[Feature Request] Example of using onnxruntime models within .net TPL data pipelines

### Describe the feature request

I have an existing TPL pipeline (https://learn.microsoft.com/en-us/dotnet/api/system.threading.tasks.dataflow.dataflowblockoptions.taskscheduler?view=net-7.0 https://github.com/dotnet/runtime/tree/main/src/libraries/System.Threading.Tasks.Dataflow). I'd like to use CPU-backed ONNX models in its threads.

How can I do it properly?

I guess there should be some custom ThreadPool threads init function that loads the ONNX model?

If the functions are lightweight, then it's critical that every thread has its own loaded ONNX model and loads it only once

### Describe scenario use case

Migrating existing TPL pipeline to using python/ONNX-exported graphs in its components

Start with the linked .NET TPL Dataflow documentation and System.Threading.Tasks.Dataflow source, then compare its TaskScheduler behavior with ONNX Runtime's .NET model-loading and threading APIs. Done would be a documented, working example showing how to use an ONNX-exported model in the pipeline, including the intended model lifetime and per-thread behavior.

Written by the indexing model from the issue text.