Alejandro Companioni

Fixing postprocess() interface in README template.

1

## :rocket: What This PR corrects a small interface definition in the README template. Instead of referencing `postprocess(request)` we now reference `postprocess(response)` in alignment with eg `truss.model_wrapper` ([see code](https://github.com/basetenlabs/truss/blob/6570f7059adc7c33d0d23294d66a4e0fdbdd079d/truss/templates/server/model_wrapper.py#L310-L317)). ##...

Allow users to configure `embed_batch_size` or `ThreadPoolExecutor` size when calling `Client.embed`

1

It looks like batching was added in #437 - thank you for implementing this, it's very helpful. I notice that batching, as defined [here](https://github.com/cohere-ai/cohere-python/blob/main/src/cohere/client.py#L135), depends on a [fixed batch size](https://github.com/cohere-ai/cohere-python/blob/main/src/cohere/config.py#L1)....

[Enhancement] - Supporting LLM routing by integrating Not Diamond.

2

### Reference Issues None yet. ### Summary Hi there! I am a big fan of kotaemon and would love to integrate Not Diamond into it. In case you’re unfamiliar with...

community: `NotDiamondRoutedRunnable` for langchain.

2

## Description Per https://github.com/langchain-ai/langchain/pull/25319 we have reimplementd our langchain integration using a `Runnable[LanguageModelInput, str]`. The output of this new `NotDiamondRunnable` can then be chained with an input set of prompts,...

chore: clear notebook outputs for Not Diamond example notebook

2

## Description Somehow I forgot to clear these notebook outputs. This PR corrects that! ## Testing No need to test, just clearing outputs.

This file is quite interesting. Happy to land as is, but in the near future (a few weeks), we will have a more "direct" eval API that allows users to...