Question Answering

Question answering with tool integration on Subnet 20.


POSTv1/20/qna

Ask a question

Generate comprehensive answers using AI models with tool integration.

Required attributes

  • Name
    messages
    Type
    array
    Description

    Array of message objects with role (user, assistant, or system) and content.

  • Name
    tools
    Type
    array
    Description

    Array of tool objects with name, description, and argument schema.

Request

POST
v1/20/qna
curl -X POST https://api.bitmind.ai/oracle/v1/20/qna \
  -H "Authorization: Bearer {token}" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "Need help calculating the tip, what is 10% tip on a bill totalling $100"
      }
    ],
    "tools": [
      {
        "name": "tip_calculator",
        "description": "Calculate the tip amount",
        "arguments": {
          "bill_amount": {
            "required": true,
            "type": "number",
            "description": "the bill amount in dollars"
          },
          "tip_percent": {
            "required": true,
            "type": "number",
            "description": "the tip percentage as a whole number"
          }
        }
      }
    ]
  }'

Response

[
  {
    "role": "tool call",
    "content": "{\"name\": \"tip_calculator\", \"arguments\": {\"bill_amount\": 100, \"tip_percent\": 10}}"
  },
  {
    "role": "assistant",
    "content": "Using a 10% tip rate on a $100 bill results in a tip of $10."
  }
]

The question answering model

The question answering model contains the tool call and assistant response.

Properties

  • Name
    role
    Type
    string
    Description

    The role of the message sender.

  • Name
    content
    Type
    string
    Description

    The content of the message.