The deepset SDK is an open source software development kit that provides convenient access to and integration with deepset AI Platform, a powerful cloud offering for various AI tasks. This README provides an overview of the SDK and its features, and information on contributing to the project and exploring related resources.
In its current shape, the SDK offers a suite of tools for seamless data upload to deepset AI Platform and for importing Haystack pipelines and indexes. The following examples demonstrate how to use the deepset SDK to interact with deepset AI Platform using Python. You can use the deepset SDK in the command line as well. For more information, see the CLI documentation.
The deepset SDK is available on PyPI and you can install it using pip:
pip install deepset-cloud-sdkAfter installing the deepset SDK, you can use it to interact with deepset AI Platform. It comes with a command line interface (CLI), that you can use by calling:
deepset-cloud --help
To install the deepset SDK for development, clone the repository and install the package in editable mode:
pip install hatch==1.7.0
hatch buildInstead of calling the CLI from the build package, you can call it directly from the source code:
python3 -m deepset_cloud_sdk.cli --helpWe welcome contributions from the open source community to enhance the deepset SDK. If you would like to contribute, have a look at CONTRIBUTING.md for guidelines and instructions on how to get started. We appreciate your contributions, whether they're bug fixes, new features, or documentation improvements.
deepset AI Platform is powered by Haystack, an open source framework for building end-to-end NLP pipelines.
The SDK is licensed under Apache 2.0, you can see the license here
We use several libraries in this SDK that are licensed under the MPL 2.0 license