feat(metadata): enhance document processing to include metadata extraction and handling
- Updated DocReaderServicer to pass metadata in responses. - Modified PipelineParser to accumulate and merge metadata from all parsers. - Enhanced StdWebParser to extract and log the title from web page content. - Implemented logic in knowledge service to update knowledge title based on extracted metadata.
This commit is contained in:
@@ -151,6 +151,7 @@ class DocReaderServicer(docreader_pb2_grpc.DocReaderServicer):
|
||||
markdown_content=_c(result.content),
|
||||
image_refs=image_refs,
|
||||
image_dir_path=image_dir,
|
||||
metadata={k: _c(str(v)) for k, v in result.metadata.items()} if result.metadata else {},
|
||||
)
|
||||
logger.info(
|
||||
"Read response: content_len=%d, images=%d",
|
||||
|
||||
Reference in New Issue
Block a user