Mark Ericksen

Hi @jeroenbourgois! Interesting. It should not cause an error, but the two aren't intended to be used together. If you are working with a model that supports tool calls, you...

If you can provide some additional details or example errors, I think it's worth trying to make the dev experience clearer and smoother. Thanks!

@jeroenbourgois, > But elaborating on your initial response, you say that if you are working with a model that support tool calls, you don't _need_ a JSON processor? I am...

@jeroenbourgois, Thanks for the example! > I have put a simple example on Github: https://github.com/jeroenbourgois/langchain_json_preprocessor/blob/main/lib/langchain_json_processor.ex > So running the module will give an error: > > ``` > ** (CaseClauseError)...

@jeroenbourgois, Thanks for taking the time to bring me up to speed with what you're doing. I get your point. It is valid for the LLM to execute a function...

Watching your PR, I saw your selection and use of Mimic. I researched it and was happy enough with it that I moved to it generally. That's here in PR...

Hi @stevehodgkiss! Where does this stand currently? Do you feel it's ready?

Your code looks clean, clear and thoughtful. ❤️💛💙💜

Hi @manukall! Please check out the v0.4.0-rc.0 release. There are other breaking changes that I expect are needed for DeepSeek to be supported, but your TokenUsage update would be best...

Well darn. Stupidly, the two Google LLMs have different APIs. The hope was we could add both versions and let the API use the one it cared about. I'm not...