yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-11-29 08:26:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into pick-trunk-by-vector

Browse Source
This commit is contained in:
yangdx 2025-08-14 05:34:15 +08:00
commit cb122c63e4
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
lightrag/api/routers/document_routes.py
View File

@ -811,20 +811,20 @@ async def pipeline_enqueue_file(
# Validate content
if not content or len(content.strip()) == 0:
logger.error(f"Empty content in file: {file_path.name}")
return False
return False, ""
# Check if content looks like binary data string representation
if content.startswith("b'") or content.startswith('b"'):
logger.error(
f"File {file_path.name} appears to contain binary data representation instead of text"
)
return False
return False, ""
except UnicodeDecodeError:
logger.error(
f"File {file_path.name} is not valid UTF-8 encoded text. Please convert it to UTF-8 before processing."
)
return False
return False, ""
case ".pdf":
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
@ -920,7 +920,7 @@ async def pipeline_enqueue_file(
logger.error(
f"Unsupported file type: {file_path.name} (extension {ext})"
)
return False
return False, ""
# Insert into the RAG queue
if content:
@ -942,6 +942,7 @@ async def pipeline_enqueue_file(
return True, track_id
else:
logger.error(f"No content could be extracted from file: {file_path.name}")
return False, ""
except Exception as e:
logger.error(f"Error processing or enqueueing file {file_path.name}: {str(e)}")