---
id: opensearch-project/opensearch-agent-skills/document-processing
version: "428b6f76"
license: Apache-2.0
install: manual
updated: 2026-07-22
---

# document-processing — Document Processing transforms unstructured files into indexed-ready JSONL chunks using the open-source Docling library, running entirely on your machine. Output includes text, headings, source file references, and page numbers for direct ingestion into OpenSearch.

Publisher: opensearch-project · Stars: 37 · Updated: 2026-07-22

Install (manual): `git clone https://github.com/opensearch-project/opensearch-agent-skills`

## SKILL.md

# Document Processing

Process unstructured documents into search-ready JSONL chunks using [Docling](https://docling.site/) (open-source, runs locally). No AWS credentials or cloud services needed.

## When to Use

- User has unstructured documents (PDF, DOCX, PPTX, XLSX)
- User wants to prepare documents for OpenSearch indexing
- User wants to inspect or evaluate chunk quality

## Output

JSONL files at `.opensearch/chunks/<index>/<filename>.jsonl`. Each line:
```json
{"text": "...", "headings": ["Section Title"], "source_file": "doc.pdf", "chunk_id": 0, "page_number": 1}
```

The JSONL output can be ingested into any OpenSearch target:
- **Local cluster** — bulk-index directly
- **AOS domain / AOSS collection** — via [managed-ingestion-service](../../cloud/managed-ingestion-service/SKILL.md) (OSIS pipeline)

## Reference

See [document_processing_guide.md](document_processing_guide.md) for the full workflow:
processing profiles, quality evaluation, and chunking adjustments.


[View on SkillFed](https://skillfed.io/opensearch-project/opensearch-agent-skills/document-processing) · [View on GitHub](https://github.com/opensearch-project/opensearch-agent-skills)