Skip to content

berkaybakac/rag-supportbot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

rag-supportbot

Streamlit App

rag-supportbot is a local, document-based AI assistant designed to help technical support teams answer user questions based on existing documents.

The system is built using the Retrieval-Augmented Generation (RAG) architecture, which enables reliable and source-grounded responses by retrieving relevant document chunks and generating answers using a local large language model.

Key Features

  • Offline operation with no external API dependencies
  • Source-based, grounded answer generation
  • Local vector search using FAISS and LlamaIndex
  • Modular architecture for future extensions

Technologies (initial setup)

  • Python 3.11
  • FAISS
  • LlamaIndex
  • LangChain (optional)
  • LLaMA 3 Instruct (via llama.cpp)
  • Streamlit (for UI)

License

MIT License

This project is in active development. The architecture and components may change as the system evolves.

About

Offline, document-grounded AI assistant for technical support teams — powered by LLaMA, FAISS. Built with full RAG pipeline.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors