ThomasJButler/Morpheus
An intelligent document reasoning system with a Matrix-themed interface.
Implements retrieval-augmented generation (RAG) by chunking documents into vectors, storing them in Pinecone under session-isolated namespaces, and retrieving relevant context via semantic search to ground Claude's responses with source citations. Built with a Next.js/TypeScript frontend and FastAPI backend, integrating Anthropic's Claude and OpenAI embeddings for reasoning and vectorization. Session-based architecture ensures automatic data deletion without persistent storage, prioritizing privacy while reducing costs compared to subscription-based AI services.
Stars
5
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ThomasJButler/Morpheus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
Cerno-AI/Cerno-Insight
High-performance RAG system for intelligent document Q&A with hybrid retrieval, GPU...
kaumnen/lumen
Leveraging RAG, MCPs and Amazon Nova LLMs for Efficient AWS Documentation Queries
elcaiseri/Survey-Analysis-RAG-System
A web application using Retrieval-Augmented Generation (RAG) to analyze and compare survey...
qingni/rag-pipeline-hub
Full-stack RAG platform for document loading, smart chunking, embedding, indexing, hybrid...
Rupeshbhardwaj002/Hybrid-RAG-Qwen-FAISS-XGBoost
Hybrid RAG pipeline with Qwen LLM, FAISS vector search, and XGBoost re-ranking for high-accuracy...