Agent Search lets you build AI-enabled search and recommendation
experiences for your public websites or mobile applications.

Powered by large language models, it offers search and RAG across
websites, unstructured documents, and structured data. Agent Search
also provides specialized tuning for industry requirements for commerce
catalogs, media libraries, and clinical data repositories.

Agent Search provides natural language understanding and semantic
search, synonym understanding, spell correction, and auto-suggest out of the
box.

Other key features include:

- Generative AI summarization
- Generative AI conversational search
- Self-learning ranking models
- Parsers for unstructured file types such as PDF, HTML, and TXT
- Controls for search results such as boost and bury, filters, and URI redirects
- An out-of-the-box search widget for embedding in your websites

To learn more about Agent Search for custom, media, and healthcare
use cases, see the
[Agent Search](https://docs.cloud.google.com/generative-ai-app-builder/docs/introduction#es-and-personalize)
documentation.

To learn about Agent Search for retail and commerce use cases, see
[Features and capabilities](https://docs.cloud.google.com/retail/docs/features) in the
Agent Search for commerce documentation.

## Get started

To get started with Agent Search:

- [Try a demo of Agent Search](https://docs.cloud.google.com/generative-ai-app-builder/docs/introduction#try-it)
- Follow a step-by-step tutorial:
  - [Create a search app for website, unstructured, or structured data](https://docs.cloud.google.com/generative-ai-app-builder/docs/try-enterprise-search.md.txt)
  - [Create a media recommendations app](https://docs.cloud.google.com/generative-ai-app-builder/docs/try-generic-recommendations.md.txt)
  - [Create a media search app](https://docs.cloud.google.com/generative-ai-app-builder/docs/try-media-search.md.txt)
  - [Try interactive task tutorials for Agent Search for commerce](https://docs.cloud.google.com/retail/docs/retail-api-tutorials)