Vertex AI Search offers a complete toolkit for accessing, processing and analyzing your enterprise information. With Google-grade search capabilities and Gemini generative AI, it offers specialized solutions for retail, media, healthcare, websites, intranets, and custom applications.

Key features include out-of-the-box performance with advanced crawling, parsing, and document understanding, along with tuning and customization options like events-based reranking and autocomplete. Generative AI features enable grounded answers, blending multiple sources, and conversational AI capabilities.

Vertex AI Search provides a foundational platform with connectors for various data sources, document AI capabilities, RAG APIs, vector search, and grounded Gemini for generative AI grounded on Google Search and your data.

• Create a site index: This is done simply by adding your site URL. Your index is available right away to search if you don’t need generative answers. If you need generative answers, you will need to verify your domain ownership first.
• Connect to a search app: Connect your site index to a new search app, where you will be able to manage the search experience. Make sure to turn LLM features on if you intend to use generative answers.
• Configure your search experience: Set up the right configurations that will define your search experience such as choosing between getting search results only, or being able to receive generative answers.
• Test & refine the search: Preview search results for various queries, and refine your search based on your needs. You can for example add metadata based on your site’s html, boost results based on publication date or other information, filter based on metadata or url patterns.
• Deploy the search to your site: you can choose to deploy using our out of the box widget as an HTML component to add to your site, or to directly integrate using the API.

Find similar things in seconds, even with billions of items. Vector Search unlocks powerful semantic matching for recommendations, chatbots, and more. Let's see how to build a recommendation engine with Vector Search:

1. Generate embeddings: Create a numerical representation (embedding) of your items to capture their semantic relationships. You can do this externally or use Vertex AI's generative AI.
2. Upload to Cloud Storage: Store your embeddings in Cloud Storage for Vector Search to access.
3. Connect to Vector Search: Link your embeddings to Vector Search to perform nearest neighbor search.
4. Create and deploy index: Build an index from your embeddings and deploy it to an endpoint for querying.
5. Query for recommendations: Use the index endpoint to query for approximate nearest neighbors, finding items semantically similar to your query.
6. Evaluate and adjust: Assess the results and refine the algorithm's parameters or scaling as needed to ensure accuracy and performance.