GitVita
New repositoryImport repositoryNew issue
Your repositories Your dashboard Sign in

openai/openai-python

Public

mirrored from https://github.com/openai/openai-pythonAvailable

Watch0Fork0Star0
CodeCommitsIssuesPull requestsActionsInsightsSecurity
v0.23.0

Branches

Tags

  • No tags available.
0Branches0Tags
Go to file
Add file
Code

Clone

HTTPS

Download ZIP

README.md

203lines · modeblame

RawDownload
Latest commit unavailable.
3c6d4cd6Greg Brockman5 years ago1# OpenAI Python Library
2
3The OpenAI Python library provides convenient access to the OpenAI API
4from applications written in the Python language. It includes a
5pre-defined set of classes for API resources that initialize
6themselves dynamically from API responses which makes it compatible
7with a wide range of versions of the OpenAI API.
8
9## Documentation
10
d53d9efbRachel Lim5 years ago11See the [OpenAI API docs](https://beta.openai.com/docs/api-reference?lang=python).
3c6d4cd6Greg Brockman5 years ago12
13## Installation
14
15You don't need this source code unless you want to modify the package. If you just
16want to use the package, just run:
17
18```sh
19pip install --upgrade openai
20```
21
22Install from source with:
23
24```sh
25python setup.py install
26```
27
d53d9efbRachel Lim5 years ago28## Usage
29
30The library needs to be configured with your account's secret key which is available on the [website](https://beta.openai.com/account/api-keys). Either set it as the `OPENAI_API_KEY` environment variable before using the library:
31
32```bash
33export OPENAI_API_KEY='sk-...'
34```
35
36Or set `openai.api_key` to its value:
37
38```python
39import openai
40openai.api_key = "sk-..."
41
42# list engines
43engines = openai.Engine.list()
44
45# print the first engine's id
46print(engines.data[0].id)
47
48# create a completion
49completion = openai.Completion.create(engine="ada", prompt="Hello world")
50
51# print the completion
52print(completion.choices[0].text)
53```
54
3edecbeehallacy3 years ago55
56### Params
57All 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: https://requests.readthedocs.io/en/latest/user/quickstart/#timeouts).
58
f288b001Sorin Suciu4 years ago59### Microsoft Azure Endpoints
60
7884a7b9Ted Sanders3 years ago61In 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.
f288b001Sorin Suciu4 years ago62In addition, the deployment name must be passed as the engine parameter.
63
64```python
65import openai
66openai.api_type = "azure"
67openai.api_key = "..."
68openai.api_base = "https://example-endpoint.openai.azure.com"
69openai.api_version = "2021-11-01-preview"
70
71# create a completion
53e5ba4bt-asutedjo4 years ago72completion = openai.Completion.create(engine="deployment-name", prompt="Hello world")
f288b001Sorin Suciu4 years ago73
74# print the completion
75print(completion.choices[0].text)
76
77# create a search and pass the deployment-name as the engine Id.
53e5ba4bt-asutedjo4 years ago78search = openai.Engine(id="deployment-name").search(documents=["White House", "hospital", "school"], query ="the president")
f288b001Sorin Suciu4 years ago79
80# print the search
81print(search)
82```
62b51ca0Boris Dayma4 years ago83
02e4008dSorin Suciu4 years ago84Please note that for the moment, the Microsoft Azure endpoints can only be used for completion, search and fine-tuning operations.
7884a7b9Ted Sanders3 years ago85For a detailed example on how to use fine-tuning and other operations using Azure endpoints, please check out the following Jupyter notebooks:
86* [Using Azure fine-tuning](https://github.com/openai/openai-cookbook/tree/main/examples/azure/finetuning.ipynb)
87* [Using Azure embeddings](https://github.com/openai/openai-cookbook/blob/main/examples/azure/embeddings.ipynb)
f288b001Sorin Suciu4 years ago88
53e5ba4bt-asutedjo4 years ago89### Microsoft Azure Active Directory Authentication
90
91In 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.
92
93
94```python
95from azure.identity import DefaultAzureCredential
96import openai
97
98# Request credential
99default_credential = DefaultAzureCredential()
100token = default_credential.get_token("https://cognitiveservices.azure.com")
101
102# Setup parameters
103openai.api_type = "azure_ad"
104openai.api_key = token.token
105openai.api_base = "https://example-endpoint.openai.azure.com/"
106openai.api_version = "2022-03-01-preview"
107
108# ...
109```
d53d9efbRachel Lim5 years ago110### Command-line interface
111
112This library additionally provides an `openai` command-line utility
113which makes it easy to interact with the API from your terminal. Run
114`openai api -h` for usage.
115
0e21703eTed Sanders4 years ago116```sh
d53d9efbRachel Lim5 years ago117# list engines
118openai api engines.list
119
120# create a completion
