Paul-Louis Pröve

i think i have a similar problem with my SvelteKit application. I managed to run everything nicely when using the build directory. However, in dev mode I'm getting 304s on...

The cleanest API from a user perspective would be that if a "sub model" is not a direct instance of `BaseModel` but `marvin.Model` instead, the calls would be split into...

@zzstoatzz What are some ways of helping Marvin development at the moment? I'm using this library a lot and I would like to contribute instead of asking for features all...

Sorry I didn't mention that. I haven't looked into the prompt template of cast but the results were pretty bad for purposes outside the core idea of cast. Generating, summarizing,...

@HamzaFarhan completely agree with this! It would be great to define it at runtime and also offer async. I like the decorator syntax for the ai function. It's such a...

Personally, I'm not looking for a chat interface. Maybe I misunderstood you. This is my workaround for now: ```python from marvin.ai.text import _generate_typed_llm_response_with_tool from marvin.ai.prompts.text_prompts import FUNCTION_PROMPT async def ai_function(...

Oh boy, that would be so nice!

Please also consider integrating `AzureOpenAI `with this. The OpenAI SDK 1.x changed the way that Azure is integrated. Did someone manage to get Azure OpenAI running at the moment? Even...

I'm doing this and it works perfectly (except for click outside to close). Might be worth sharing it in the docs: ```html ... Open Modal ```

@Atmos4 That's true and I don't _really_ care if it's added to the docs or not. However, given Picos philosophy and design principles, I think that my provided solution is...