dot Stop testing, start deploying your AI apps. See how with MIT Technology Review’s latest research.

Download now

Agentic RAG: Using Semantic Caching for Speed and Cost Optimization

Use the latest developments with agents to enhance chatbots.

More and more companies are building their own virtual assistants utilizing agents and Retrieval Augmented Generation (RAG) to enhance responses from Large Language Models (LLMs). This approach allows companies to enhance virtual assistants by grounding answers in fact while minimizing security and data leakage concerns. Many companies are in the exploratory phase, and architects and devs have questions about the best ways to structure virtual assistants and the flow of data. Building these apps for production requires weighing considerations such as performance, quality, flexibility, and cost. With Redis and LlamaIndex, customers can build faster, more accurate chatbots at scale while optimizing cost.

Join this session to learn best practices for:

  • Architecting virtual assistant apps
  • Accelerating document ingestion while minimizing cost
  • Improving responses using AI agents
  • Optimizing response time and cost with semantic caching

Event Speakers

Tyler Hutcherson, Senior Applied AI Engineer, Redis

Tyler Hutcherson

Senior Applied AI Engineer
Redis

Laurie Voss

VP of Developer Relations
LlamaIndex

Watch Now!

Discover GenAI for chatbots with Redis and LlamaIndex