Request Body
{
    "point":  string, // Extension point, different modules may contain multiple extension points
    "params": {
        ...  // Parameters passed to each module's extension point
    }
}

API Response
{
    ...  // For the content returned by the API, see the specific module's design specifications for different extension points.
}

Check

When configuring API-based Extension in Cyberwisdom TalentBot LLMops, Cyberwisdom TalentBot LLMops will send a request to the API Endpoint to verify the availability of the API. When the API Endpoint receives point=ping, the API should return result=pong, as follows:

Header
Content-Type: application/json
Authorization: Bearer {api_key}

Request Body
{
    "point": "ping"
}

Expected API response
{
    "result": "pong"
}

For Example

Here we take the external data tool as an example, where the scenario is to retrieve external weather information based on the region as context.

API Specifications
POST https://fake-domain.com/api/Cyberwisdom TalentBot LLMops/receive

Header
Content-Type: application/json
Authorization: Bearer 123456

Request Body
{
    "point": "app.external_data_tool.query",
    "params": {
        "app_id": "61248ab4-1125-45be-ae32-0ce91334d021",
        "tool_variable": "weather_retrieve",
        "inputs": {
            "location": "London"
        },
        "query": "How's the weather today?"
    }
}

API Response
{
    "result": "City: London\nTemperature: 10°C\nRealFeel®: 8°C\nAir Quality: Poor\nWind Direction: ENE\nWind Speed: 8 km/h\nWind Gusts: 14 km/h\nPrecipitation: Light rain"
}

Code demo
The code is based on the Python FastAPI framework.

Install dependencies.
pip install 'fastapi[all]' uvicorn

Write code according to the interface specifications.
from fastapi import FastAPI, Body, HTTPException, Header
from pydantic import BaseModel

app = FastAPI()


class InputData(BaseModel):
    point: str
    params: dict


@app.post("/api/Cyberwisdom TalentBot LLMops/receive")
async def Cyberwisdom TalentBot LLMops_receive(data: InputData = Body(...), authorization: str = Header(None)):
    """
    Receive API query data from Cyberwisdom TalentBot LLMops.
    """
    expected_api_key = "123456"  # TODO Your API key of this API
    auth_scheme, _, api_key = authorization.partition(' ')

    if auth_scheme.lower() != "bearer" or api_key != expected_api_key:
        raise HTTPException(status_code=401, detail="Unauthorized")

    point = data.point

    # for debug
    print(f"point: {point}")

    if point == "ping":
        return {
            "result": "pong"
        }
    if point == "app.external_data_tool.query":
        return handle_app_external_data_tool_query(params=data.params)
    # elif point == "{point name}":
        # TODO other point implementation here

    raise HTTPException(status_code=400, detail="Not implemented")


def handle_app_external_data_tool_query(params: dict):
    app_id = params.get("app_id")
    tool_variable = params.get("tool_variable")
    inputs = params.get("inputs")
    query = params.get("query")

    # for debug
    print(f"app_id: {app_id}")
    print(f"tool_variable: {tool_variable}")
    print(f"inputs: {inputs}")
    print(f"query: {query}")

    # TODO your external data tool query implementation here, 
    #  return must be a dict with key "result", and the value is the query result
    if inputs.get("location") == "London":
        return {
            "result": "City: London\nTemperature: 10°C\nRealFeel®: 8°C\nAir Quality: Poor\nWind Direction: ENE\nWind "
                      "Speed: 8 km/h\nWind Gusts: 14 km/h\nPrecipitation: Light rain"
        }
    else:
        return {"result": "Unknown city"}

Launch the API service.
The default port is 8000. The complete address of the API is: http://127.0.0.1:8000/api/Cyberwisdom TalentBot LLMops/receivewith the configured API Key '123456'.

uvicorn main:app --reload --host 0.0.0.0

Configure this API in Cyberwisdom TalentBot LLMops.