Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove the legacy document format to move to docling v2 output #485

Closed
wants to merge 2 commits into from
Closed

Remove the legacy document format to move to docling v2 output #485

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0b91a3f
Remove the legacy document format to move to docling v2 output
aakankshaduggal Jan 16, 2025
1484355
Initialize pipelines for more doc types
aakankshaduggal Jan 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions src/instructlab/sdg/utils/chunkers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,9 @@ def chunk_documents(self) -> List:
docling_json_paths = list(docling_artifacts_path.glob("*.json"))
chunks = []
for json_fp in docling_json_paths:
chunks.extend(self._process_parsed_docling_json(json_fp))
with json_fp.open("r", encoding="utf-8") as file:
data = json.load(file)
chunks.extend(self._process_parsed_docling_json(data))

return chunks

Expand Down Expand Up @@ -522,11 +524,11 @@ def export_documents(self, converted_docs: Iterable[ConversionResult]):

# Export Deep Search document JSON format:
with (docling_artifacts_path / f"{doc_filename}.json").open("w") as fp:
fp.write(json.dumps(doc.legacy_document.export_to_dict()))
fp.write(json.dumps(doc.document.export_to_dict()))

# Export Markdown format:
with (docling_artifacts_path / f"{doc_filename}.md").open("w") as fp:
fp.write(doc.legacy_document.export_to_markdown())
fp.write(doc.document.export_to_markdown())
else:
logger.info(f"Document {doc.input.file} failed to convert.")
failure_count += 1
Expand Down
Loading