pnkvalavala/repochat
Chatbot assistant enabling GitHub repository interaction using LLMs with Retrieval Augmented Generation
Runs entirely locally using quantized GGUF models (via llama-cpp-python) with hardware acceleration options for CPU/GPU, embedding-based RAG powered by Sentence Transformers and ChromaDB vector storage, and Streamlit web interface. Supports dual deployment modes: fully self-contained on local machines or cloud-based via external API calls, with conversation memory for contextual responses across interactions.
315 stars. No commits in the last 6 months.
Stars
315
Forks
55
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/pnkvalavala/repochat"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ScrapeGraphAI/Scrapegraph-demo
Streamlit demo of Scrapegraph-ai for GPT4-hackaton
run-llama/rags
Build ChatGPT over your data, all with natural language
Caellwyn/long-memory-character-chat
A character chat with integrated medium and long-term memory
Daethyra/FreeStream
Prebuilt Streamlit/LangChain Agent with Tools and Memory
couchbase-examples/qa-bot-demo
Q&A Chatbot Demo using Couchbase, LangChain, OpenAI and Streamlit