Create a model response

Server: https://{kibana_url}

POST /api/security_ai_assistant/chat/complete
POST /s/{space_id}/api/security_ai_assistant/chat/complete

Api key auth Basic auth

Refer to Spaces for more information.

Create a model response for the given chat conversation.

Query Parameters

content_references_disabled boolean · default: false: If true, the response will not include content references.

Request

Responses

Indicates a successful model response call.

application/octet-stream

Bad Request response.

application/json

Examples

Request curl 1 / 1 language

curl Shell

curl \
 --request POST 'http://localhost:5601/api/security_ai_assistant/chat/complete' \
 --header "Authorization: $API_KEY" \
 --header "Content-Type: application/json" \
 --data '{"connectorId":"conn-001","persist":true,"messages":[{"role":"user","content":"What are common phishing techniques?"}]}'

Request

Request example

{
  "connectorId": "conn-001",
  "conversationId": "abc123",
  "isStream": true,
  "langSmithApiKey": "\u003CLANGSMITH_API_KEY\u003E",
  "langSmithProject": "security_ai_project",
  "messages": [
    {
      "content": "What are some common phishing techniques?",
      "data": {
        "user_id": "user_789"
      },
      "fields_to_anonymize": [
        "user.name",
        "source.ip"
      ],
      "role": "user"
    }
  ],
  "model": "gpt-4",
  "persist": true,
  "promptId": "prompt_456",
  "responseLanguage": "en"
}

Response

(streaming binary response)

{
  "error": "Bad Request",
  "message": "Invalid request payload.",
  "statusCode": 400
}

Query Parameters

Request { connectorId , conversationId , isStream , langSmithApiKey , langSmithProject , messages , model , persist , promptId , responseLanguage , }

Responses

Request