121openai api completions.create -e ada -p "Hello world"
122```
123
0e21703eTed Sanders4 years ago124## Example code
125
7884a7b9Ted Sanders3 years ago126Examples of how to use this Python library to accomplish various tasks can be found in the [OpenAI Cookbook](https://github.com/openai/openai-cookbook/). It contains code examples for:
127
128* Classification using fine-tuning
129* Clustering
130* Code search
131* Customizing embeddings
132* Question answering from a corpus of documents
133* Recommendations
134* Visualization of embeddings
135* And more
136
137Prior 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](https://github.com/openai/openai-cookbook/).
0e21703eTed Sanders4 years ago138
139### Embeddings
140
141In 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.
142
143To get an embedding for a text string, you can use the embeddings method as follows in Python:
144
145```python
146import openai
147openai.api_key = "sk-..." # supply your API key however you choose
148
149# choose text to embed
150text_string = "sample text"
151
152# choose an embedding
f4be8f2fhallacy4 years ago153model_id = "text-similarity-davinci-001"
0e21703eTed Sanders4 years ago154
155# compute the embedding of the text
f4be8f2fhallacy4 years ago156embedding = openai.Embedding.create(input=text_string, engine=model_id)['data'][0]['embedding']
0e21703eTed Sanders4 years ago157```
158
7884a7b9Ted Sanders3 years ago159An example of how to call the embeddings method is shown in this [get embeddings notebook](https://github.com/openai/openai-cookbook/blob/main/examples/Get_embeddings.ipynb).
0e21703eTed Sanders4 years ago160
161Examples of how to use embeddings are shared in the following Jupyter notebooks:
162
7884a7b9Ted Sanders3 years ago163- [Classification using embeddings](https://github.com/openai/openai-cookbook/blob/main/examples/Classification_using_embeddings.ipynb)
164- [Clustering using embeddings](https://github.com/openai/openai-cookbook/blob/main/examples/Clustering.ipynb)
165- [Code search using embeddings](https://github.com/openai/openai-cookbook/blob/main/examples/Code_search.ipynb)
166- [Semantic text search using embeddings](https://github.com/openai/openai-cookbook/blob/main/examples/Semantic_text_search_using_embeddings.ipynb)
167- [User and product embeddings](https://github.com/openai/openai-cookbook/blob/main/examples/User_and_product_embeddings.ipynb)
168- [Zero-shot classification using embeddings](https://github.com/openai/openai-cookbook/blob/main/examples/Zero-shot_classification_with_embeddings.ipynb)
169- [Recommendation using embeddings](https://github.com/openai/openai-cookbook/blob/main/examples/Recommendation_using_embeddings.ipynb)
0e21703eTed Sanders4 years ago170
171For more information on embeddings and the types of embeddings OpenAI offers, read the [embeddings guide](https://beta.openai.com/docs/guides/embeddings) in the OpenAI documentation.
172
173### Fine tuning
174
175Fine 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).
176
177Examples of fine tuning are shared in the following Jupyter notebooks:
178
7884a7b9Ted Sanders3 years ago179- [Classification with fine tuning](https://github.com/openai/openai-cookbook/blob/main/examples/Fine-tuned_classification.ipynb) (a simple notebook that shows the steps required for fine tuning)
0e21703eTed Sanders4 years ago180- Fine tuning a model that answers questions about the 2020 Olympics
7884a7b9Ted Sanders3 years ago181- [Step 1: Collecting data](https://github.com/openai/openai-cookbook/blob/main/examples/fine-tuned_qa/olympics-1-collect-data.ipynb)
182- [Step 2: Creating a synthetic Q&A dataset](https://github.com/openai/openai-cookbook/blob/main/examples/fine-tuned_qa/olympics-2-create-qa.ipynb)
183- [Step 3: Train a fine-tuning model specialized for Q&A](https://github.com/openai/openai-cookbook/blob/main/examples/fine-tuned_qa/olympics-3-train-qa.ipynb)
0e21703eTed Sanders4 years ago184
62b51ca0Boris Dayma4 years ago185Sync your fine-tunes to [Weights & Biases](https://wandb.me/openai-docs) to track experiments, models, and datasets in your central dashboard with:
186
187```bash
188openai wandb sync
189```
190
0e21703eTed Sanders4 years ago191For more information on fine tuning, read the [fine-tuning guide](https://beta.openai.com/docs/guides/fine-tuning) in the OpenAI documentation.
192
3c6d4cd6Greg Brockman5 years ago193## Requirements
194
62f8d40fMadeleine Thompson4 years ago195- Python 3.7.1+
3c6d4cd6Greg Brockman5 years ago196
197In general we want to support the versions of Python that our
198customers are using, so if you run into issues with any version
199issues, please let us know at support@openai.com.
200
201## Credit
202
203This library is forked from the [Stripe Python Library](https://github.com/stripe/stripe-python).