Skill Store 33

Document Processing

Process unstructured documents (PDF, DOCX, PPTX, XLSX) into search-ready JSONL chunks using Docling.

by opensearch-project · Apache-2.0

The skill

Process unstructured documents (PDF, DOCX, PPTX, XLSX) into search-ready JSONL chunks using Docling. Runs locally — no AWS or cloud services needed. Use this skill when the user wants to prepare documents for indexing, chunk documents, evaluate chunk quality, or convert PDFs to searchable text. Activate even if the user says process documents, chunk my files, prepare for search, or Docling.

Document Processing

Process unstructured documents into search-ready JSONL chunks using Docling (open-source, runs locally). No AWS credentials or cloud services needed.

Prerequisites

  • uv installed (for running Python scripts)

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:

{"text": "...", "headings": ["Section Title"], "source_file": "doc.pdf", "chunk_id": 0, "page_number": 1}

The JSONL output can be ingested into any OpenSearch target:

Reference

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

Use this skill

Connect your agent to the Skill Store MCP server and ask for it by ref: opensearch-project/document-processing-5731488011.

Download SKILL.md · Markdown version

Details

Publisher
opensearch-project
Category
Data & Analytics › Data pipelines & ETL
License
Apache-2.0
Updated
2026-08-19

References

More from opensearch-project