ingest
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.
ingest converts unstructured documents like PDFs into search-ready JSONL chunks locally using Docling.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-22
ingest converts unstructured documents like PDFs into search-ready JSONL chunks locally using Docling. 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.
Use it when
- Yes.
- ingest supports PDF, DOCX, and PPTX formats.
Verify before relying
Read SKILL.md below before installing (3 files). Open directory: indexed for reading, not audited.
Similar skills
Install
opensearch-project/opensearch-agent-skills/ingest · 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
How does ingest convert PDF to JSONL chunks?
ingest transforms PDF, DOCX, and PPTX files into JSONL chunks using Docling, a document-processing engine that runs locally on your machine. The skill parses unstructured content, structures it into discrete chunks, and outputs them in JSONL format ready for indexing without cloud dependency.
Can ingest process unstructured documents for search?
Yes. ingest is designed to process unstructured documents for search by converting them into search-ready JSONL chunks. It evaluates chunk quality and structure to optimize search performance, then prepares the output for OpenSearch indexing or other downstream systems.
What file formats does ingest support?
ingest supports PDF, DOCX, and PPTX formats. The skill handles all three through its document-processing pipeline, converting each into consistently structured JSONL chunks suitable for ingestion into search systems.
Does ingest require cloud infrastructure?
No. ingest operates entirely locally on your machine, eliminating cloud dependency. All document processing, chunking, and quality assessment happen without AWS or external services, giving you full control over your data pipeline.
How does ingest assess chunk quality before indexing?
ingest evaluates chunk quality and structure locally before ingestion, examining factors like coherence, size, and metadata completeness. This assessment ensures optimal search performance when chunks are indexed into OpenSearch or similar systems.
What license does ingest use?
ingest is licensed under Apache-2.0, allowing free use, modification, and distribution under the terms of the Apache License 2.0.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Ingest
Category skill for local document processing — turning unstructured files into search-ready JSONL chunks.
Skills
| Skill | Description |
|---|---|
| document-processing | Process PDF/DOCX/PPTX into JSONL chunks via Docling (local, no AWS needed) |
Not Covered
This skill covers local document processing only (PDF/DOCX → JSONL chunks).
It does NOT cover:
- Cloud-scale ingestion via OSIS pipelines → see managed-ingestion-service
- Structured bulk-indexing (_bulk API)
- OpenSearch _ingest processor pipelines (grok, date, set, script)
- Log/metric shipping (Fluent Bit, Data Prepper,
(truncated - see the full file via the links below)
File tree — 3 files
skills/opensearch-skills/ingest/SKILL.md
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 (PDF, DOCX, PPTX) into JSONL chunks”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
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.
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.
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.
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 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.
More skills observability (Apache-2.0) · trace-analytics (Apache-2.0)