OpenWebUI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2025-06-08 15:37:22 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fix: rag duplicate collection issue

Browse Source
This commit is contained in:
Timothy J. Baek 2024-09-21 03:53:53 +02:00
parent aed8e2156f
commit ee6b1376c3
1 changed files with 26 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
backend/open_webui/apps/rag/main.py
View File

@ -1099,35 +1099,35 @@ def store_docs_in_vector_db(
log.info(f"deleting existing collection {collection_name}") log.info(f"deleting existing collection {collection_name}")
VECTOR_DB_CLIENT.delete_collection(collection_name=collection_name) VECTOR_DB_CLIENT.delete_collection(collection_name=collection_name)
embedding_function = get_embedding_function( if VECTOR_DB_CLIENT.has_collection(collection_name=collection_name):
app.state.config.RAG_EMBEDDING_ENGINE, log.info(f"collection {collection_name} already exists")
app.state.config.RAG_EMBEDDING_MODEL,
app.state.sentence_transformer_ef,
app.state.config.OPENAI_API_KEY,
app.state.config.OPENAI_API_BASE_URL,
app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
)
VECTOR_DB_CLIENT.insert(
collection_name=collection_name,
items=[
{
"id": str(uuid.uuid4()),
"text": text,
"vector": embedding_function(text.replace("\n", " ")),
"metadata": metadatas[idx],
}
for idx, text in enumerate(texts)
],
)
return True
except Exception as e:
if e.__class__.__name__ == "UniqueConstraintError":
return True return True
else:
embedding_function = get_embedding_function(
app.state.config.RAG_EMBEDDING_ENGINE,
app.state.config.RAG_EMBEDDING_MODEL,
app.state.sentence_transformer_ef,
app.state.config.OPENAI_API_KEY,
app.state.config.OPENAI_API_BASE_URL,
app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
)
VECTOR_DB_CLIENT.insert(
collection_name=collection_name,
items=[
{
"id": str(uuid.uuid4()),
"text": text,
"vector": embedding_function(text.replace("\n", " ")),
"metadata": metadatas[idx],
}
for idx, text in enumerate(texts)
],
)
return True
except Exception as e:
log.exception(e) log.exception(e)
return False return False