Pass kwargs to encoder

Nobody has claimed this yet.

### Feature request

Models like https://huggingface.co/BAAI/bge-m3 and https://huggingface.co/jinaai/jina-embeddings-v3 can take extras kwargs as input of the `encode` function such as `task=...` for Jina v3 or `return_dense=False/True` for bge-m3

It would be great if we could pass these kwargs either when using the async engine via the Python API
`engine.embed(sentences=[...], additional_args=**kwargs)`

or when we are sending requests to an endpoint create using your docker image

`r = requests.post("http://0.0.0.0:7997/embeddings", json={"model":"test_model","input":["Two cute cats."], "task": "text-matching"})`

### Motivation

This would could also be used to handle `truncate_dim` for Matryoshka embeddings.

might be linked to: #476

### Your contribution

I could try to implement it on my free time but I do not have much currently plus I'm still navigating the code. Any pointers at where to start are welcome.

Start by tracing the Python API entry point for engine.embed and the /embeddings request handler in the Docker-served endpoint through to the model's encode call. Confirm how request parameters are currently parsed and forwarded, then verify that kwargs such as task, return_dense, and truncate_dim reach both paths without changing existing behavior.

Written by the indexing model from the issue text.