MiniChain
MiniChain copied to clipboard
srush
A tiny library for coding with large language models.
I got below error when running math_demo.ipynb, do you know what is wrong here ? TypeError Traceback (most recent call last) Cell In[6], line 1 ----> 1 gradio = show(math_demo,...
Hello, I like your library but i can't understand how to use a different model than OpenAI's one. I'm interested in particular in using HF models.
Hi @srush Following on from this issue -https://github.com/srush/MiniChain/issues/22. I'm working on litellm (simple library to standardize LLM API Calls - https://github.com/BerriAI/litellm) and was wondering if we could be helpful. I...
gradio is a fairly heavyweight dependency and may not be necessary in production deployments. currently, `import minichain` requires gradio to be installed via https://github.com/srush/MiniChain/blob/b79ebc51bdedb836c9265eec2fcc21cd60b17327/minichain/__init__.py#L16 and https://github.com/srush/MiniChain/blob/b79ebc51bdedb836c9265eec2fcc21cd60b17327/minichain/gradio.py#L6 would it be possible...
looking at the pypi (https://pypi.org/project/minichain/), it appears as though 0.3.3 is the latest version, however the latest tag/release on GitHub is 0.2. would it be possible to get a git...
Hey @srush, saw that you're using manifest for making OpenAI/LLM calls vs. calling it yourself - why is that? https://github.com/srush/MiniChain/blob/b79ebc51bdedb836c9265eec2fcc21cd60b17327/minichain/backend.py#L206 context: I'm working on [LiteLLM](https://github.com/BerriAI/litellm) an abstraction library to simplify...
Something like dask to run graphs in parallel, where safe? This maybe deserves a separate issue, but what about integrating with a prompt templating language like lmql or guidance
Hi great looking library. Love the simplicity! I'm playing with things and exploring the examples but I'm sort of curious how I could print out my rendered template prior to...
