Data could be in any form – from text, app logs, tables to documents, video and audio. But, AI/ML innovations have made it possible to create specialised Embedding Models to encode all of these data types into Vectors – this can help capture the meaning and context from this data and provide richer experiences than just plain text-based search.

That’s where Vector Databases come in! They operationalise these embedding models at scale and enable lightning-fast searches based on semantic similarity. When paired with Large Language Models (LLMs), they can be used to build intelligent Gen AI applications that aligns with existing data and user intent.

Join this hand-on session to learn about a variety of Vector databases and how you can use them to build GenAI solutions along with popular frameworks such as LangChain, as well as fully-managed services like Amazon Bedrock.

Key Takeaways – Attendees will:

• Learn key concepts behind Vector Databases.
• Explore popular Vector Databases such as PostgreSQL (pgvector), OpenSearch etc.
• How can use they Vector Databases and LLMs to power Generative AI use cases such as RAG (Retrieval Augmented Generation).
• Experience hands-on demos of practical solutions.