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.
Document Processing converts unstructured documents into search-ready JSONL chunks for OpenSearch indexing.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-22
Document Processing converts unstructured documents into search-ready JSONL chunks for OpenSearch indexing. 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.
Use it when
- Document Processing automatically converts your files into indexed-ready JSONL chunks.
- Yes.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Similar skills
Install
opensearch-project/opensearch-agent-skills/document-processing · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What file formats does Document Processing support?
Document Processing handles PDF, DOCX, PPTX, and XLSX files. The skill processes these formats locally on your machine using the open-source Docling library, converting unstructured content into search-ready chunks without relying on cloud services.
How do I chunk documents for search indexing with this tool?
Document Processing automatically converts your files into indexed-ready JSONL chunks. Each chunk includes extracted text, headings, source file references, and page numbers, making them ready for direct ingestion into OpenSearch or other search engines.
Can Document Processing process unstructured documents locally?
Yes. Document Processing runs entirely on your machine without cloud services. It transforms unstructured files into search-ready chunks locally, giving you full control over your document data while preparing it for indexing.
What output format does Document Processing generate?
Document Processing outputs JSONL format optimized for OpenSearch ingestion. Each record contains extracted text, headings, source file references, and page numbers, allowing you to index documents with full context and traceability.
How can I evaluate document chunk quality before indexing?
Document Processing includes inspection capabilities to review chunk quality before indexing. You can examine the generated JSONL output, verify text extraction accuracy, and validate that headings and metadata are properly captured for your search engine.
Does Document Processing handle batch processing of multiple files?
Document Processing is designed to extract and split large documents into manageable indexed segments. It can process multiple PDFs, DOCX, PPTX, and XLSX files, converting them into search-ready chunks that maintain document structure and reference information.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Document Processing
Process unstructured documents into search-ready JSONL chunks using Docling (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:
{"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
(truncated - see the full file via the links below)
File tree — 2 files
skills/opensearch-skills/ingest/document-processing/SKILL.md
skills/opensearch-skills/ingest/document-processing/document_processing_guide.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Convert unstructured documents into search-ready chunks for indexing”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
ingest is a category skill for transforming unstructured files into JSONL chunks on your machine. It handles PDF, DOCX, and PPTX formats through the document-processing skill, which uses Docling to produce search-ready output without requiring cloud infrastructure or AWS.
OpenSearch Launchpad is your guided path from initial requirements to a fully operational search system. It handles data ingestion, strategy selection (keyword, semantic, hybrid, or agentic), and deployment to either local Docker or Amazon OpenSearch Serverless. The skill walks you through architecture planning and launches a search UI ready for queries.
Scale document ingestion into Amazon OpenSearch using OSIS pipelines. Upload pre-chunked JSONL to S3 for indexing, or send raw PDFs to the cloud for automatic parsing and embedding. Supports both OpenSearch Service domains and Serverless collections.
This skill guides you through building complete search applications on OpenSearch, covering index setup, document processing, and multiple search strategies including BM25, semantic, hybrid, and agentic approaches. Deploy ML models, ingest PDFs and other documents, and evaluate search quality end-to-end.
OpenSearch Skills provides a modular toolkit for constructing search applications with advanced retrieval strategies including vector and semantic search, plus observability features for log analysis and trace investigation. Deploy locally or to AWS, process documents at scale, and route queries intelligently across search, observability, and cloud infrastructure tasks.
Cloud is a category skill for deploying OpenSearch search applications to AWS infrastructure. It guides you through provisioning Amazon OpenSearch Service domains or Serverless collections, configuring IAM roles, setting up Bedrock connectors for ML models, and migrating local setups to the cloud.
More skills observability (Apache-2.0) · aoss-nextgen-provisioning (Apache-2.0) · trace-analytics (Apache-2.0)