FLAML VS ML.NET

I really like the simplicity of this framework, and they hit on a lot of common problems found in other agent-based frameworks. Most intrigued by the RAG improvements.

Seems like Microsoft was frustrated with the pace of movement in this space and the shitty results of agents (which admittedly kept my interest turned away from agents for the last few months). I'm interested again because it makes practical sense, and from looking at the example notebooks, seems fairly easy to integrate into existing applications.

Maybe this is the 'low code' approach that might actually work, and bridge together engineering and non-engineering resources.

This example was what caught my eye: https://github.com/microsoft/FLAML/blob/main/notebook/autoge...

4. FLAML

Improved AutoML - Again, with collaboration from Microsoft Research, we used FLAML to update our existing AutoML solutions. What does this mean for you? You're using the latest techniques but all you need is a problem to solve and some data to get started.

For a complete tutorial, navigate to this Jupyter Notebook: https://github.com/microsoft/FLAML/blob/main/notebook/flaml_automl.ipynb

Microsoft Researchers have developed FLAML (Fast Lightweight AutoML) which can now utilize Ray Tune for distributed hyperparameter tuning to scale up FLAML’s resource-efficient & seamlessly parallelizable algorithms across a cluster.

Looks nice but I wonder if this is practical for non-tiny problems. The papers are a bit hard to follow but it looks like training is restarted with every new architecture choice. As for the library itself, the only large neural net example is a finetune of an NLP model that only searches over ADAM's optimizer params - which could be useful but it's a stretch to call that AutoML.

You can direct your question to https://github.com/dotnet/machinelearning/issues. Perhaps it is already documented.

Here I'm analyzing all projects in the src and test directories of the ML.NET repository. I chose to include these as separate paths because they represent two different groupings of projects in this repository.

Important Note: looping over repository commits takes a long time for large repositories. It took 52 minutes to analyze the ML.NET repository this code example refers to, which had 2,681 commits at the time of analysis on February 25th, 2023.

We checked the ML.NET 1.7.1 version. The source code of this project's version is available on GitHub.

machine learning? https://github.com/dotnet/machinelearning

You can follow some of our plans by taking a look at our roadmap which we'll be updating shortly to more accurately reflect the areas we're investing in.

Re: ONNX, if you run into similar issues in the future, feel free to reach out in our GitHub repo or the ONNX Runtime repo and we'd be happy to help!

Good clarification, I think using something like ML.NET could be cool but I have some experience with Blazor that might be fun to use as well, I think generally performance monitoring or optimizing systems seems interesting to me, and I'm really open to other ideas as well. Let me know if any of that helps narrow my question down!