OpenAI Chat Completions API
OpenAI Chat Completions API
The OpenAI Chat Completions API is a powerful tool for developers to integrate the capabilities of OpenAI’s advanced language models(LLMs like GPT-4) into their applications. This API is designed to respond to text inputs.
To understand the API, use the OpenAI platform playground to interact with the model.
Login to the Open AI platform playground.
Choose Chat from the drop-down.
Pick an AI model and adjust the settings.
Submit a user prompt for the model.
Chat Completions API
Send a POST request to the following API endpoint.
POST /v1/chat/completions
Prerequisites
- OpenAI Python SDK Setup.
- API Keys: Generate API keys through the OpenAI Platform to authenticate your API requests.
Code
Let’s write a simple Python program to invoke the API. The user prompt is a simple math equation to be solved.
“””
OpenAI Chat Completions API Demo
— Python OpenAI SDK
— OpenAI Tutorials — www.TestingDocs.com
“””
from openai import OpenAI
client = OpenAI()
prompt = “3 + 9 = ?”
print(“User Prompt: “,prompt)
# Chat Completions API call
response = client.chat.completions.create(
model=”gpt-4-turbo-preview”,
messages=[
{
“role”: “user”,
“content”: prompt
}
],
temperature=1,
max_tokens=256,
top_p=1,
frequency_penalty=0,
presence_penalty=0,
)
print(“Assistant Response: “,response.choices[0].message.content)
Output
Run the program to invoke the API and see the AI assistant response message.
That’s it. You successfully ran the API call and got the AI model response.
The Assistants API is the next evolution to this API. However, the Assistants API
is still in the beta phase.
