Repository of Natural Language Processing project at Polytechnic of Milan. Generative chatbots, with audio, images and RAG.

A FastAPI-based Retrieval-Augmented Generation (RAG) chatbot with audio upload, Whisper transcription, FAISS vector search, and GPT-powered responses.

Showcasing the use of GPT-4o Audio model

The AudioChatBot App receives voice inputs and sends them to the backend, then waits for a response. Once a response is received, it plays the audio.