Openai python api

Introduction

You can interact with the API through HTTP requests from any language, via our official Python bindings, our official Node.js library, or a community-maintained library.

To install the official Python bindings, run the following command:

pip install openai

To install the official Node.js library, run the following command in your Node.js project directory:

npm install openai@^4.0.0

Authentication

The OpenAI API uses API keys for authentication. Visit your API Keys page to retrieve the API key you'll use in your requests.

Remember that your API key is a secret! Do not share it with others or expose it in any client-side code (browsers, apps). Production requests must be routed through your own backend server where your API key can be securely loaded from an environment variable or key management service.

All API requests should include your API key in an Authorization HTTP header as follows:

Authorization: Bearer OPENAI_API_KEY

Organization (optional)

For users who belong to multiple organizations, you can pass a header to specify which organization is used for an API request. Usage from these API requests will count as usage for the specified organization.

Example curl command:

curl https://api.openai.com/v1/models \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "OpenAI-Organization: YOUR_ORG_ID"

Example with the openai Python package:

from openai import OpenAI

client = OpenAI(
  organization='YOUR_ORG_ID',
)

Example with the openai Node.js package:

import OpenAI from "openai";

const openai = new OpenAI({
  organization: 'YOUR_ORG_ID',
});

Organization IDs can be found on your Organization settings page.

Making requests

You can paste the command below into your terminal to run your first API request. Make sure to replace $OPENAI_API_KEY with your secret API key.

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
     "model": "gpt-3.5-turbo",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   }'

This request queries the gpt-3.5-turbo model (which under the hood points to the latest gpt-3.5-turbo model variant) to complete the text starting with a prompt of "Say this is a test". You should get a response back that resembles the following:

{
    "id": "chatcmpl-abc123",
    "object": "chat.completion",
    "created": 1677858242,
    "model": "gpt-3.5-turbo-1106",
    "usage": {
        "prompt_tokens": 13,
        "completion_tokens": 7,
        "total_tokens": 20
    },
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "\n\nThis is a test!"
            },
            "finish_reason": "stop",
            "index": 0
        }
    ]
}

Now that you've generated your first chat completion, let's break down the response object. We can see the finish_reason is stop which means the API returned the full chat completion generated by the model without running into any limits. In the choices list, we only generated a single message but you can set the n parameter to generate multiple messages choices.

Streaming

The OpenAI API provides the ability to stream responses back to a client in order to allow partial results for certain requests. To achieve this, we follow the Server-sent events standard.

Our official Node and Python libraries handle Server-sent events for you. In Python, a streaming request looks like:

from openai import OpenAI

client = OpenAI()

stream = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Say this is a test"}],
    stream=True,
)
for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

In Node / Typescript, a streaming request looks like:

import OpenAI from "openai";

const openai = new OpenAI();

async function main() {
    const stream = await openai.chat.completions.create({
        model: "gpt-4",
        messages: [{ role: "user", content: "Say this is a test" }],
        stream: true,
    });
    for await (const chunk of stream) {
        process.stdout.write(chunk.choices[0]?.delta?.content || "");
    }
}

main();

Parsing Server-sent events

Parsing Server-sent events is non-trivial and should be done with caution. Simple strategies like splitting by a new line may result in parsing errors. We recommend using existing client libraries when possible.