openai / openai-python

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

OpenAI Python Library

The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language. It includes a pre-defined set of classes for API resources that initialize themselves dynamically from API responses which makes it compatible with a wide range of versions of the OpenAI API.


See the OpenAI API docs.


You don't need this source code unless you want to modify the package. If you just want to use the package, just run:

pip install --upgrade openai

Install from source with:

python install


The library needs to be configured with your account's secret key which is available on the website. Either set it as the OPENAI_API_KEY environment variable before using the library:

export OPENAI_API_KEY='sk-...'

Or set openai.api_key to its value:

import openai
openai.api_key = "sk-..."

# list engines
engines = openai.Engine.list()

# print the first engine's id

# create a completion
completion = openai.Completion.create(engine="ada", prompt="Hello world")

# print the completion


All endpoints have a .create method that support a request_timeout param. This param takes a Union[float, Tuple[float, float]] and will raise a openai.error.TimeoutError error if the request exceeds that time in seconds (See:

Microsoft Azure Endpoints

In order to use the library with Microsoft Azure endpoints, you need to set the api_type, api_base and api_version in addition to the api_key. The api_type must be set to 'azure' and the others correspond to the properties of your endpoint. In addition, the deployment name must be passed as the engine parameter.

import openai
openai.api_type = "azure"
openai.api_key = "..."
openai.api_base = ""
openai.api_version = "2021-11-01-preview"

# create a completion
completion = openai.Completion.create(engine="deployment-name", prompt="Hello world")

# print the completion

# create a search and pass the deployment-name as the engine Id.
search = openai.Engine(id="deployment-name").search(documents=["White House", "hospital", "school"], query ="the president")

# print the search

Please note that for the moment, the Microsoft Azure endpoints can only be used for completion, search and fine-tuning operations. For a detailed example on how to use fine-tuning and other operations using Azure endpoints, please check out the following Jupyter notebooks:

Microsoft Azure Active Directory Authentication

In order to use Microsoft Active Directory to authenticate to your Azure endpoint, you need to set the api_type to "azure_ad" and pass the acquired credential token to api_key. The rest of the parameters need to be set as specified in the previous section.

from azure.identity import DefaultAzureCredential
import openai

# Request credential
default_credential = DefaultAzureCredential()
token = default_credential.get_token("")

# Setup parameters
openai.api_type = "azure_ad"
openai.api_key = token.token
openai.api_base = ""
openai.api_version = "2022-03-01-preview"

# ...

Command-line interface

This library additionally provides an openai command-line utility which makes it easy to interact with the API from your terminal. Run openai api -h for usage.

# list engines
openai api engines.list

# create a completion
openai api completions.create -e ada -p "Hello world"

Example code

Examples of how to use this Python library to accomplish various tasks can be found in the OpenAI Cookbook. It contains code examples for:

  • Classification using fine-tuning
  • Clustering
  • Code search
  • Customizing embeddings
  • Question answering from a corpus of documents
  • Recommendations
  • Visualization of embeddings
  • And more

Prior to July 2022, this OpenAI Python library hosted code examples in its examples folder, but since then all examples have been migrated to the OpenAI Cookbook.


In the OpenAI Python library, an embedding represents a text string as a fixed-length vector of floating point numbers. Embeddings are designed to measure the similarity or relevance between text strings.

To get an embedding for a text string, you can use the embeddings method as follows in Python:

import openai
openai.api_key = "sk-..."  # supply your API key however you choose

# choose text to embed
text_string = "sample text"

# choose an embedding
model_id = "text-similarity-davinci-001"

# compute the embedding of the text
embedding = openai.Embedding.create(input=text_string, engine=model_id)['data'][0]['embedding']

An example of how to call the embeddings method is shown in this get embeddings notebook.

Examples of how to use embeddings are shared in the following Jupyter notebooks:

For more information on embeddings and the types of embeddings OpenAI offers, read the embeddings guide in the OpenAI documentation.

Fine tuning

Fine tuning a model on training data can both improve the results (by giving the model more examples to learn from) and reduce the cost & latency of API calls (by reducing the need to include training examples in prompts).

Examples of fine tuning are shared in the following Jupyter notebooks:

Sync your fine-tunes to Weights & Biases to track experiments, models, and datasets in your central dashboard with:

openai wandb sync

For more information on fine tuning, read the fine-tuning guide in the OpenAI documentation.


  • Python 3.7.1+

In general we want to support the versions of Python that our customers are using, so if you run into issues with any version issues, please let us know at


This library is forked from the Stripe Python Library.


License:MIT License


Language:Python 99.9%Language:Makefile 0.1%