Vertex AI Search
Vertex AI Search helps developers build secure, Google-quality search experiences for websites, intranet and RAG systems for generative AI agents and apps. Vertex AI Search is a part of Vertex AI Agent Builder.
*for customers new to Vertex AI Search. Credits are valid for 1 year period beginning from account signup with Vertex AI Search and automatically applied. Credit can be used across other eligible Agent Builder SKUs too. See pricing page for more details.
Features
Power your search with Google technologies
Unlock Google-quality search for your enterprise apps and experiences. Built on Google’s deep expertise and decades of experience in semantic search technologies, Vertex AI Search delivers more relevant results across your content, both structured and unstructured.
Get started in minutes and tailor search experiences to your specific needs with extensive customization abilities.
Getting started can be as easy as simply adding a search widget for an improved website search experience.
If you are building generative AI applications, Vertex AI Search can function as a grounding or Retrieval Augmented Generation (RAG) system using your data.
Vertex AI Search is designed for enterprise environments, offering seamless scalability, robust privacy controls, and comprehensive governance features.
Optimized for industries
Vertex AI Search has specialized offerings tuned for unique industry requirements like searching product catalogs, media libraries, and clinical data repositories.
Vertex AI Search for retail offers retailers the ability to improve the search, product recommendations, and browsing experience on their channels.
Vertex AI Search for media offers media and entertainment companies the ability to provide more personalized content recommendations powered by generative AI, increasing consumer time spent on their platforms, which can lead to higher engagement, revenue, and retention.
Vertex AI Search for healthcare and life sciences is a medically tuned search that improves patient and provider experience.
Solution for Retrieval Augmented Generation (RAG) in the enterprise
Today, there is a lot of excitement about RAG, an architecture that combines LLMs with a data retrieval system, or in other words, a search engine. Grounding LLM responses in your company's own data improves the accuracy, reliability, and relevance of generative AI apps, something that's critical for real-world business applications. You could build your own RAG system but this can be a highly complex process.
Vertex AI Search functions as an out-of-the-box RAG system for information retrieval. Under the hood with Vertex AI Search, we’ve simplified the end-to-end search and discovery process of managing ETL, OCR, chunking, embedding, indexing, storing, input cleaning, schema adjustments, information retrieval, and summarization to just a few clicks. This makes it easy for you to build RAG-powered apps using Vertex AI Search as your retrieval engine.
Vertex AI also offers a comprehensive set of APIs that help developers create bespoke RAG solutions. These APIs expose the underlying components of Vertex AI Search's out-of-the-box RAG system, empowering developers to address custom use cases or serve customers who want granular control. These include the Document AI Layout Parser API, ranking API, grounded generation API, and check grounding API.
Vector search for embeddings based applications
Vertex AI Search lets organizations and developers set up search engines out of the box. These search engines offer adequate customization for most enterprise needs and even offer automatic fine-tuning for embeddings. In some cases, you may have custom embeddings, and Vertex AI Search works fine with your own embeddings. However, more advanced developers who need direct control of a highly performant vector database to power niche use cases like recommendations and ad serving can use vector search, the vector database used by Vertex AI Search as a component for their use cases. We’ve recently updated Vector Search’s user experience so developers can create and deploy indexes without coding. We’ve also significantly reduced indexing latency from hours to minutes for smaller datasets.
AI for document understanding
Vertex AI search benefits from the document processing capabilities of our Document AI suite. With document understanding you can easily turn structured and unstructured documents into actionable data to increase operational efficiency, simplify business processes, and make better decisions.
Industry-compliant data privacy and security
When you use Vertex AI Search from Google Cloud, your data is secure in your cloud instance. Google does not access or use your data to train models or for any other purpose you have not explicitly authorized. Vertex AI Search also meets specific industry compliance standards like HIPAA, ISO 27000-series, and SOC -1/2/3. We’re expanding support for access transparency to provide customers with awareness of Googler administrative access to their data. Virtual Private Cloud Service Controls prevent customers or employees from infiltrating or exfiltrating data. We are also offering Customer-managed Encryption Keys (CMEK) in Preview, allowing customers to encrypt their core content with their own encryption keys.
Data freshness through connectors
Vertex AI Search can connect to your first-party, Google, and third-party applications through Vertex AI extensions and data connectors. Vertex AI extensions help in ingesting data and drive transactions on the users' behalf while data connectors ingest data with read-only access to key applications like Jira, Confluence, and Salesforce. Together, Vertex AI extensions and data connectors ensure your data is fresh across your search engines.
How It Works
With Vertex AI Search, you can go from frustrating keyword matching to modern conversational search experiences. You can also improve the quality of your generative AI applications by grounding them in your enterprise data using Vertex AI Search as an out of the box system for Retrieval Augmented Generation or RAG.
With Vertex AI Search, you can go from frustrating keyword matching to modern conversational search experiences. You can also improve the quality of your generative AI applications by grounding them in your enterprise data using Vertex AI Search as an out of the box system for Retrieval Augmented Generation or RAG.
Common Uses
A complete suite for your enterprise information needs
Improve search experiences for employees and customers
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.
Learning resources
Improve search experiences for employees and customers
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.
Enable Google-quality search on your website
Boost customer engagement with generative AI powered search
Boost customer engagement with generative AI powered search
- 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.
Tutorials, quickstarts, & labs
Boost customer engagement with generative AI powered search
Boost customer engagement with generative AI powered search
- 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.
Use Vertex AI Search for RAG
Grounding: increase factuality and relevance in generative AI agents and apps
Tired of AI making things up? Grounding or Retrieval Augmented Generation (RAG) ensures your AI's answers are based on your enterprise truth.
