For Agents
Run semantic search, recommendations, and RAG-grounded conversations over your own data via Vertex AI Search.
Get started with Discovery Engine API in minutes using your preferred integration method.
# Add to your MCP client config (Claude Desktop, Cursor, Windsurf)
{
"jentic": {
"url": "https://api.jentic.com/mcp",
"auth": "oauth"
}
}
# Then ask your agent:
"search a Vertex AI Search data store"
# → Jentic returns the GET /events tool with parameter schema, agent executes.What an agent can do with Discovery Engine API API.
Run semantic search and autocomplete over a custom data store of documents
Train and serve custom search ranking models on a data store
Ground LLM responses against indexed content via the groundingConfig:check endpoint
Map enterprise identities into a data store so search respects user-level ACLs
GET STARTED
Use for: Search a Vertex AI Search data store for documents matching a query, Check whether an LLM answer is grounded against indexed content, Train a custom search ranking model on a data store, Get autocomplete suggestions for a partial query
Not supported: Does not host raw LLMs, train embedding models, or manage GPUs — use for managed retrieval, ranking, and grounding via Vertex AI Search only.
Google Discovery Engine (the API behind Vertex AI Search and Vertex AI Conversation) lets developers build retrieval, search, and grounded conversational experiences over their own structured and unstructured data. The API exposes data stores, schemas, documents, completion configs, and grounding/check operations so teams can run semantic search, recommendations, and RAG-grounded chat against enterprise content. It supports custom model training, evaluation, and identity-mapped retrieval.
Run and inspect search-quality evaluations to measure model performance
Issue autocomplete suggestions and remove unwanted suggestions
Patterns agents use Discovery Engine API API for, with concrete tasks.
★ Enterprise Semantic Search
Build a private semantic search experience over indexed enterprise documents. The completionConfig:completeQuery endpoint provides autocomplete; the search endpoints (under data stores) return ranked results with snippets. Teams swap out keyword search for semantic ranking without managing embeddings or vector indexes themselves.
Call completeQuery on completionConfig 'projects/p/locations/global/dataStores/ds/completionConfig' with input 'reset pass' and return the top 5 suggestions.
RAG Grounding Verification
When a downstream LLM produces an answer, call groundingConfig:check to verify the answer is supported by indexed content. The endpoint returns citations and a grounding score, which apps use to gate publishing or display source links beside the answer. Critical for compliance-sensitive deployments.
Call groundingConfig:check with answer text 'Pricing is $99 per seat per month' and grounding sources set to data store ds-pricing, then return the grounding score and citations.
Custom Ranking Model Training
Train a custom search model on a data store via the trainCustomModel endpoint. The model learns from in-product engagement signals (clicks, dwell) and outranks the default for the customer's domain. Teams iterate by running listResults on evaluation jobs to measure NDCG and recall.
Trigger trainCustomModel on data store ds-products, then poll evaluation:listResults until the run is COMPLETED and return the NDCG@10 score.
Agent-Driven Search-and-Verify
Through Jentic, an AI agent can search a private data store for relevant context, then call groundingConfig:check to verify its synthesised answer is supported before responding to the user. Credentials are scoped per agent run by the MAXsystem vault.
Use Jentic to search 'search a Vertex AI data store', load the schema, execute the search for query 'refund policy' on ds-help, then call groundingConfig:check on the synthesised answer.
75 endpoints — google discovery engine (the api behind vertex ai search and vertex ai conversation) lets developers build retrieval, search, and grounded conversational experiences over their own structured and unstructured data.
METHOD
PATH
DESCRIPTION
/v1beta/{+completionConfig}:completeQuery
Get autocomplete suggestions
/v1beta/{+completionConfig}:removeSuggestion
Remove an autocomplete suggestion
/v1beta/{+groundingConfig}:check
Check whether an answer is grounded against sources
/v1beta/{+dataStore}:trainCustomModel
Train a custom ranking model on a data store
/v1beta/{+evaluation}:listResults
List results of a search-quality evaluation
/v1beta/{+identityMappingStore}:importIdentityMappings
Import enterprise identity mappings
/v1beta/{+completionConfig}:completeQuery
Get autocomplete suggestions
/v1beta/{+completionConfig}:removeSuggestion
Remove an autocomplete suggestion
/v1beta/{+groundingConfig}:check
Check whether an answer is grounded against sources
/v1beta/{+dataStore}:trainCustomModel
Train a custom ranking model on a data store
/v1beta/{+evaluation}:listResults
List results of a search-quality evaluation
Three things that make agents converge on Jentic-routed access.
Credential isolation
Google OAuth tokens for Discovery Engine are stored encrypted in the Jentic vault (MAXsystem). Agents receive scoped, short-lived tokens with cloud-platform scope only — service-account keys never enter the agent context.
Intent-based discovery
Agents search by intent (e.g., 'check if an LLM answer is grounded') and Jentic returns the matching groundingConfig:check operation with its parameter schema across the 75-endpoint surface.
Time to first call
Direct Discovery Engine integration: 3-5 days for OAuth, data store provisioning, query and grounding wiring. Through Jentic: under 1 hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Vertex AI API
Foundational LLMs, embeddings, and training infra that pairs with Discovery Engine retrieval
Use Vertex AI for raw model inference and embeddings; use Discovery Engine for managed retrieval, ranking, and grounding.
Dialogflow API
Conversational orchestration that can be grounded with Discovery Engine
Use Dialogflow for structured flows and intent routing; ground responses with Discovery Engine when the answer must come from indexed content.
Custom Search API
Lightweight site-search over public web content — different from private RAG
Choose Custom Search for keyword search across configured public sites; choose Discovery Engine for private semantic search and grounding.
Specific to using Discovery Engine API API through Jentic.
What authentication does the Discovery Engine API use?
OAuth 2.0 with the cloud-platform scope. Through Jentic, OAuth tokens are scoped per agent run and stored encrypted in the MAXsystem vault, so service-account JSON keys never enter the agent runtime.
Can I ground LLM answers against my own documents with Discovery Engine?
Yes. The /v1beta/{groundingConfig}:check endpoint takes an answer plus grounding sources (data stores or chunks) and returns a grounding score plus citations. Use it to gate publishing of LLM-generated content.
What are the rate limits for the Discovery Engine API?
Quotas are per project and depend on the operation: query and complete operations have higher per-second budgets than write or train operations. Check the Google Cloud Console under APIs and Services for the current quotas on your project.
How do I run autocomplete on a data store through Jentic?
Search 'autocomplete a Vertex AI Search query', load the schema for /v1beta/{completionConfig}:completeQuery, then execute it with your completion config name and input string. Jentic returns the suggestion list.
Does Discovery Engine support per-user ACLs?
Yes. Use identityMappingStore:importIdentityMappings to load enterprise identities, then queries scoped to a user respect document-level ACLs at search time. Useful for HR, legal, and finance content where access varies by role.
Is the Discovery Engine API free?
No. Pricing is per query and per indexed document, with tiers for Search, Recommendations, and Conversation. Custom model training has separate compute charges. Check current pricing in the Google Cloud Console.
/v1beta/{+identityMappingStore}:importIdentityMappings
Import enterprise identity mappings