Vector Databases and Large Language Models for Context Retrieval - LLMs in Production

Explore the intersection of vector databases and large language models in this 13-minute conference talk from the LLMs in Production Conference. Discover how vector embeddings and databases can provide context for generative models, enabling real-time updates to an external knowledge base. Learn about the advantages of this approach for handling constantly changing data and preventing model hallucinations. Gain insights into practical applications, such as creating an onboarding tool for company documentation. Follow along with examples, instructions, and open-source code to implement these techniques in your own projects. Understand the role of Redis as a vector database and online feature store in AI applications.

Introduction
What are vectors
What are vector databases
Why is Redis in this conversation
Context Retrieval
External Knowledge Base
Long Term Memory
Chat GPT Memory
GPT Cache