models how to use functions with GPT chat API - Azure/azureml-assets GitHub Wiki

how-to-use-functions-with-GPT-chat-API

Overview

The "Use Functions with Chat Models" is a chat model illustrates how to employ the LLM tool's Chat API with external functions, thereby expanding the capabilities of GPT models. The Chat Completion API includes an optional 'functions' parameter, which can be used to stipulate function specifications. This allows models to generate arguments that comply with the given specifications. However, it's important to note that the API will not directly execute any function calls. The responsibility of executing function calls using the model outputs lies with the developers.

Inference samples

Inference type CLI VS Code Extension
Real time deploy-promptflow-model-cli-example deploy-promptflow-model-vscode-extension-example
Batch N/A N/A

Sample inputs and outputs (for real-time inference)

Sample input

{
    "inputs": {
        "question": "How about London next week?"
    }
}

Sample output

{
    "outputs": {
        "answer": "Function generation requested, function = get_n_day_weather_forecast, args = { 'location': 'London', 'num_days': 7, 'format': 'celsius' }"
    }
}

Version: 10

View in Studio: https://ml.azure.com/registries/azureml/models/how-to-use-functions-with-GPT-chat-API/version/10

Properties

is-promptflow: True

azureml.promptflow.section: gallery

azureml.promptflow.type: chat

azureml.promptflow.name: Use GPT Function Calling

azureml.promptflow.description: Learn how to use GPT function calling to extend the capabilities of GPT models with external data sources.

inference-min-sku-spec: 2|0|14|28

inference-recommended-sku: Standard_DS3_v2

⚠️ **GitHub.com Fallback** ⚠️