Skip to main content
Google Cloud Documentation
Documentation
  • Get Started
  • Get Started with Google Cloud
  • Product List
  • Cloud Customer Care
  • Featured Products
  • Agent Platform
  • Apigee API Management
  • BigQuery
  • Compute Engine
  • Cloud CDN
  • Cloud Run
  • Cloud Storage
  • Cloud SQL
  • Gemini Enterprise
  • Google Kubernetes Engine
  • Looker
  • Cross-product Tools
  • Access and resources management
  • Costs and usage management
  • Infrastructure as code
  • SDK, languages, frameworks, and tools
  • Technology Areas
  • AI and ML
  • Application development
  • Application hosting
  • Compute
  • Data analytics and pipelines
  • Databases
  • Distributed, hybrid, and multicloud
  • Industry solutions
  • Migration
  • Networking
  • Observability and monitoring
  • Security
  • Storage
/
Console
  • English
  • Deutsch
  • Español – América Latina
  • Français
  • Indonesia
  • Italiano
  • Português – Brasil
  • עברית
  • 中文 – 简体
  • 中文 – 繁體
  • 日本語
  • 한국어
Sign in
  • Gemini Enterprise Agent Platform
Start free
Overview Studio Agents Models Notebooks
  • Agent Platform
  • Generative AI
Engineering Blog
Google Cloud Documentation
  • Documentation
    • More
    • Overview
    • Studio
    • Agents
    • Models
    • Notebooks
    • Pricing
      • More
    • Engineering Blog
  • Console
  • Overview
  • Get an API key
  • Get started
  • Build an agent with ADK and Agents CLI
  • Build
  • Overview
  • Create agents
    • Overview
    • Set up the environment
    • Prebuilt agents
      • Agent Garden
      • Gemini Deep Research Agent
        • Use Deep Research
        • Agent card
    • Create agents in the console
      • Agent Studio
    • Managed Agents API on Agent Platform
      • Overview
      • Create and manage agents
      • Interact with agents
      • Sandbox environment
      • Evaluate agents
    • Create agents with frameworks
      • Quickstart: Develop with agent frameworks on Agent Runtime
      • Agent Development Kit (ADK)
        • ADK Overview
        • Quickstart: Develop with Agent Development Kit on Agent Runtime
        • Develop an ADK agent
      • Agent2Agent
      • LangChain
      • LangGraph
      • AG2
      • LlamaIndex
      • Create a custom agent
  • Skill Registry
    • Overview
    • Create and manage skills
  • Authentication
    • Authenticate to services using 3-legged OAuth with auth manager
    • Authenticate to services using 2-legged OAuth with auth manager
    • Authenticate to services using API key with auth manager
  • RAG Engine
    • RAG overview
    • RAG quickstart
    • RAG Engine billing
    • Deployment modes in RAG Engine
      • Overview
      • Managing Spanner mode
      • Serverless mode
      • Switching between modes
    • Data ingestion
    • Supported models
      • Generative models
      • Embedding models
    • Document parsing
      • Supported documents
      • Fine-tune RAG transformations
      • Use Document AI layout parser
      • Use the LLM parser
    • Vector database choices in RAG
      • Overview of vector database choices
      • Use RagManagedDb with RAG
      • Use Agent Platform Vector Search 2.0 with RAG
      • Use Agent Platform Vector Search with RAG
      • Use Feature Store with RAG
      • Use Weaviate with RAG
      • Use Pinecone with RAG
      • Use Agent Platform Search with RAG
    • Reranking for RAG
    • Manage your RAG corpus
    • Filter with metadata search
    • Use CMEK with RAG
    • Use RAG in Gemini Live API
    • RAG Cross Corpus Retrieval
  • Tokenizer
    • List and count tokens
    • Use the Count Tokens API
  • Multimodal datasets
  • Use Agent Search
  • Perform vector similarity searches
    • Vector Search overview
    • Try it
    • Get started
      • Vector Search quickstart
      • Before you begin
      • Notebook tutorials
    • About hybrid search
    • Create and manage index
      • Input data format and structure
      • Create and manage your index
      • Storage-optimized indexes
      • Index configuration parameters
      • Update and rebuild index
      • Filter vector matches
      • Import index data from BigQuery
      • Embeddings with metadata
    • Deploy and query an index
      • Private Service Connect (recommended)
        • Set up Vector Search with Private Service Connect
        • Query
        • JSON Web Token authentication
      • Public endpoint
        • Deploy
        • Query
      • Private services access
        • Set up a VPC network peering connection
        • Deploy
        • Query
        • JSON Web Token authentication
    • Monitor a deployed index
    • Use custom organization policies
    • Get support
  • Agent Retrieval (formerly Vector Search 2.0) - Intelligent Retrieval for AI Applications
    • Overview
    • Try it
    • Migrate from Vector Search 1.0
    • Collections
    • Autogenerated Embeddings
    • Data Objects
    • Using ETags for Concurrency Control
    • Querying Collections for Data Objects
    • Searching for Data Objects
    • Reranking
    • Indexes
    • Use MCP to connect to AI and custom applications
    • Customer Managed Encryption Keys (CMEK)
    • Audit logging
    • Quotas
    • Get support
  • Scale
  • Overview
  • Agent Runtime
    • Overview
    • Deploy agents
    • Provision agents with Terraform
    • Manage deployed agents
      • Overview
      • Manage agent access
      • Manage revisions and traffic
      • Set up tracing
      • Set up logging
      • Set up monitoring
    • Use agents
      • Overview
      • Agent Development Kit
      • Agent2Agent
      • LangChain
      • LangGraph
      • AG2
      • LlamaIndex
      • Custom
      • Runtime contract
    • Agent Identity with Agent Runtime
    • Route traffic through Agent Gateway
    • Bidirectional streaming
    • Optimize and scale Agent Runtime performance
    • Use Private Service Connect (PSC) interfaces
    • Agent Runtime SDK migration
  • Sessions
    • Overview
    • Manage sessions with Agent Development Kit
    • Manage sessions using the console or API calls