Ben Heckmann comments

Results 18 comments of


                                            Ben Heckmann

LLMMathChain to allow ChatOpenAI as an llm

@cnndabbler Are you currently working on this? Otherwise, I would take on this issue. Apart from changing the typing of `LLMMathChain.llm` to allow for a `BaseChatModel`, I would also suggest...

Extend token count to Embeddings and (non-streaming) BaseChatModel (#945)

First of all, thank you so much for taking a look and for your feedback! Regarding 1. & 2.: Do you mean something like this would be the ideal solution:...

Extend token count to Embeddings and (non-streaming) BaseChatModel (#945)

Thank you both! I do want to pursue this further! I will have a look at #1930 and incorporate your suggestions. :)

Extend token count to Embeddings and (non-streaming) BaseChatModel (#945)

Hi and sorry for the delay! I have implemented the wrapper for the `Embeddings` (base) class. None of the new methods are abstract so there should be no breaking changes....

Extend token count to Embeddings and (non-streaming) BaseChatModel (#945)

Would be great if either of you could take a look @hwchase17 or @agola11.

Extend token count to Embeddings and (non-streaming) BaseChatModel (#945)

Closing this now.

Total token count of openai callback does not count embedding usage

I will start to work on this as a first issue. Will try to submit a draft in about two weeks. I am following the guidelines and hoping for a...

feat: PreProcessor split by token (tiktoken & Hugging Face)

Oh right, sorry @ZanSara! My test is loading the tokenizer from Hugging Face's model hub. I will mock it.

feat: PreProcessor split by token (tiktoken & Hugging Face)

@ZanSara Fixed the checks.

feat: PreProcessor split by token (tiktoken & Hugging Face)

@ZanSara Would be great if you could take a look :)