Otman404/local-rag-llamaindex
Local llamaindex RAG to assist researchers quickly navigate research papers
Implements a complete retrieval-augmented generation pipeline using LlamaIndex for document chunking and embedding, Qdrant for vector storage, and Ollama for local LLM inference—all orchestrated via FastAPI. Automatically downloads research papers from arXiv, indexes them into the vector database, retrieves relevant chunks for user queries, and generates grounded answers with source citations. Fully containerized with Docker Compose for reproducible offline operation without API dependencies.
133 stars. No commits in the last 6 months.
Stars
133
Forks
23
Language
Python
License
—
Category
Last pushed
May 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Otman404/local-rag-llamaindex"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
run-llama/llama_index
LlamaIndex is the leading document agent and OCR platform
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)