vertex-ai-samples VS transformers.js

Google Cloud Platform (GCP) provides a very befitting Machine Learning solution called Vertex Ai that handles Google Cloud's unified platform for building, deploying, and managing machine learning (ML) models. Our goal is to build a simple Machine Learning application that optimizes all that GCP provides plus an implementation of continuous integration and continuous development (CI/CD).

Cross posting some links from another post that HNers found helpful

- https://cloud.google.com/vertex-ai (marketing page)

- https://cloud.google.com/vertex-ai/docs (docs entry point)

- https://console.cloud.google.com/vertex-ai (cloud console)

- https://console.cloud.google.com/vertex-ai/model-garden (all the models)

- https://console.cloud.google.com/vertex-ai/generative (studio / playground)

VertexAI is the umbrella for all of the Google models available through their cloud platform.

For the peer comments

- https://cloud.google.com/vertex-ai (main page)

- https://cloud.google.com/vertex-ai/docs/start/introduction-u... (docs entry point)

- https://console.cloud.google.com/vertex-ai (cloud console)

Starting on December 13, developers and enterprise customers can access Gemini Pro via the Gemini API in Google AI Studio or Google Cloud Vertex AI.

Google Cloud Platform (https://cloud.google.com/vertex-ai): Conversely, Google Cloud Platform (GCP) provides a comprehensive suite of AI and machine learning services, including APIs for vision, language, conversation, and structured data analysis. Whether you're analyzing images, interpreting human speech, or diving deep into data patterns, GCP has something for you.

VertexAI is a machine learning platform available on Google Cloud. It offers a variety of services to train and deploy AI models, including those for Generative AI.

Depending on how much work you want to put into it, you can get started at HuggingFace with their models and datasets, but you'd need compute power, multiple MLOps, etc. I was introduced to the concept in this video, since Google has their Vertex AI tools on Google Cloud, and there's always LangChain but I'm not sure about anything recent.

We have some other WebGPU demos, including:

- WebGPU embedding benchmark: https://huggingface.co/spaces/Xenova/webgpu-embedding-benchm...

- Real-time object detection: https://huggingface.co/spaces/Xenova/webgpu-video-object-det...

- Real-time background removal: https://huggingface.co/spaces/Xenova/webgpu-video-background...

- WebGPU depth estimation: https://huggingface.co/spaces/Xenova/webgpu-depth-anything

- Image background removal: https://huggingface.co/spaces/Xenova/remove-background-webgp...

You can follow the progress for full WebGPU support in the v3 development branch (https://github.com/xenova/transformers.js/pull/545).

To answer your question, while there are certain ops missing, the main limitation at the moment is for models with decoders... which are not very fast (yet) due to inefficient buffer reuse and many redundant copies between CPU and GPU. We're working closely with the ORT team to fix these issues though!

BTW: you might want to add support for typed arrays.

See: https://github.com/xenova/transformers.js/blob/8804c36591d11...

This is really old, but added as part of the shape of the vector as well: https://github.com/nicolaspanel/numjs/blob/master/src/dtypes...

Made possible by Xenova and Supabase / gte-small

To build the application, you’ll use the youtube-transcript package to retrieve YouTube video transcripts. You will then use LangChain and the Transformers.js package to generate free Hugging Face embeddings for the given transcript and store them in a vector store instead of relying on potentially expensive OpenAI embeddings. Lastly, you will use LangChain and an OpenAI model to retrieve information stored in the vector store.

Transformers.js: A groundbreaking library, Transformers.js brings transformer models like GPT-3, BERT, and Whisper straight to your browser. With the introduction of technologies like webGPU and LLM, Transformers.js has garnered significant attention. If you’d like to learn how to integrate a small model in the UI, check out their code and examples here.

The announcement seems somewhat disingenuous. The PR[1] found from their release notes[2] seems to contain only boilerplate and no real support for Mistral models or their weights.

[1]: https://github.com/xenova/transformers.js/pull/379