SciPy 2025

AI assistants are evolving from simple Q&A bots to intelligent, multimodal, multilingual, and agentic systems capable of reasoning, retrieving, and autonomously acting. In this talk, we’ll showcase how to build a voice-enabled, multilingual, multimodal RAG (Retrieval-Augmented Generation) assistant using Gradio, OpenAI’s Whisper, LangChain, LangGraph, and FAISS. Our assistant will not only process voice and text inputs in multiple languages but also intelligently retrieve information from structured and unstructured data. We’ll demonstrate this with a flight search use case—leveraging a flight database for retrieval and, when necessary, autonomously searching external sources using LangGraph. You will gain practical insights into building scalable, adaptive AI assistants that move beyond static chatbots to autonomous agents that interact dynamically with users and the web.

Education should be accessible to everyone, yet millions of students with visual impairments or learning disabilities like dyslexia struggle with traditional learning materials. What if AI could read, understand, and interact with books in a conversational and voice-enabled way? In this talk, we introduce a voice-powered AI learning assistant that allows students to upload books, extract text using OCR, store it in a vector database (FAISS), and interact with it using Retrieval-Augmented Generation (RAG). This assistant, accessible via a web or mobile app, will provide multilingual support and conversational learning through voice or text. We will explore its potential in non-profit and educational settings, demonstrating how AI can empower learners who need accessible, adaptable, and personalized study aids.