README.md

Awersome RAG

Libraries/Frameworks

Name	About	Stars
LangChain	A framework for developing applications powered by LLMs.
LlamaIndex	A data framework for your LLM applications.
Dify	An open-source LLM app development platform.
Flowise	Drag & drop UI to build your customized LLM flow.
Haystack	LLM orchestration framework to build customizable, production-ready LLM applications.
RAGFlow	An open-source RAG engine based on deep document understanding.
Cognita	RAG Framework for building modular, open source applications for production.
fastRAG	Efficient Retrieval Augmentation and Generation Framework.
AutoRAG	RAG AutoML Tool - Find optimal RAG pipeline for your own data.
FlashRAG	A Python Toolkit for Efficient RAG Research.

Framework Tutorials

• LangChain:
  • LangChain: Chat with Your Data
  • LangChain for LLM Application Development
  • Functions, Tools and Agents with LangChain
• LlamaIndex:
  • Building and Evaluating Advanced RAG Applications
  • Building Agentic RAG with LlamaIndex
• Haystack:
  • Building AI Applications with Haystack

Agents

Name	About	Stars
LangGraph	Build resilient language agents as graphs.
AutoGen	A programming framework for agentic AI 🤖
crewAI	Cutting-edge framework for orchestrating role-playing, autonomous AI agents.
BabyAGI	An AI-powered autonomous task manager.

Agent-Related Projects

• AI Agent Service Toolkit: Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit

Agent Tutorials

• LangGraph:
  • AI Agents in LangGraph
• AutoGen:
  • AI Agentic Design Patterns with AutoGen
• crewAI:
  • Multi AI Agent Systems with crewAI

GraphRAG

Name	About	Stars
GraphRAG	A modular graph-based Retrieval-Augmented Generation (RAG) system.

GraphRAG-Related Projects

• GraphRAG-Visualizer: A web-based tool for visualizing and exploring artifacts from Microsoft's GraphRAG.
• nano-GraphRAG: A Simple GraphRAG Implementation.

GraphRAG Tutorials

• Neo4j:
  • Knowledge Graphs for RAG

Vector Stores

Name	About	Stars
Weaviate	A cloud-native, open source vector database that is robust, fast, and scalable.
Milvus	A cloud-native vector database, storage for next generation AI applications.
FAISS	A library for efficient similarity search and clustering of dense vectors.
Chroma	The AI-native open-source embedding database.
LanceDB	Developer-friendly, serverless vector database for AI applications.
Pinecone	The vector database to build knowledgeable AI.
Qdrant	High-performance, massive-scale Vector Database for the next generation of AI.
PGVector	Open-source vector similarity search for Postgres.
Vearch	Distributed vector search for AI-native applications.

Vector Store Tutorials

• Weaviate:
  • Vector Databases: from Embeddings to Applications
• Pinecone:
  • Building Applications with Vector Databases

Memory Systems

Name	About	Stars
Mem0	The memory layer for Personalized AI.

Guardrails

Name	About	Stars
NeMo Guardrails	A toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Evaluation Frameworks

Name	About	Stars
RAGAS	Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines.
DeepEval	The LLM Evaluation Framework.
TruLens	Evaluation and Tracking for LLM Experiments.
ARES	A cross-platform, open source, multi-system emulator, focusing on accuracy and preservation.
RGB	Implementation for Benchmarking Large Language Models in Retrieval-Augmented Generation.

PDF and Document Processing Tools

Name	About	Stars
Unstructured	A library to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
Nougat	The academic document PDF parser that understands LaTeX math and tables.
PDFPlumber	Extracts tables, text, and metadata from PDFs.
MinerU	A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.
PDF-Extract-Kit	A Comprehensive Toolkit for High-Quality PDF Content Extraction.
grobid	A machine learning software for extracting information from scholarly documents.
GOT-OCR2.0	Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model.
marker	Convert PDF to markdown + JSON quickly with high accuracy.
markitdown	Python tool for converting files and office documents to Markdown.

Image Processing

Name	About	Stars
CLIP	A neural network that learns visual concepts from natural language descriptions.

UI/Interface

Name	About	Stars
Verba	Retrieval Augmented Generation (RAG) chatbot powered by Weaviate.
Streamlit	A faster way to build and share data apps.
Gradio	Build and share delightful machine learning apps.
Chainlit	Build Conversational AI in minutes.

UI/Interface Tutorials

• Gradio:
  • Building Generative AI Applications with Gradio

References

• Awesome-LLM
• Awesome-RAG-Evaluation
• DeepLearning.AI