Working with GPT-4 and ChatGPT models on Azure

Manu Bhardwaj
4 min readMar 22, 2023

--

Artificial intelligence (AI) has become an essential part of our daily lives, and its impact on society is undeniable. With the release of the new ChatGPT model, gpt-3.5-turbo, and the GPT-4 models, gpt-4 and gpt-4–32k, Azure OpenAI Service has made it easier for developers to create more effective conversational dialogue. However, it’s essential to keep in mind the changes that come with the introduction of these models, including the Chat Completions API and changes to how models are versioned.

[
{"role": "system", "content": "You are an AI assistant."},
{"role": "user", "content": "What is few shot learning?"}
]

Firstly, the Chat Completions API is a valuable addition to the Azure OpenAI Service. It allows developers to pass in prompts as an array of messages, making it easy to keep track of the conversation and include previous messages in the prompt for context. This feature is particularly useful in multi-turn conversations, where context is critical for effective communication. By using the Chat Completions API, developers can create more accurate and effective conversational dialogue.

import os
import openai

openai.api_type = "azure"
openai.api_base = "https://{resource-name}.openai.azure.com/"
openai.api_version = "2023-03-15-preview"
openai.api_key = os.getenv("OPENAI_API_KEY")

response = openai.ChatCompletion.create(
engine = "gpt-35-turbo",
messages = [
{"role":"system","content":"You are an AI assistant."},
{"role":"user","content":"What is few shot learning?"}
]
)

Secondly, the changes to how models are versioned are persuasive. OpenAI plans to make new versions of the ChatGPT and GPT-4 models available regularly, ensuring that developers have access to the latest versions of these models. By choosing to use the “latest” version of the model, developers can ensure that their requests are always served with the most up-to-date version of the model. The faster deprecation timelines for models also ensure that developers can continue to use the latest versions of these models, creating more effective conversational dialogue.

Organizing these changes and features in Azure OpenAI Service is also essential. The Models page and the Models API make it easy for developers to keep track of the deprecation times for models and ensure that they are using the most up-to-date version of the model. Additionally, Azure OpenAI Studio provides an easy-to-use platform for developers to get started with these models. The Chat playground in the Azure OpenAI Studio allows developers to customize their system message, test out the model, and iterate from there, creating more effective conversational dialogue.

Finally, the language used in this article is clear and easy to understand. By explaining the changes and features of Azure OpenAI Service in simple terms, developers can quickly grasp the benefits of using these models. The article’s clear language ensures that developers do not need to re-read it and can understand the changes that come with the introduction of these models.

In conclusion, Azure OpenAI Service has made it easier for developers to create more effective conversational dialogue with the introduction of the ChatGPT model, gpt-3.5-turbo, and the GPT-4 models, gpt-4 and gpt-4–32k. By using the Chat Completions API, choosing the latest version of the model, and keeping track of the deprecation times for models, developers can create more accurate and effective conversational dialogue. Additionally, Azure OpenAI Studio provides an easy-to-use platform for developers to get started with these models, creating a more caring world for developers and the people who use their applications.

--

--

Manu Bhardwaj
Manu Bhardwaj

No responses yet