OpenWebUI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2025-05-19 04:43:00 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

add debug logging to RAG utils

Browse Source
This commit is contained in:
Robert Norberg 2025-04-08 12:08:32 -04:00
parent 63533c9e3a
commit 2337b36609
No known key found for this signature in database
GPG Key ID: E11589C8BED869F3
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
backend/open_webui/retrieval/utils.py
View File

@ -77,6 +77,7 @@ 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: try:
log.debug(f"query_doc:doc {collection_name}")
result = VECTOR_DB_CLIENT.search( result = VECTOR_DB_CLIENT.search(
collection_name=collection_name, collection_name=collection_name,
vectors=[query_embedding], vectors=[query_embedding],
@ -94,6 +95,7 @@ def query_doc(
def get_doc(collection_name: str, user: UserModel = None): def get_doc(collection_name: str, user: UserModel = None):
try: try:
log.debug(f"get_doc:doc {collection_name}")
result = VECTOR_DB_CLIENT.get(collection_name=collection_name) result = VECTOR_DB_CLIENT.get(collection_name=collection_name)
if result: if result:
@ -116,6 +118,7 @@ def query_doc_with_hybrid_search(
r: float, r: float,
) -> dict: ) -> dict:
try: try:
log.debug(f"query_doc_with_hybrid_search:doc {collection_name}")
bm25_retriever = BM25Retriever.from_texts( bm25_retriever = BM25Retriever.from_texts(
texts=collection_result.documents[0], texts=collection_result.documents[0],
metadatas=collection_result.metadatas[0], metadatas=collection_result.metadatas[0],
@ -168,6 +171,7 @@ def query_doc_with_hybrid_search(
) )
return result return result
except Exception as e: except Exception as e:
log.exception(f"Error querying doc {collection_name} with hybrid search: {e}")
raise e raise e
@ -257,6 +261,7 @@ def query_collection(
) -> dict: ) -> dict:
results = [] results = []
for query in queries: for query in queries:
log.debug(f"query_collection:query {query}")
query_embedding = embedding_function(query, prefix=RAG_EMBEDDING_QUERY_PREFIX) query_embedding = embedding_function(query, prefix=RAG_EMBEDDING_QUERY_PREFIX)
for collection_name in collection_names: for collection_name in collection_names:
if collection_name: if collection_name:
@ -292,6 +297,7 @@ def query_collection_with_hybrid_search(
collection_results = {} collection_results = {}
for collection_name in collection_names: for collection_name in collection_names:
try: try:
log.debug(f"query_collection_with_hybrid_search:VECTOR_DB_CLIENT.get:collection {collection_name}")
collection_results[collection_name] = VECTOR_DB_CLIENT.get( collection_results[collection_name] = VECTOR_DB_CLIENT.get(
collection_name=collection_name collection_name=collection_name
) )
@ -613,6 +619,7 @@ def generate_openai_batch_embeddings(
user: UserModel = None, user: UserModel = None,
) -> Optional[list[list[float]]]: ) -> Optional[list[list[float]]]:
try: try:
log.debug(f"generate_openai_batch_embeddings:model {model} batch size: {len(texts)}")
json_data = {"input": texts, "model": model} json_data = {"input": texts, "model": model}
if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str): if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix
@ -655,6 +662,7 @@ def generate_ollama_batch_embeddings(
user: UserModel = None, user: UserModel = None,
) -> Optional[list[list[float]]]: ) -> Optional[list[list[float]]]:
try: try:
log.debug(f"generate_ollama_batch_embeddings:model {model} batch size: {len(texts)}")
json_data = {"input": texts, "model": model} json_data = {"input": texts, "model": model}
if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str): if isinstance(RAG_EMBEDDING_PREFIX_FIELD_NAME, str) and isinstance(prefix, str):
json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix json_data[RAG_EMBEDDING_PREFIX_FIELD_NAME] = prefix