Query LMT (Language Model Testing)

Used to query the Language Model Testing endpoint for conversational interactions with AI agents. This endpoint processes user queries and returns AI-generated responses along with follow-up suggestions.

API Endpoint

Property	Value
Request Method	POST
Request URL	https://api.seliseblocks.com/ai-agent/query-lmt

Request

Request Example

curl -X POST 'https://api.seliseblocks.com/ai-agent/query-lmt' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "project_key": "YOUR_PROJECT_KEY",
    "query": "What are the key features of your platform?",
    "session_id": "session_abc123"
  }'

Request Headers

Field	Type	Required	Description
accept	string	Yes	Accepted response format. Use application/json
Content-Type	application/json	Yes	Data type, must be application/json.

Request Body

Request Body Schema

{
  "project_key": "string",
  "query": "string",
  "session_id": "string"
}

Request Body Parameters

Field	Type	Required	Description
project_key	string	Yes	The project key for your project.
query	string	Yes	The user's question or message to the AI agent.
session_id	string	Yes	Unique identifier for the conversation session to maintain context.

note

Session Management

• The session_id is used to maintain conversation context across multiple queries
• Use the same session_id for related queries in a conversation
• Generate a new session_id for each new conversation session
• The AI agent uses the session history to provide contextually relevant responses

Response

Success Response (200 OK)

Returns an object containing the AI agent's response and additional metadata.

{
  "is_success": true,
  "detail": "Query processed successfully",
  "query": "What are the key features of your platform?",
  "response": "Our platform offers several key features including: multi-language support for over 50 languages, real-time analytics and reporting, comprehensive API documentation, scalable architecture for high-volume requests, and advanced AI-powered automation capabilities. Each feature is designed to help businesses streamline their operations and improve customer engagement.",
  "response_timestamp": "2026-01-11T13:24:48.085Z",
  "next_step_questions": [
    "Can you tell me more about the multi-language support?",
    "What kind of analytics are available?",
    "How does the API integration work?"
  ],
  "session_id": "session_abc123"
}

Response Fields

Field	Type	Description
is_success	boolean	Indicates whether the query was processed successfully.
detail	string	Success or failure message with additional context.
query	string	The original user query that was processed.
response	string	The AI agent's generated response to the query.
response_timestamp	string	ISO 8601 timestamp of when the response was generated.
next_step_questions	array	Array of suggested follow-up questions.
session_id	string	The session identifier used for this conversation.

tip

Using Next Step Questions The next_step_questions array contains AI-generated suggestions for follow-up queries. These can be presented to users as clickable options to:

• Guide the conversation naturally
• Help users discover relevant information
• Improve user engagement
• Reduce friction in finding answers

Error Response (422 Unprocessable Entity)

Returns validation error details when the request body is invalid.

{
  "detail": [
    {
      "loc": [
        "body",
        "query"
      ],
      "msg": "field required",
      "type": "value_error.missing"
    }
  ]
}

Error Response Fields

Field	Type	Description
detail	array	Array of validation error objects.
loc	array	Location of the error in the request (e.g., body field).
msg	string	Human-readable error message.
type	string	Error type identifier.

Error Codes

Status Code	Description	Response Type
200	Successful Response	Success
400	Bad Request - Invalid query or session	Bad Request
422	Validation Error - Invalid request parameters	Unprocessable Entity
500	Internal Server Error - LLM processing failed	Server Error