Skip to content

sohamw03/v2v-textbook-rag-llm

Repository files navigation

Minimal latency V2V chatbot for students' learning in remote areas

A latency optimized Django REST API for a Audio LLM Audio sandwich chatbot that does Retrieval Augmented Generation (RAG) on NCERT school textbooks. There is also a minimal html demo that demonstrates compatible audio processing for Azure Speech Services.

Air Gapped Systems

Server is also ready and optimized to deploy on air gapped servers thanks to local models.

Tech Stack

  • Ollama - Local models
  • gpt-4
  • FAISS
  • Langchain
  • Azure Document Intelligence
  • Azure Speech Services