Generate streaming AI chat response

Generates an AI response with real-time streaming for improved user experience. This endpoint redirects to the o2-sre-agent service for processing.

post/api/{org_id}/ai/chat_stream

Request

Base URL
https://api.openobserve.ai (the document declares no server; this is the origin it was published from)
Auth
API key in header Authorization
TypeScript
https://skmtc.dev/openobserve/apis/openobserve-api-http/docs/api/:org_id/ai/chat_stream/post.ts
A function with typed inputs. Its response is checked against the schema.

Path parameters

org_idstring required

Organization name

Request body

confirm_timeout_secsinteger nullable

Seconds the agent waits for a tool approval before denying it (capped at 600).

contextobject

Contextual information for the AI assistant. Should include:

start_time: Start of the time range in microseconds (required for search queries)
end_time: End of the time range in microseconds (required for search queries)
stream_name: Current stream being viewed (optional)
stream_type: Type of stream - logs, metrics, traces (optional)

The frontend should pass the user's currently selected time range and stream context to enable the AI assistant to search within the relevant data scope.

messagesobject[] required

Chat messages in the conversation.

modelstring

Optional model name override.

providerstring

Optional provider name override.

Response

Server-sent event stream

Changes

No recorded changes to this operation across all 1 revision of this API.