Stoyan

hi @iuiu34 thanks for bringing this up. I also had some feedback that loading API keys by default can create some issues like using the wrong API key. Another concern...

Thank you for submitting a feature request @jonnyjohnson1 ! What do you think the expected behaviour should be in cases where there are multiple final steps?

Hey @jonnyjohnson1 thank you so much for sharing these! I will have some time to look into this over the weekend. I am currently working on a large update and...

Hey @jonnyjohnson1 I spent some time looking into this. I think a good solution would be to create a new `.run_stream()` method for flows in addition to the current `.run()`...

you can try the demo here: https://llmflows-ws-template-96085e33adde.herokuapp.com/

It's on my todo list. I am working on a few updates that I will release in the coming weekends and I will look into this afterwards

yes I used a scrappy script to crawl the wikipedia pages: ```python # pylint: skip-file from mediawiki import MediaWiki import nltk from nltk.tokenize import sent_tokenize import os from llmflows.llms import...

I am trying to avoid defining these until I start adding LLMs from other providers. Any idea on how we can make this generic enough beforehand?

Reevaluating this since I added support for another LLM and the need for this becomes more obvious. My worry is that dataclasses are not serializable by default

This would be awesome! Thank you! 🤞