Lecture 10: Building a RAG System with Gemini, LlamaIndex, and ChromaDB

Name: Lecture 10: Building a RAG System with Gemini, LlamaIndex, and ChromaDB
Start: 2025-04-05T20:00:00+05:00
End: 2025-04-05T21:00:00+05:00

GDG on Campus University of Management and Technology - Lahore, Pakistan

Learn how to build a powerful Retrieval-Augmented Generation (RAG) system using Google Gemini, LlamaIndex, and ChromaDB. This lecture covers the complete workflow from data ingestion and embedding to retrieval and response generation using local vector storage and cutting-edge LLMs.

Apr 5, 2025, 3:00 – 4:00 PM (UTC)

39 RSVP'd

Key Themes

AI - GeminiBuild with AIWorkshop / hands-on session

About this event

In this lecture, we dive into the world of Retrieval-Augmented Generation (RAG)  a cutting-edge technique that enhances LLMs with external knowledge. You'll learn how to build a complete RAG pipeline using Google Gemini (Flash 2.0) for response generation, Google’s Text Embedding API for semantic understanding, ChromaDB for efficient local vector storage, and LlamaIndex for data indexing, querying, and integration.
We'll cover the following key steps:
Chunking and preprocessing your documents
Creating embeddings with Google's Text Embedding API
Persisting and retrieving embeddings using ChromaDB
Connecting LlamaIndex to ChromaDB for smart document retrieval
Crafting a custom system prompt and querying Gemini Flash 2.0
By the end of this session, you'll have a fully working RAG application capable of answering real-world queries, perfect for applications like university department bots, legal assistants, or internal knowledge hubs.