run-llama/llama_index
LlamaIndex is the leading document agent and OCR platform
This platform helps businesses unlock insights from diverse documents like PDFs, scanned images, and more. It takes unstructured document data and transforms it into structured information that can be easily searched, analyzed, or used to power AI applications. Knowledge workers, data analysts, or operations managers dealing with large volumes of documents would find this useful.
47,631 stars. Used by 36 other packages. Actively maintained with 116 commits in the last 30 days. Available on PyPI.
Use this if you need to extract specific information, answer questions, or automate workflows using data trapped in various document formats, including those requiring optical character recognition (OCR).
Not ideal if your data is already structured and easily accessible in databases or standard spreadsheet formats.
Stars
47,631
Forks
7,002
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
116
Dependencies
8
Reverse dependents
36
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/run-llama/llama_index"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related tools
emarco177/documentation-helper
Reference implementation of a RAG-based documentation helper using LangChain, Pinecone, and Tavily..
janus-llm/janus-llm
Leveraging LLMs for modernization through intelligent chunking, iterative prompting and...
JetXu-LLM/llama-github
Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and...
Vasallo94/ObsidianRAG
RAG system to query your Obsidian notes using LangGraph and local LLMs (Ollama)
GURPREETKAURJETHRA/RAG-using-Llama3-Langchain-and-ChromaDB
RAG using Llama3, Langchain and ChromaDB