llama-parse

Parse files into RAG-Optimized formats.

llama-parse Permissive license MIT AGING v0.6.94 released 2026-02-13

Install

llama-parse on PyPI

pip

pip install llama-parse

uv

uv add llama-parse

poetry

poetry add llama-parse

Package facts

License	MIT (permissive)
Python support	supports the current Python release (<4.0,>=3.9)
Install friction	low — pure-Python wheel
Runtime dependencies	1 — llama-cloud-services
Maintenance	aging — 181 days since the last release
First released	2024-02-02
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: llama_parse-0.6.94-py3-none-any.whl

About llama-parse

from the package's own PyPI description — quoted content, verbatim

LlamaParse

> ⚠️ DEPRECATION NOTICE > > This repository and its packages are deprecated and will be maintained until May 1, 2026. > > Please migrate to the new packages: > - Python: pip install llama-cloud>=1.0 (GitHub) > - TypeScript: npm install @llamaindex/llama-cloud (GitHub) > > The new packages provide the same functionality with improved performance, better support, and active development.

PyPI - Downloads (image) GitHub contributors (image) Discord (image)

LlamaParse is a GenAI-native document parser that can parse complex document data for any downstream LLM use case (RAG, agents).

It is really good at the following:

✅ Broad file type support: Parsing a variety of unstructured file types (.pdf, .pptx, .docx, .xlsx, .html) with text, tables, visual elements,...

Read as markdown · JSON record

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

LlamaParse is a GenAI-native document parser that converts complex unstructured files (PDF, PPTX, DOCX, XLSX, HTML) into structured, LLM-ready formats with support for tables, visual elements, and custom parsing instructions.

Low friction: pure Python wheel with a single runtime dependency (llama-cloud-services). However, the package is marked deprecated and will be maintained only until May 1, 2026; users should plan migration to the successor package.

MIT license permits broad commercial and private use with minimal restrictions, making it suitable for most projects.

Usage

pip install llama-parse

from llama_parse import LlamaParse

parser = LlamaParse(api_key="llx-...", result_type="markdown")
documents = parser.load_data("./my_file.pdf")

Requires LLAMA_CLOUD_API_KEY environment variable or api_key parameter; API key obtained from https://cloud.llamaindex.ai/api-key. Free tier limited to 1000 pages/day.

Verdict: LlamaParse offers document parsing for RAG pipelines with low install friction and permissive MIT licensing, but its deprecation status with maintenance ending May 1, 2026 makes it a transitional choice. New projects should migrate to the recommended successor package for active development.

Needs verification

Whether llama-cloud-services dependency itself has known vulnerabilities or maintenance concerns
Performance and accuracy metrics for the deprecated version versus the recommended replacement
Impact of deprecation timeline on existing production deployments

document parser for llmpdf to markdown conversiontable extraction from documentsrag document parsingmultimodal document processingunstructured file parsingparse complex documents