---
id: opensearch-project/opensearch-agent-skills/ingest
version: "986fda63"
license: Apache-2.0
install: manual
updated: 2026-07-22
---

# 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.

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

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

## SKILL.md

# Ingest

Category skill for local document processing — turning unstructured files into search-ready JSONL chunks.

## Skills

| Skill | Description |
|---|---|
| [document-processing](document-processing/SKILL.md) | 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](../cloud/managed-ingestion-service/SKILL.md)
- Structured bulk-indexing (`_bulk` API)
- OpenSearch `_ingest` processor pipelines (grok, date, set, script)
- Log/metric shipping (Fluent Bit, Data Prepper, Logstash)

## When to Use

Read [document-processing/SKILL.md](document-processing/SKILL.md) when:
- User has PDFs/documents and needs JSONL chunks
- User wants to evaluate chunk quality before ingestion
- User mentions Docling, document processing, chunking

For cloud ingestion (JSONL → OSIS → OpenSearch index), see
[cloud/managed-ingestion-service](../cloud/managed-ingestion-service/SKILL.md).


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