neuron-core/raptor-retrieval
Recursive Abstractive Processing for Tree-Organized Retrieval - Neuron PHP Framework
Implements a hierarchical retrieval strategy that recursively clusters documents and generates abstractive summaries at multiple levels, enabling comprehensive multi-step reasoning across long contexts—complementing traditional chunk-based RAG. Integrates with the Neuron PHP framework via pluggable vector stores and embedding providers, with configurable clustering strategies (similarity-based or Gaussian mixture models) for handling distinct versus overlapping topics.
Stars
9
Forks
4
Language
PHP
License
MIT
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/neuron-core/raptor-retrieval"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
llm-tools/embedJs
A NodeJS RAG framework to easily work with LLMs and embeddings
parthsarthi03/raptor
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
DHT-AI-Studio/RAPTOR
RAPTOR (Rapid AI-Powered Text and Object Recognition) is an AI-native Content Insight Engine...
Neverdecel/CodeRAG
CodeRAG is an AI-powered tool for real-time codebase querying and augmentation using OpenAI and...
himanshu231204/ragnova-rag-chatbot
🔍 End-to-end RAG (Retrieval-Augmented Generation) pipeline built with LangChain, ChromaDB &...