Create Agent Response

POST

/api/v2/agents/{agent_id}/responses

Allows generating a new response from a specific agent based on user input. This endpoint processes the user's query, utilizes AI models,
and optionally retrieves information from predefined sources before returning a response.

Staging behaviour:

Pass agent_version=staging as a query parameter to generate the response using the staging version instead of the published agent's.

Path Parameters:

agent_id: ID of the agent for which the response is to be created.

Request Body:

A JSON object with fields to process the chat interaction.

Returns:

JsonResponse: A JSON response containing the result of the chat interaction or an error message.

Current Version:

2.0.0

Request

Path Params

Header Params

Body Params

application/json

Required

Examples

Responses

🟢201Created

application/json

Success

Bodyapplication/json

🟠400Bad Request

🟠403Record Not Found

🟠404Server Error

🔴500

🔴503

Request Example

Shell

JavaScript

Java

Swift

curl --location --globoff 'https:///api/v2/agents//responses' \
--header 'Organization-Id;' \
--header 'Ocp-Apim-Subscription-Key: ' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
    "history": [
        {
            "user": "string",
            "bot": "string"
        }
    ],
    "model": "string",
    "chat_thread_id": 0,
    "overrides": {
        "sources": true,
        "corpus_ids": [
            0
        ]
    },
    "query_source": "string"
}'

Response Example

201 - Example 1

{
    "message": "string",
    "success": true,
    "data": {
        "answer": "string",
        "sources": "string",
        "followup_questions": [
            "string"
        ],
        "indexes": [
            "string"
        ],
        "query": "string",
        "total_tokens": 0,
        "prompt_tokens": 0,
        "completion_tokens": 0,
        "cache_hit": true,
        "history": [
            {
                "user": "string",
                "bot": "string"
            }
        ],
        "prompt_prefix": "string",
        "instructions": [
            "string"
        ],
        "agent_mode": "string",
        "references": [
            {
                "number": 0,
                "url": "string",
                "order": 0
            }
        ],
        "success": true,
        "corpus_ids": [
            0
        ],
        "run_id": "string",
        "chat_thread_name": "string",
        "thread_id": 0,
        "agent_response_id": 0
    }
}

Generate Agent Response (Non-Streaming)

Delete an Agent Response