Intro to Grounding with Gemini in Vertex AI GSP1264 скачать в хорошем качестве

Intro to Grounding with Gemini in Vertex AI GSP1264

Overview Grounding in Vertex AI lets you use generative text models to generate content grounded in your own documents and data. This capability lets the model access information at runtime that goes beyond its training data. By grounding model responses in Google Search results or data stores within Vertex AI Search, LLMs that are grounded in data can produce more accurate, up-to-date, and relevant responses. Grounding provides the following benefits: Reduces model hallucinations (instances where the model generates content that isn't factual) Anchors model responses to specific information, documents, and data sources Enhances the trustworthiness, accuracy, and applicability of the generated content You can configure two different sources of grounding in Vertex AI: Google Search results for data that is publicly available and indexed. If you use this service in a production application, you will also need to use a Google Search entry point. Data stores in Vertex AI Search, which can include your own data in the form of website data, unstructured data, or structured data Objectives In this lab, you learn how to: Generate LLM text and chat model responses grounded in Google Search results. Compare the results of ungrounded LLM responses with grounded LLM responses. Create and use a data store in Vertex AI Search to ground responses in custom documents and data. Generate LLM text and chat model responses grounded in Vertex AI Search results. #gcp #googlecloud #qwiklabs #learntoearn