chore: format

backend/open_webui/retrieval/utils.py

@@ -17,7 +17,11 @@ from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
 from open_webui.utils.misc import get_last_user_message
 from open_webui.models.users import UserModel
 
-from open_webui.env import SRC_LOG_LEVELS, OFFLINE_MODE, ENABLE_FORWARD_USER_INFO_HEADERS
+from open_webui.env import (
+    SRC_LOG_LEVELS,
+    OFFLINE_MODE,
+    ENABLE_FORWARD_USER_INFO_HEADERS,
+)
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
@@ -62,10 +66,7 @@ class VectorSearchRetriever(BaseRetriever):
 
 
 def query_doc(
-    collection_name: str,
-    query_embedding: list[float],
-    k: int,
-    user: UserModel=None
+    collection_name: str, query_embedding: list[float], k: int, user: UserModel = None
 ):
     try:
         result = VECTOR_DB_CLIENT.search(
@@ -258,7 +259,7 @@ def get_embedding_function(
     embedding_function,
     url,
     key,
-    embedding_batch_size
+    embedding_batch_size,
 ):
     if embedding_engine == "":
         return lambda query, user=None: embedding_function.encode(query).tolist()
@@ -269,14 +270,16 @@ def get_embedding_function(
             text=query,
             url=url,
             key=key,
-            user=user
+            user=user,
         )
 
         def generate_multiple(query, user, func):
             if isinstance(query, list):
                 embeddings = []
                 for i in range(0, len(query), embedding_batch_size):
-                    embeddings.extend(func(query[i : i + embedding_batch_size], user=user))
+                    embeddings.extend(
+                        func(query[i : i + embedding_batch_size], user=user)
+                    )
                 return embeddings
             else:
                 return func(query, user)
@@ -428,7 +431,11 @@ def get_model_path(model: str, update_model: bool = False):
 
 
 def generate_openai_batch_embeddings(
-    model: str, texts: list[str], url: str = "https://api.openai.com/v1", key: str = "", user: UserModel = None
+    model: str,
+    texts: list[str],
+    url: str = "https://api.openai.com/v1",
+    key: str = "",
+    user: UserModel = None,
 ) -> Optional[list[list[float]]]:
     try:
         r = requests.post(
@@ -506,7 +513,13 @@ def generate_embeddings(engine: str, model: str, text: Union[str, list[str]], **
             )
         else:
             embeddings = generate_ollama_batch_embeddings(
-                **{"model": model, "texts": [text], "url": url, "key": key, "user": user}
+                **{
+                    "model": model,
+                    "texts": [text],
+                    "url": url,
+                    "key": key,
+                    "user": user,
+                }
             )
         return embeddings[0] if isinstance(text, str) else embeddings
     elif engine == "openai":

backend/open_webui/retrieval/web/exa.py

@@ -46,7 +46,9 @@ def search_exa(
     }
 
     try:
-        response = requests.post(f"{EXA_API_BASE}/search", headers=headers, json=payload)
+        response = requests.post(
+            f"{EXA_API_BASE}/search", headers=headers, json=payload
+        )
         response.raise_for_status()
         data = response.json()
 

backend/open_webui/routers/files.py

@@ -195,7 +195,7 @@ async def update_file_data_content_by_id(
             process_file(
                 request,
                 ProcessFileForm(file_id=id, content=form_data.content),
-                user=user
+                user=user,
             )
             file = Files.get_file_by_id(id=id)
         except Exception as e:

backend/open_webui/routers/knowledge.py

@@ -291,7 +291,7 @@ def add_file_to_knowledge_by_id(
         process_file(
             request,
             ProcessFileForm(file_id=form_data.file_id, collection_name=id),
-            user=user
+            user=user,
         )
     except Exception as e:
         log.debug(e)
@@ -376,7 +376,7 @@ def update_file_from_knowledge_by_id(
         process_file(
             request,
             ProcessFileForm(file_id=form_data.file_id, collection_name=id),
-            user=user
+            user=user,
         )
     except Exception as e:
         raise HTTPException(

backend/open_webui/routers/memories.py

@@ -160,7 +160,9 @@ async def update_memory_by_id(
                 {
                     "id": memory.id,
                     "text": memory.content,
-                    "vector": request.app.state.EMBEDDING_FUNCTION(memory.content, user),
+                    "vector": request.app.state.EMBEDDING_FUNCTION(
+                        memory.content, user
+                    ),
                     "metadata": {
                         "created_at": memory.created_at,
                         "updated_at": memory.updated_at,

