Thank you creators for contributing to Visual Blocks for ML! We firmly believe that: with your contribution, we can inspire more hackers, designers, and practitioners unleash their creativity!
First, fork this repository and clone the forked repo to your laptop or workstation. Review and sign the Contributor License Agreement (CLA). Now you are ready to create a pull request!
Second, visit https://visualblocks.withgoogle.com/, click the Demo button.
Next, click the Demo: Create Your Own tab and start dragging and dropping
nodes from the node gallery and make your own pipelines. After you complete,
come up with a descriptive title, and click the Export button on the top right
corner to download. You may also click the Import button to load an existing
pipeline.
Finally, copy the downloaded your pipeline to your local repository, commit and create a pull request by following the official GitHub guide. Make sure to add your pipeline to the corresponding subfolder within the pipeline folder (i.e. audio, vision, multi-modal, etc.). We strongly recommend contributors to also upload a GIF or JPG screenshot for your pipeline (width: 320px) to be featured in this guide.
After you have uploaded your pipeline to the pipelines folder, you can easily
share your amazing creation via URL like:
https://visualblocks.withgoogle.com/#/edit/_?project_json=https:%2F%2Fraw.githubusercontent.com%2Fgoogle%2Fvisualblocks%2Fmain%2Fpipelines%2Fgraphics%2F3dphoto_portrait_depth.json
Please refer to graphics%2F3dphoto_portrait_depth.json and palm2_weather_summarizer.json
for two example pipelines. Note that API keys and locally uploaded images are
not exported for privacy and security.
Before you get started on the PaLM example, you need to get an API key first. Head to makersuite.google.com, sign up with your Google account, and click "Get an API key". Once you have the key, you can start using the API.
We highlight a set of community-contributed pipelines of Visual Blocks below:
-
Weather Summarizer with PaLM API
-
LaTeX Manuscript Helper with PaLM API
-
Werewolf Game with PaLM API
-
Review Generation and Rating with GPT3.5
-
Email tones explorer with PaLM API
-
Email genereation review with PaLM API
This project follows Google's Open Source Community Guidelines.