As TiDB Serverless introduced Vector Search feature that enable users to access vector data via SQL, we are also starting to build the ORM, SDK or libraries for the users to interact with TiDB Serverless and vector data. Such as Python SDK for TiDB Serverless it self, or new column support for traditional ORM like SQLAlchemy, Django ORM, etc.
Here we call for contributions to enhance the ecosystem of TiDB Serverless and vector data. You can contribute to the following areas:
- Python
- TiDB Serverless for testing the SDK or libraries
- Visual Studio Code or any other code editor
This repo pingcap/tidb-vector-python is the Python SDK for TiDB Serverless. You can contribute to this repo by adding new features, fixing bugs, or improving the performance of the SDK.
In this repo, there is a directory examples that contains examples and tutorials for using TiDB Serverless and vector data. You can contribute to this directory by adding new examples or tutorials.
Currently, we are looking for the following types of examples or tutorials:
- Tutorials that enable users to use TiDB Serverless and vector data in different business scenarios, such as suggestion, recommendation system, etc.
- Examples that demonstrate how to use TiDB Serverless and other tools or libraries, such as Dify, Jina AI, Anthropic AI, etc.
- Notebooks that show how to use TiDB Serverless and vector data in different machine learning or deep learning tasks.
Not limited to the above types, you can also contribute other types of examples or tutorials that you think are helpful for the users.
Please feel free to reach out to the maintainers if you have any questions or need help with the project.
If you have any questions or suggestions, please feel free to open a discussion in the Discussions
or contact us via @TiDB_Developer on Twitter.