Markus Ecker

You are welcome! This feature did exist in a previous version, but I was not sure if it was needed so it got removed... One thing you can do to...

Hi, The algorithm for image classification works best if you have roughly the same amount of images per category. 50 images are not ideal, but should be ok. Try deleting...

Can you check the value of `os.environ['http_proxy']` and make sure it is correct? For example, via curl: https://stackoverflow.com/questions/9445489/performing-http-requests-with-curl-using-proxy

@tbruyelle thanks, I'll wait

@TimeLordRaps that's awesome, thanks for figuring this out! Would you mind contributing this to our documentation?

This would make a great first issue: Add the code to the langchain docs to explain how to use other LLMs.

@ramiborni we recently added support for LangServe which can connect to your Python chains: https://docs.copilotkit.ai/reference/CopilotBackend#langserve Would this work for your use case?

Hi Benoit, I'm considering removing this as it can easily be done by the user of the library and might be confusing/unexpected. The idea was to make it easy to...

In `{headers, Result, Parser}` the `Result` value can be transformed by a map operation. Or do you mean getting the header tuples out and avoid building the list ?

Hey @gusye1234, we have added more documentation. You can read about the Chatbot UI here: https://docs.copilotkit.ai/reference/CopilotKitPopup Or here for the sidebar: https://docs.copilotkit.ai/reference/CopilotKitSidebar Let me know if this helps 👍