multer VS onnxruntime

Some basic examples of popular packages in the Javascript community include Express (a framework for building server applications) and Multer (a middleware for handling file uploads). These packages, when integrated into your project, can significantly streamline your development process.

Here are the docs for multer

You could use multipart/form-data https://github.com/expressjs/multer

multer - Middleware for Express.js to handle file uploads

busboy is what many Express middleware's such as multer use under the hood.

Maybe multer or validate-image-type?

🔀 Repositório no GitHub

Multer has some functions used to determine what type of file(s) to expect from the API request. Here we have used the 'multer.single("file")' function to let multer know that we're expecting a single file. (The full multer documentation can be found here).

You need something that can parse formData stuff. Like multer https://github.com/expressjs/multer

ONNX Runtime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Embedding generation uses the ONNX runtime under the hood. This is a cross-platform inferencing library that supports multiple execution providers from CPU to specialized GPUs.

tfjs is dead, looking at the commit history. The standard now is to convert PyTorch to onnx, then use onnxruntime (https://github.com/microsoft/onnxruntime/tree/main/js/web) to run the model on the browsdr.

- slang[2] has the potential, but the meta programming part is not as strong as C++, existing libraries cannot be used.

The above conclusion is drawn from my work https://github.com/microsoft/onnxruntime/tree/dev/opencl, purely nightmare to work with thoes drivers and jit compilers. Hopefully Vcc can take compute shader more seriously.

[1]: https://www.circle-lang.org/

I did. It depends what you want, for an overview of how ONNX Runtime works then Microsoft have a bunch of things on https://onnxruntime.ai, but the Java content is a bit lacking on there as I've not had time to write much. Eventually I'll probably write something similar to the C# SD tutorial they have on there but for the Java API.

For writing ONNX models from Java we added an ONNX export system to Tribuo in 2022 which can be used by anything on the JVM to export ONNX models in an easier way than writing a protobuf directly. Tribuo doesn't have full coverage of the ONNX spec, but we're happy to accept PRs to expand it, otherwise it'll fill out as we need it.

What about models besides GPT? Most of the popular vector encoding models aren't using this architecture.

If you really didn't want PyTorch/Transformers, you could consider exporting your models to ONNX (https://github.com/microsoft/onnxruntime).