Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Processing documents into search-ready chunks v1.0.0

Use this resource to prepare unstructured documents for search indexing

New

  • 327 downloads
  • 226 likes
  • 236 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install process-documents-into-chunks

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent converts your documents into JSONL chunks locally with Docling, then helps evaluate chunk quality. You get files per index, each line holding the text, its headings and its source file.

Mostly picked by

Updated November 2, 2026

Card for the “Processing documents into search-ready chunks” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: agent role and processing rules
  • document-processing/: Docling guide and JSONL output format

Good fit for

  • You want to index PDFs in OpenSearch
  • You are checking how your documents are split before search

Not for

    Tags

    • ingestion
    • pdf
    • docling
    • chunks
    • search

    About

    You say

    “Split my contract PDFs into JSONL chunks for OpenSearch.”

    Card for the “Processing documents into search-ready chunks” skill

    Skill published by opensearch-project under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to prepare unstructured documents for search indexing
    3. Review and adjust the result

    Content preview

    Files

    • document-processing/document_processing_guide.md6.6 KB
    • document-processing/SKILL.md1.6 KB
    • LICENSE9.9 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.6 KB

    Origin and licence

    Listed unmodified

    Author
    opensearch-project
    Source
    github.com/opensearch-project/opensearch-agent-skills/tree/5076c03d24fdd61d9b06fa4e451c900023ad00da/skills/opensearch-skills/ingest
    Licence
    Apache-2.0

    Notice

    « ingest » (opensearch-project, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.