Clelia (Astra) Bertelli 2dcef7c624 Merge pull request #10 from run-llama/__release
Release 1.0.0 for llamacloud-index
2026-07-03 21:36:52 +02:00
2026-03-02 22:06:50 +01:00
2026-03-03 17:49:22 +01:00
2026-07-03 19:36:16 +00:00
2026-03-03 16:40:43 +01:00
2026-03-02 15:19:17 +01:00
2026-07-03 19:36:16 +00:00

LlamaParse Skills

Unblock document intelligence for your agents with LlamaParse skills.

Available Skills

llamaparse

Skill for unstructured documents parsing and text-extraction leveraging LlamaParse.

Use with:

  • PDFs, presentations, Word documents, spreadsheets, images
  • Complex documents which need advanced parsing capabilties in order to get their content extracted
  • Documents with images, charts and tables
  • In general, whenever the agent needs to have access to a deeper layer than just raw text extraction

Pre-requisites

  • A LLAMA_CLOUD_API_KEY available within the environment
  • Node 18+ and npm (or another package manager)
  • (Optional) @llamaindex/llama-cloud@latest typescript package installed in the current Node environment

liteparse

Skill for local-first, fast document parsing, conversion and spatial text extraction.

Use with:

  • PDFs (main target), Office documents and images (require extra dependencies)
  • Text-dense documents with tables and images
  • In general, whenever the agent needs a quick and not-100%-accurate way to extract content from unstructured documents

Pre-requisites

  • Node 18+ and npm (or another package manager)
  • @llamaindex/liteparse globally installed (npm install -g @llamaindex/liteparse)
  • (Optional) Libreoffice for Office documents support
  • (Optional) Imagemagick for images support

llamacloud-index

Skill for agentic retrieval over LlamaCloud Index v2, the managed knowledge base of the LlamaParse Platform, through the platform REST API with curl.

Use with:

  • Questions that should be answered from documents stored in an Index v2 knowledge base
  • Agentic retrieval workflows: discover indexes, locate files, grep indexed content, and retrieve passages with hybrid (sparse + dense) search
  • In general, whenever the agent should navigate an index like a file system instead of doing one-shot RAG

Pre-requisites

  • A LLAMA_CLOUD_API_KEY available within the environment
  • curl (and, recommended, jq)
  • An existing Index v2 index

Installation

With the skills CLI:

npx skills add run-llama/llamaparse-agent-skills

Or, if you wish to download only one skill:

npx skills add run-llama/llamaparse-agent-skills --skill llamaparse # or the name of another skill

You can also download the skills folder in .zip format from GitHub Releases.

License

MIT

S
Description
Use this skill whenever a task involves a document file (PDF, DOCX, PPTX, XLSX, or image) and you need to read it or pull text, tables, or specific values out…
Readme MIT 80 KiB
Languages
Python 66.3%
JavaScript 33.7%