Allow KeyBERT to pass `batch_size` to `llm.encode()` method

[adhadseKavida]

I'm using SentenceTransformer with KeyBERT. the SentenceTransformer.encode() (is called by self.model.encode()) allows to change batch_size parameter. But this parameter is not modifiable through the KeyBERT.extract_sentences().

I would recommend if we can pass on **kwargs to the function to update this. Changing batch size hugely decreases the inference time by maximum utilization of GPU memory.

I know we can send the doc and word embeddings ourselves, but that doesn't seem intuitive.

I'm open to discussion regarding possible alternatives.

[MaartenGr]

Thanks for sharing this! I would prefer the use of **kwargs as much as possible for two reasons. First, it is less explicit and clear to users what it exactly means. Second, it would be a **kwargs for the sole purpose of a specific backend, which seems a rather big change for a small feature.

Instead, I think opening up SentenceTransformerBackend might fit a bit better here since your suggestion relates to sentence-transformers only. Here, we could simply create another variable, encode_kwargs, that takes in you suggested changes.

[adhadseKavida]

That seems a much better suggestion!

[MaartenGr]

Thanks! Unfortunately, I do not have much time these days to work on this, so it might take a couple of weeks at least. If you, or someone else, wants to work on this then that would be appreciated!

[adhadseKavida]

I'll look into it and submit a PR as soon as possible.

[adhadse]

Opened up a PR for review!