search",
+                                "urls": results["filenames"],
+                            }
+                        )
 
                 form_data["files"] = files
         except Exception as e:

backend/open_webui/utils/tools.py

@@ -337,7 +337,9 @@ def convert_openapi_to_tool_payload(openapi_spec):
             tool = {
                 "type": "function",
                 "name": operation.get("operationId"),
-                "description": operation.get("summary", "No description available."),
+                "description": operation.get(
+                    "description", operation.get("summary", "No description available.")
+                ),
                 "parameters": {"type": "object", "properties": {}, "required": []},
             }
 

backend/requirements.txt

@@ -54,6 +54,7 @@ elasticsearch==8.17.1
 
 transformers
 sentence-transformers==3.3.1
+accelerate
 colbert-ai==0.2.21
 einops==0.8.1