Skip to main content
POST
/
sessions
/
{session_id}
/
chat
Python
from meibel import MeibelClient

client = MeibelClient(api_key="your-api-key")

# Create request body
body = ChatMessageRequest(name="Example")

result = client.agents.sessions.send_chat_message("session_id_value", body=body)
print(result)
{
  "signal_id": "<string>",
  "response": {
    "message": "",
    "sources": [
      {
        "title": "<string>",
        "url": "<string>",
        "snippet": "<string>",
        "data_element_id": "<string>",
        "relevance_score": 123
      }
    ],
    "follow_up_questions": [
      "<string>"
    ],
    "call_to_actions": [
      {
        "label": "<string>",
        "action": "<string>",
        "action_data": {}
      }
    ],
    "artifacts": [
      {
        "artifact_id": "<string>",
        "filename": "<string>",
        "mime_type": "<string>",
        "content": "<string>",
        "storage_url": "<string>",
        "size_bytes": 123,
        "created_at": "<string>"
      }
    ]
  },
  "assistant_response": "<string>",
  "tool_activity": [
    {
      "tool_id": "<string>",
      "tool_name": "<string>",
      "arguments": {},
      "timestamp": "<string>",
      "result": {}
    }
  ],
  "thinking": "<string>",
  "token_usage": {}
}

Documentation Index

Fetch the complete documentation index at: https://docs.meibel.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

Meibel-API-Key
string
header
required

Path Parameters

session_id
string
required

Body

application/json

Request body for chat message endpoints.

user_message
string
required

The user's chat message

timeout_seconds
integer | null

Maximum time to wait for response (seconds)

include_thinking
boolean | null

Whether to include thinking content in response

include_tool_activity
boolean | null

Whether to include tool call/result activity

Response

Successful Response

Response from the non-streaming chat endpoint.

signal_id
string
required

Unique ID for this message exchange

response
ChatResponse · object
required

The structured response

assistant_response
string
required

The assistant response in text-format

tool_activity
ToolActivity · object[] | null

Tool calls made during response generation

thinking
string | null

LLM thinking/reasoning content

token_usage
Token Usage · object

Token usage statistics