Skip to main content
POST
Query
Query the Vrin knowledge base. Returns an AI-generated answer backed by knowledge graph facts and vector search results.
string
required
Bearer token. Example: Bearer vrin_live_abc123
string
required
Natural-language question to answer.
boolean
default:"false"
If true, the response is delivered as Server-Sent Events (SSE). Each event contains a JSON object with type and data fields.
string
default:"chat"
Answer depth: "chat" (concise), "thinking" (reasoning chains), "research" (exhaustive multi-hop).
string
Override retrieval depth: "basic", "thinking", "research".
string
LLM model override (e.g. "gpt-4o").
string
Conversation session ID to continue.
boolean
default:"false"
If true, maintain conversation context. A session_id will be returned in the response.
boolean
default:"true"
If true, include AI-generated summary. Set to false for raw fact retrieval only.
boolean
default:"false"
Enable web search augmentation.
string[]
Upload IDs to include as additional context.

Non-streaming response

Streaming response (SSE)

When stream: true, the response is text/event-stream:

SSE event types

Insufficient coverage

When the knowledge base has no relevant facts, the response includes insufficient_coverage: true and skips LLM generation.