parthsarthi03/raptor
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
RAPTOR helps developers build intelligent applications that can answer complex questions by sifting through large collections of text documents. It takes raw text documents as input and processes them into a unique, organized tree structure. This allows the application to retrieve and summarize relevant information efficiently to provide precise answers. This is a tool for AI/ML engineers and data scientists building retrieval-augmented generation (RAG) systems.
1,613 stars. No commits in the last 6 months.
Use this if you are a developer or AI engineer looking to enhance the accuracy and contextual awareness of question-answering systems over extensive documentation or knowledge bases.
Not ideal if you are an end-user simply looking for a ready-to-use chatbot or a non-technical person who doesn't work with code.
Stars
1,613
Forks
217
Language
Python
License
MIT
Category
Last pushed
Sep 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/parthsarthi03/raptor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
llm-tools/embedJs
A NodeJS RAG framework to easily work with LLMs and embeddings
neuron-core/raptor-retrieval
Recursive Abstractive Processing for Tree-Organized Retrieval - Neuron PHP Framework
DHT-AI-Studio/RAPTOR
RAPTOR (Rapid AI-Powered Text and Object Recognition) is an AI-native Content Insight Engine...
manjotdhiman/ragify-js
RAG implementation for Node JS
Neverdecel/CodeRAG
CodeRAG is an AI-powered tool for real-time codebase querying and augmentation using OpenAI and...