backend/open_webui/routers/retrieval.py

@@ -666,7 +666,7 @@ def save_docs_to_vector_db(
     overwrite: bool = False,
     split: bool = True,
     add: bool = False,
-    user = None,
+    user=None,
 ) -> bool:
     def _get_docs_info(docs: list[Document]) -> str:
         docs_info = set()
@@ -782,8 +782,7 @@ def save_docs_to_vector_db(
         )
 
         embeddings = embedding_function(
-            list(map(lambda x: x.replace("\n", " "), texts)),
-            user = user
+            list(map(lambda x: x.replace("\n", " "), texts)), user=user
         )
 
         items = [
@@ -941,7 +940,7 @@ def process_file(
                     "hash": hash,
                 },
                 add=(True if form_data.collection_name else False),
-                user=user
+                user=user,
             )
 
             if result:
@@ -1032,7 +1031,9 @@ def process_youtube_video(
         content = " ".join([doc.page_content for doc in docs])
         log.debug(f"text_content: {content}")
 
-        save_docs_to_vector_db(request, docs, collection_name, overwrite=True, user=user)
+        save_docs_to_vector_db(
+            request, docs, collection_name, overwrite=True, user=user
+        )
 
         return {
             "status": True,
@@ -1073,7 +1074,9 @@ def process_web(
         content = " ".join([doc.page_content for doc in docs])
 
         log.debug(f"text_content: {content}")
-        save_docs_to_vector_db(request, docs, collection_name, overwrite=True, user=user)
+        save_docs_to_vector_db(
+            request, docs, collection_name, overwrite=True, user=user
+        )
 
         return {
             "status": True,
@@ -1289,7 +1292,9 @@ def process_web_search(
             requests_per_second=request.app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
         )
         docs = loader.load()
-        save_docs_to_vector_db(request, docs, collection_name, overwrite=True, user=user)
+        save_docs_to_vector_db(
+            request, docs, collection_name, overwrite=True, user=user
+        )
 
         return {
             "status": True,
@@ -1323,7 +1328,9 @@ def query_doc_handler(
             return query_doc_with_hybrid_search(
                 collection_name=form_data.collection_name,
                 query=form_data.query,
-                embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(query, user=user),
+                embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(
+                    query, user=user
+                ),
                 k=form_data.k if form_data.k else request.app.state.config.TOP_K,
                 reranking_function=request.app.state.rf,
                 r=(
@@ -1331,14 +1338,16 @@ def query_doc_handler(
                     if form_data.r
                     else request.app.state.config.RELEVANCE_THRESHOLD
                 ),
-                user=user
+                user=user,
             )
         else:
             return query_doc(
                 collection_name=form_data.collection_name,
-                query_embedding=request.app.state.EMBEDDING_FUNCTION(form_data.query, user=user),
+                query_embedding=request.app.state.EMBEDDING_FUNCTION(
+                    form_data.query, user=user
+                ),
                 k=form_data.k if form_data.k else request.app.state.config.TOP_K,
-                user=user
+                user=user,
             )
     except Exception as e:
         log.exception(e)
@@ -1367,7 +1376,9 @@ def query_collection_handler(
             return query_collection_with_hybrid_search(
                 collection_names=form_data.collection_names,
                 queries=[form_data.query],
-                embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(query, user=user),
+                embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(
+                    query, user=user
+                ),
                 k=form_data.k if form_data.k else request.app.state.config.TOP_K,
                 reranking_function=request.app.state.rf,
                 r=(
@@ -1380,7 +1391,9 @@ def query_collection_handler(
             return query_collection(
                 collection_names=form_data.collection_names,
                 queries=[form_data.query],
-                embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(query,user=user),
+                embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(
+                    query, user=user
+                ),
                 k=form_data.k if form_data.k else request.app.state.config.TOP_K,
             )
 

backend/open_webui/utils/middleware.py

@@ -634,7 +634,9 @@ async def chat_completion_files_handler(
                     lambda: get_sources_from_files(
                         files=files,
                         queries=queries,
-                        embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(query,user=user),
+                        embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(
+                            query, user=user
+                        ),
                         k=request.app.state.config.TOP_K,
                         reranking_function=request.app.state.rf,
                         r=request.app.state.config.RELEVANCE_THRESHOLD,