This course explores a Retrieval Augmented Generation (RAG) solution in BigQuery to mitigate AI hallucinations. It introduces a RAG workflow that encompasses creating embeddings, searching a vector space, and generating improved answers. The course explains the conceptual reasons behind these...
Build with Vertex AI: Building RAG Applications with Vertex AI
Retrieval Augmented Generation (RAG) allows enterprises to combine Large Language Models (LLMs) with real world data to create grounded applications that are far less likely to produce inaccuracies and hallucinations. This learning path begins with an overview of embeddings, vector space and RAG in BigQuery, and proceeds to equip you with the necessary skills and practical experience to build custom RAG solutions using Vertex AI APIs, vector stores and the LangChain framework.
This path is part of the curriculum to earn the Build with Vertex Technical Expert Badge. To earn your Technical Expert Badge you need to have a valid Professional Google Cloud Certification, earn the Skill Badge at the end of this path, and earn the other four Skill Badges to showcase your Build with Vertex AI skills.
You can earn the other Skill Badges needed at Build with Vertex AI: Working with Gemini, Build with Vertex AI: Developing, Tuning and Deploying Solutions using Model Garden Models , Build with Vertex AI: Generating, Editing, and Responding to Media, and Build with Vertex AI: Evaluating Model and Agent Performance.
Learn how to build your own Retrieval-Augmented Generation (RAG) solutions for greater control and flexibility than out-of-the-box implementations. Create a custom RAG solution using Vertex AI APIs, vector stores, and the LangChain framework.

This lab tests your ability to develop a real-world Generative AI Q&A solution using a RAG framework. You will use Firestore as a vector database and deploy a Flask app as a user interface to query a food safety knowledge...