Vectors in Action: Hands-on with FAISS & ChromaDB, Comparative Insights Across Vector DBs

In the era of Generative AI, vector embeddings are the foundation of semantic understanding, powering applications from Retrieval-Augmented Generation (RAG) to recommendation systems. This session offers a deep dive into FAISS and ChromaDB, two leading vector databases enabling high-performance similarity search on massive datasets.

Join us for an interactive and practical session where we’ll not only explore the architectures and use cases of FAISS and ChromaDB but also walk through live hands-on demos, compare them against Pinecone, Weaviate, Qdrant, and Milvus, and discuss best-fit scenarios for different workloads. Whether you are building LLM pipelines, semantic search engines, or intelligent retrieval systems, this session will equip you with the insights and tools you need to succeed.

Key Takeaways:

• Understand the role of vector embeddings in modern AI pipelines.
• Learn the core differences between FAISS and ChromaDB with practical demonstrations.
• Compare top vector databases: FAISS, ChromaDB, Pinecone, Weaviate, Qdrant, and Milvus
• Get hands-on exposure to similarity search, indexing strategies, and performance metrics
• Discover how to integrate vector DBs into RAG pipelines and GenAI applications
• Access open-source tools and code to build your own vector search applications

Prerequisites :

• Basic knowledge of Python programming
• Familiarity with embeddings and machine learning concepts
• Prior exposure to NLP or vector representations (recommended, but not mandatory)

Lakshmi Devi Prakash is Vice President – AI/ML Lead at JPMorgan Chase, based in Bengaluru, with over a decade of experience in Machine Learning, NLP, and Generative AI.

She specializes in building production-ready AI systems, including enterprise solutions, agent-based architectures, and multimodal applications. She is currently pursuing a PhD in AI, has published research papers, authored books on Generative AI, and holds a patent in AI-driven automation.