Sample python script: using Text-Bison model via Azure OpenAI

To use the Text-Bison model via Azure OpenAI, you need to set up your Azure account and configure the necessary resources. Below is a sample Python script that demonstrates how to interact with the Text-Bison model using Azure OpenAI.

Prerequisites

1. Azure Account: Create an Azure account if you don’t have one.
2. Create an OpenAI Resource: Set up an OpenAI resource in the Azure portal and obtain your endpoint and API key.
3. Install Required Libraries:

   pip install requests

Sample Python Script

Here's a basic script to interact with the Text-Bison model:

import requests

# Azure OpenAI configuration
endpoint = "https://<your-endpoint>.openai.azure.com/"
api_key = "<your-api-key>"
deployment_name = "text-bison"  # Your deployment name

def generate_text(prompt):
    url = f"{endpoint}openai/deployments/{deployment_name}/completions?api-version=2023-05-15"

    headers = {
        "Content-Type": "application/json",
        "api-key": api_key
    }

    # Define the request body
    data = {
        "prompt": prompt,
        "max_tokens": 100,
        "temperature": 0.7
    }

    # Make the request to the Azure OpenAI API
    response = requests.post(url, headers=headers, json=data)

    if response.status_code == 200:
        return response.json()['choices'][0]['text'].strip()
    else:
        print(f"Error: {response.status_code} - {response.text}")
        return None

if __name__ == "__main__":
    prompt = "What are the benefits of using AI in healthcare?"
    generated_text = generate_text(prompt)

    if generated_text:
        print("Generated Text:", generated_text)

Explanation

1. Configuration: Replace <your-endpoint> and <your-api-key> with your Azure OpenAI endpoint and API key. The deployment_name should match the name of your Text-Bison model deployment.

2. Function to Generate Text:

   • The generate_text function constructs the API request.
   • It sets the necessary headers for authentication and specifies the request body, including the prompt and parameters like max_tokens and temperature.

3. Making the Request:

   • The script uses the requests library to send a POST request to the Azure OpenAI API.
   • If the request is successful, it returns the generated text; otherwise, it prints an error message.

4. Execution: The script runs a prompt and prints the generated text.

Notes

• Ensure you have set the proper permissions and configurations in your Azure portal.
• Adjust parameters such as max_tokens and temperature based on your requirements.
• Make sure you handle any API limits or quotas as specified by Azure.