Create a model response

View as Markdown
POST /api/security_ai_assistant/chat/complete
Api key auth Basic auth

Spaces method and path for this operation:

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

Refer to Spaces for more information.

Create a model response for the given chat conversation.

Query parameters

  • content_references_disabled boolean

    If true, the response will not include content references.

    Default value is false.

application/json

Body Required

  • connectorId string Required

    Required connector identifier to route the request.

  • conversationId string(nonempty)

    A string that does not contain only whitespace characters.

    Minimum length is 1.

  • isStream boolean

    If true, the response will be streamed in chunks.

  • langSmithApiKey string

    API key for LangSmith integration.

  • langSmithProject string

    LangSmith project name for tracing.

  • messages array[object] Required

    List of chat messages exchanged so far.

    A message exchanged within the AI chat conversation.

    Hide messages attributes Show messages attributes object
    • content string

      The textual content of the message.

    • data object

      ECS-style metadata attached to the message.

      Additional properties are allowed.

    • fields_to_anonymize array[string]

      List of field names within the data object that should be anonymized.

    • role string Required

      The role associated with the message in the chat.

      Values are system, user, or assistant.

  • model string

    Model ID or name to use for the response.

  • persist boolean Required

    Whether to persist the chat and response to storage.

  • promptId string

    Prompt template identifier.

  • responseLanguage string

    ISO language code for the assistant's response.

Responses

  • 200 application/octet-stream

    Indicates a successful model response call.
  • 400 application/json

    Generic Error

    Hide response attributes Show response attributes object
    • error string

      Error type.

    • message string

      Human-readable error message.

    • statusCode number

      HTTP status code.
POST /api/security_ai_assistant/chat/complete 
curl \ --request POST 'https://localhost:5601/api/security_ai_assistant/chat/complete' \ --header "Authorization: $API_KEY" \ --header "Content-Type: application/json" \ --data '{"model":"gpt-4","persist":true,"isStream":true,"messages":[{"data":{"user_id":"user_789"},"role":"user","content":"What are some common phishing techniques?","fields_to_anonymize":["user.name","source.ip"]}],"promptId":"prompt_456","connectorId":"conn-001","conversationId":"abc123","langSmithApiKey":"sk-abc123","langSmithProject":"security_ai_project","responseLanguage":"en"}'
Request example 
{ "model": "gpt-4", "persist": true, "isStream": true, "messages": [ { "data": { "user_id": "user_789" }, "role": "user", "content": "What are some common phishing techniques?", "fields_to_anonymize": [ "user.name", "source.ip" ] } ], "promptId": "prompt_456", "connectorId": "conn-001", "conversationId": "abc123", "langSmithApiKey": "sk-abc123", "langSmithProject": "security_ai_project", "responseLanguage": "en" }