With Vertex AI's grounding feature, your generative AI models are anchored to reliable sources like Google Search or your own data, reducing "hallucinations" and boosting the trustworthiness of your results.
Say goodbye to unreliable AI and embrace the power of grounded intelligence for accurate, relevant, and actionable insights. Experience the difference Grounding makes in your agents and apps.
Learning resources
Grounding: increase factuality and relevance in generative AI agents and apps
Tired of AI making things up? Grounding or Retrieval Augmented Generation (RAG) ensures your AI's answers are based on your enterprise truth.
With Vertex AI's grounding feature, your generative AI models are anchored to reliable sources like Google Search or your own data, reducing "hallucinations" and boosting the trustworthiness of your results.
Say goodbye to unreliable AI and embrace the power of grounded intelligence for accurate, relevant, and actionable insights. Experience the difference Grounding makes in your agents and apps.
Create vector search and embeddings based apps
Build a recommendation engine with vector search
Build a recommendation engine with vector search
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:
- 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.
- Upload to Cloud Storage: Store your embeddings in Cloud Storage for Vector Search to access.
- Connect to Vector Search: Link your embeddings to Vector Search to perform nearest neighbor search.
- Create and deploy index: Build an index from your embeddings and deploy it to an endpoint for querying.
- Query for recommendations: Use the index endpoint to query for approximate nearest neighbors, finding items semantically similar to your query.
- Evaluate and adjust: Assess the results and refine the algorithm's parameters or scaling as needed to ensure accuracy and performance.
Tutorials, quickstarts, & labs
Build a recommendation engine with vector search
Build a recommendation engine with vector search
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:
- 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.
- Upload to Cloud Storage: Store your embeddings in Cloud Storage for Vector Search to access.
- Connect to Vector Search: Link your embeddings to Vector Search to perform nearest neighbor search.
- Create and deploy index: Build an index from your embeddings and deploy it to an endpoint for querying.
- Query for recommendations: Use the index endpoint to query for approximate nearest neighbors, finding items semantically similar to your query.
- Evaluate and adjust: Assess the results and refine the algorithm's parameters or scaling as needed to ensure accuracy and performance.
Improve the e-commerce experience in retail
Improve retail search and recommendations for your customers
Transform your customers experience, delivering improved search experiences similar to Google.
Increase conversions, reduce abandonment, and personalize recommendations – all with cutting-edge AI. Harness visual search, optimize results, and rest easy with fully managed infrastructure.
Don't settle for mediocre search quality – unlock your e-commerce potential with Vertex AI Search for retail.
Learning resources
Improve retail search and recommendations for your customers
Transform your customers experience, delivering improved search experiences similar to Google.
Increase conversions, reduce abandonment, and personalize recommendations – all with cutting-edge AI. Harness visual search, optimize results, and rest easy with fully managed infrastructure.
Don't settle for mediocre search quality – unlock your e-commerce potential with Vertex AI Search for retail.
Create high-accuracy processors to extract, classify, and split documents
Harness documents for deeper insights
Don't let your documents remain dormant data silos - transform them into actionable intelligence.
Extract valuable insights, streamline workflows, and make data-driven decisions faster than ever before. No more tedious manual tasks or complex model training - simply upload your documents and let Document AI do the heavy lifting.
With its advanced foundation models and customizable accuracy features, you'll unlock a new level of efficiency and accuracy in document analysis.
Learning resources
Harness documents for deeper insights
Don't let your documents remain dormant data silos - transform them into actionable intelligence.
Extract valuable insights, streamline workflows, and make data-driven decisions faster than ever before. No more tedious manual tasks or complex model training - simply upload your documents and let Document AI do the heavy lifting.
With its advanced foundation models and customizable accuracy features, you'll unlock a new level of efficiency and accuracy in document analysis.
Pricing
| Vertex AI Search | Vertex AI Search consists of a number of features that can be used independently or together. Vertex AI Search is a part of Vertex AI Agent Builder. Check out our $1,000 free trial offer for select SKUs* | |
|---|---|---|
| Features and usage | Description | Price |
Vertex AI search | Vertex AI search is a Google Search quality information retrieval and answer generation system that can help you create RAG-powered gen apps or improve the performance of your search applications. | Starting at $2 per 1,000 queries |
Vector search | For enterprises who need custom embeddings-based information retrieval, Vertex AI offers powerful vector search capabilities. View details | Refer to pricing page for more details |
Please visit our pricing page for more details on our $1,000 free trial offer. To make it easier for you to get started, we're offering customers new to Vertex AI Search (this includes existing Google Cloud customers) a one time credit of $1,000 per Google Cloud billing account, applicable up to 12 months post activation (or until you consume the amount, whichever is sooner).
Vertex AI Search
Vertex AI Search consists of a number of features that can be used independently or together. Vertex AI Search is a part of Vertex AI Agent Builder. Check out our $1,000 free trial offer for select SKUs*
Vertex AI search
Vertex AI search is a Google Search quality information retrieval and answer generation system that can help you create RAG-powered gen apps or improve the performance of your search applications.
Starting at
$2
per 1,000 queries
Vector search
For enterprises who need custom embeddings-based information retrieval, Vertex AI offers powerful vector search capabilities. View details
Refer to pricing page for more details
Please visit our pricing page for more details on our $1,000 free trial offer. To make it easier for you to get started, we're offering customers new to Vertex AI Search (this includes existing Google Cloud customers) a one time credit of $1,000 per Google Cloud billing account, applicable up to 12 months post activation (or until you consume the amount, whichever is sooner).