Arize-ai / openinference

OpenTelemetry Instrumentation for AI Observability
https://arize-ai.github.io/openinference/
Apache License 2.0
201 stars 34 forks source link

[bedrock] CI publish workflow #139

Closed mikeldking closed 8 months ago

mikeldking commented 8 months ago
dosubot[bot] commented 8 months ago

🤖

Hey there, @mikeldking! It's great to see you again, hope everything's been going well. I'm diving into your issue right now and will be back shortly with a comprehensive response. Hang tight!

dosubot[bot] commented 8 months ago

🤖

To set up the CI publish workflow, you can follow the process outlined in the .github/workflows/typescript-publish.yaml file in the OpenInference repository. This workflow is triggered on a push to the main branch and includes steps for setting up Node.js, setting up PNPM, installing dependencies, and creating and publishing new versions.

To trigger the "release please publish" action, you simply need to push changes to the main branch. This will initiate the GitHub Actions workflow defined in the .github/workflows/release.yml file, which includes jobs for creating a release and publishing Python and JavaScript distributions.

As for publishing the first version and adding a badge to the root README, you can manually update the README file with the version badge after the first version is published. The badge can be added using the following markdown syntax:

![version](https://img.shields.io/npm/v/@arizeai/openinference?color=blue)

This will display a badge showing the latest version of the OpenInference package on npm. Replace @arizeai/openinference with the actual package name if it's different.

Please note that the current version of the OpenInference codebase is "0.1.2" as defined in the version.py file. You might want to update this version before publishing the first version.

Let me know if you need further assistance. You can find more details about the publishing process in the typescript-publish.yaml and release.yml files in the repository.

Sources


This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.