gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

doc title fix

Browse source
This commit is contained in:
estevez.sebastian@gmail.com 2025-08-01 11:31:49 -04:00
parent 4fb6106ca0
commit 8f0ebbb968
2 changed files with 4 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
src/connectors/service.py
View file

@ -46,7 +46,8 @@ class ConnectorService:
result = await doc_service.process_file_common( result = await doc_service.process_file_common(
file_path=tmp_file.name, file_path=tmp_file.name,
file_hash=document.id, # Use connector document ID as hash file_hash=document.id, # Use connector document ID as hash
owner_user_id=owner_user_id owner_user_id=owner_user_id,
original_filename=document.filename # Pass the original Google Doc title
) )
# If successfully indexed, update the indexed documents with connector metadata # If successfully indexed, update the indexed documents with connector metadata

4
src/services/document_service.py
View file

@ -80,7 +80,7 @@ class DocumentService:
def __init__(self, process_pool=None): def __init__(self, process_pool=None):
self.process_pool = process_pool self.process_pool = process_pool
async def process_file_common(self, file_path: str, file_hash: str = None, owner_user_id: str = None): async def process_file_common(self, file_path: str, file_hash: str = None, owner_user_id: str = None, original_filename: str = None):
""" """
Common processing logic for both upload and upload_path. Common processing logic for both upload and upload_path.
1. Optionally compute SHA256 hash if not provided. 1. Optionally compute SHA256 hash if not provided.
@ -121,7 +121,7 @@ class DocumentService:
for i, (chunk, vect) in enumerate(zip(slim_doc["chunks"], embeddings)): for i, (chunk, vect) in enumerate(zip(slim_doc["chunks"], embeddings)):
chunk_doc = { chunk_doc = {
"document_id": file_hash, "document_id": file_hash,
"filename": slim_doc["filename"], "filename": original_filename if original_filename else slim_doc["filename"],
"mimetype": slim_doc["mimetype"], "mimetype": slim_doc["mimetype"],
"page": chunk["page"], "page": chunk["page"],
"text": chunk["text"], "text": chunk["text"],