Why is langchain still used, thought that not needed, can it just be replaced with some type of custom ETL functions. Or is that still defector ways to interacte with llam?
I have had a quick play around with Deno notebooks. The pain points for me were in image and UI outputs. There is such a large base of support for the Python side, it will take quite a lot of work to catch up. The various python bits seem to be quite dependent on the implementation platform though. Colab, jupyter-lab and integrated into an editor are quite different beasts.<p>Being able to display an entity that carried a MessagePort and a closure for communication would enable a lot there.
after trying the instructions I found the following issues:<p>1- Deepseek-r1 <think></think> tags in the answer break the JSON validation.<p>2- Deno's LSP keeps marking any variable in the cell as not defined even though it is defined in a prior cell, which is annoying.