Overview
Learn to build a web application using Retrieval-Augmented Generation (RAG) with LangChain in this 12-minute technical video featuring Google engineers Martin Omander and Miguel Reyes. Master the fundamentals of RAG implementation to enhance AI response accuracy, starting with data indexing techniques and progressing through the development of a user-friendly interface. Follow along with step-by-step demonstrations covering the indexing process, front-end web application development, deployment procedures, and practical application usage. Explore enterprise-level RAG applications and gain insights into leveraging Cloud Run and LangChain technologies for improved AI performance. Access the accompanying codelab for hands-on practice while learning to create more precise and reliable AI applications.
Syllabus
- Intro
- Retrieval Augmented Generation RAG
- Indexing job
- Front end web app
- Deploying the web app
- Using the application
- Enterprise uses of RAG
- Conclusion
Taught by
Google Cloud Tech