Add default file_path for missing document paths

- Set file_path to "no-file-path" if missing
- Ensure consistent document data structure
This commit is contained in:
yangdx
2025-03-18 20:06:18 +08:00
parent c42f08c0e6
commit 20de4ded30

View File

@@ -87,6 +87,9 @@ class JsonDocStatusStorage(DocStatusStorage):
# If content is missing, use content_summary as content
if "content" not in data and "content_summary" in data:
data["content"] = data["content_summary"]
# If file_path is not in data, use document id as file path
if "file_path" not in data:
data["file_path"] = "no-file-path"
result[k] = DocProcessingStatus(**data)
except KeyError as e:
logger.error(f"Missing required field for document {k}: {e}")