Generate Agent Response (Non-Streaming)

POST

/response-service/api/v2/agents/{agent_id}/responses

Ask an agent a question and get back a complete answer in an agent response. The agent searches configured corpora (knowledge bases), when available, and responds directly. Use this when you don't need to see the thinking process.

Usage Limits

Subject to your organization's spending limit. Once you reach the limit, further requests fail with 429 Quota limit exceeded.

Current Version

2.2.0

Changelog

2.2.0: Added commands.required_skill_ids to apply specific connected skills to a request.

2.1.1: Added param_override field to control reasoning effort (e.g. {"effort": "high"}).

2.1.0: User is now tracked automatically from your API key; caching_enabled can be set via the agent settings.

Request

Path Params

Query Params

Header Params

Body Params application/jsonRequired

Examples

Responses

🟢200OK

application/json

The agent answered.

Bodyapplication/json

🟠400Bad Request

🟠401Parameter Error

🟠403Server Error

🟠422

🟠429

🔴500

🔴502

🔴503

Request Example

Shell

JavaScript

Java

Swift

curl --location --globoff 'https:///response-service/api/v2/agents//responses?agent_version=' \
--header 'Ocp-Apim-Subscription-Key: ' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
    "attachment_metadata": {
        "corpus_id": 1,
        "doc_ids": [
            1
        ]
    },
    "chat_thread_id": 1,
    "history": [
        {
            "bot": "Paris is the capital of France.",
            "user": "What is the capital of France?"
        }
    ],
    "is_file_attached": false,
    "overrides": {
        "param_override": {
            "effort": "high"
        },
        "thinking_mode": "instant"
    },
    "query_source": "web",
    "share_token": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
    "user_query": "and what about the weather?"
}'

Response Example

200 - Example 1

{
    "data": {
        "agent_response_id": 1,
        "answer": "The capital of France is Paris.",
        "artifacts": [],
        "attached_file_metadata": [
            {
                "filename": "travel_policy.pdf",
                "id": 1
            }
        ],
        "blocked": false,
        "cache_hit": false,
        "chat_thread_name": "Chat Thread Name",
        "citations": [
            {
                "references": [
                    "https://storageaccount.blob.core.windows.net/container/policy.pdf",
                    "https://storageaccount.blob.core.windows.net/container/guide.pdf"
                ],
                "tool_name": "RetrieverTool"
            },
            {
                "references": [
                    "https://example.com/article"
                ],
                "tool_name": "tavily_search"
            }
        ],
        "corpus_id": 42,
        "data_points": [],
        "fork": {
            "status": "success"
        },
        "references": [],
        "thread_id": 1,
        "trace_id": "4b1c8f2ad7e94a1cb0f35d6e7a91c204"
    },
    "message": "Successfully generated the response",
    "success": true
}

Stream Agent Response (SSE)

Create Agent Response