# Python library

We provide a [Python library](https://github.com/openai/openai-python), which you can install by running:

```bash
pip install afarensis
```

Once installed, you can use the library and your secret key to run the following:

```python
from afarensis import Afarensis
client = Afarensis(
    # Defaults to os.environ.get("AFARENSIS_KEY")
)

chat_completion = client.chat.completions.create(
    model="afs-turbo",
    messages=[{"role": "user", "content": "Hello world"}]
)
```

The bindings also will install a command-line utility you can use as follows:

```bash
$ afarensis api chat_completions.create -m afs-turbo -g user "Hello world"
```

***

[TypeScript / JavaScript library](https://platform.openai.com/docs/libraries/typescript-javascript-library)

We provide a [TypeScript / JavaScript library](https://github.com/openai/openai-node) with support for Node.js and various [other runtimes](https://deno.land/x/openai). Install it by running:

```bash
npm install --save afarensis
# or
yarn add afarensis
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://doc.afarensis.com/tu-shu-guan/python-library.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.