Commit f6c360b7 authored by Jan Reimes's avatar Jan Reimes
Browse files

fix: Use unified extraction for specs in add-members 

For specs, convert_document_to_markdown() doesn't work because it's TDoc-specific.
Now using extract_document_structured() directly with file path for specs/other documents.
parent 2ed2e4b3

packages/3gpp-ai/threegpp_ai/cli.py

+10 −3
Original line number Diff line number Diff line
@@ -332,9 +332,16 @@ def _process_single_item( 
    was_md_extracted = False

    if convert_md:

        try:

            # Extract markdown using unified pipeline - this will save to .ai folder

            # For TDocs: uses TDoc ID; for specs: uses spec number

            if source_kind == SourceKind.TDOC:

                # TDoc extraction - uses TDoc ID to fetch files

                convert_document_to_markdown(document_id=item, output_path=None, force=False)

            else:

                # Generic extraction (specs, other) - uses file path directly

                doc_file = _resolve_process_file(Path(source_path))

                if doc_file:

                    from threegpp_ai.operations.extraction import extract_document_structured



                    extract_document_structured(doc_file, metadata=None, force=False)

            was_md_extracted = True

        except Exception as e:

            _logger.debug("Failed to extract markdown for %s: %s", item, e)