aleph-alpha-client

python client to interact with Aleph Alpha api endpoints


License
MIT
Install
pip install aleph-alpha-client==3.1.3

Documentation

Aleph Alpha Client

License PyPI version Documentation Status

Python client for the Aleph Alpha API.

Usage

Synchronous Client

import os
from aleph_alpha_client import Client, CompletionRequest, Prompt

client = Client(
    token=os.environ["TEST_TOKEN"],
    host=os.environ["TEST_API_URL"],
)
request = CompletionRequest(
    prompt=Prompt.from_text("Provide a short description of AI:"),
    maximum_tokens=64,
)
response = client.complete(request, model="pharia-1-llm-7b-control")

print(response.completions[0].completion)

Asynchronous Client

import os
from aleph_alpha_client import AsyncClient, CompletionRequest, Prompt

# Can enter context manager within an async function
async with AsyncClient(
    token=os.environ["TEST_TOKEN"],
    host=os.environ["TEST_API_URL"],
) as client:
    request = CompletionRequest(
        prompt=Prompt.from_text("Provide a short description of AI:"),
        maximum_tokens=64,
    )
    response = client.complete_with_streaming(request, model="pharia-1-llm-7b-control")

    async for stream_item in response:
        print(stream_item)

Interactive Examples

This table contains interactive code examples, further exercises can be found in the examples repository.

Template Description Internal Link Colab Link
1 Calling the API Template 1 Open In Colab
2 Simple completion Template 2 Open In Colab
3 Simple search Template 3 Open In Colab
4 Symmetric and Asymmetric Search Template 4 Open In Colab
5 Hidden Embeddings Template 5 Open In Colab
6 Task-specific Endpoints Template 6 Open In Colab

Installation

The latest stable version is deployed to PyPi so you can install this package via pip.

pip install aleph-alpha-client

Get started using the client by first creating an account. Afterwards head over to your profile to create an API token. Read more about how you can manage your API tokens here.

Development

For local development, start by creating a Python virtual environment as follows:

python3 -m venv venv
. ./venv/bin/activate

Next, install the test and dev dependencies:

poetry install --extras "dev"

Now you should be able to ...

  • run all the tests using pytest or, pytest -k <test_name> to run a specific test
  • typecheck the code and tests using mypy aleph_alpha_client resp. mypy tests
  • format the code using ruff

Links