llama-index-readers-llama-parse

What it is and what it does

This package integrates LlamaParse, a document parsing API by LlamaIndex, into Python workflows to convert PDF files into structured markdown or text. It wraps the llama-parse API client and provides both synchronous and asynchronous methods to load and parse single or batch PDF files, returning LlamaIndex-compatible document objects suitable for retrieval-augmented generation (RAG) systems.

The package is designed to work seamlessly with LlamaIndex's SimpleDirectoryReader, allowing you to specify it as the default PDF handler when loading directories of documents. However, the package description explicitly states it is deprecated and directs users to migrate to the llama-cloud package instead, meaning it is no longer actively maintained and should be considered end-of-life for new projects.

Use it for:

• Parse PDF documents into markdown for ingestion into LlamaIndex RAG pipelines
• Batch-process multiple PDFs asynchronously to extract structured content for semantic search
• Integrate PDF parsing as the default file handler in LlamaIndex's SimpleDirectoryReader for directory-based document loading
• Convert PDFs to text format for downstream NLP or information extraction tasks within LlamaIndex workflows

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Parses PDF files into structured markdown or text format for use with LlamaIndex, enabling efficient document retrieval and context augmentation in RAG pipelines.

No. The package is explicitly deprecated and no longer maintained; the description directs users to migrate to llama-cloud instead. While it has low install friction and no known vulnerabilities, installing a deprecated package for new projects introduces maintenance risk and locks you into an unsupported codebase. Use llama-cloud for new work.

Install

llama-index-readers-llama-parse on PyPI

pip install llama-index-readers-llama-parse

uv add llama-index-readers-llama-parse

poetry add llama-index-readers-llama-parse

Installing llama-index-readers-llama-parse

Before you install

Low install friction with two straightforward runtime dependencies. The package is marked active with a recent release (142 days old), though the description explicitly states it has been deprecated in favor of llama-cloud.

License in practice

MIT license permits use in commercial and private projects with minimal restrictions, requiring only license and copyright notice retention.

Quickstart

pip install llama-index-readers-llama-parse

from llama_parse import LlamaParse

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

Requires a valid LlamaParse API key from https://cloud.llamaindex.ai and Python 3.10 or later.

Verify before relying

• Whether the deprecation notice means the package will stop receiving security updates or bug fixes
• Current API availability and whether the free tier mentioned in the description remains available
• Compatibility guarantees with future versions of llama-index-core and llama-parse

Package facts

Evidence: llama_index_readers_llama_parse-0.6.1-py3-none-any.whl

Keywords: PDF, llama, llama-parse, parse

Tags

More Text Processing packages