ccurme
ccurme
Thanks! Feel free to update the draft status of this when ready for review.
> my guess is there's a bunch of find and replace in docs and cookbooks too thanks, changed docs here: https://github.com/langchain-ai/langchain/pull/20698
Tests pass aside from Mistral, which is broken due to another issue: https://github.com/langchain-ai/langchain/issues/20618 https://github.com/langchain-ai/langchain/actions/runs/8754704419
Hi @ReinforcedKnowledge, thanks for this. I'm finding that after this change we still get an error for the `"hello world" * 4095` case described in the [issue](https://github.com/langchain-ai/langchain/issues/20523), although it is...
sample trace: https://smith.langchain.com/public/65efe722-b970-4330-acd0-6a6b1a4cabe2/r
sample trace: https://smith.langchain.com/public/4eff5c8b-bd26-42c4-8564-c3a6ceb67c78/r
I looked into a couple ways of doing this. Let me know if you had a preferred method in mind. One is to add a dependency [nbmake](https://github.com/treebeardtech/nbmake), which is a...
It doesn't look like many. My thought is to just to use `nbmake` and opt-in to including notebooks in the test. So we'd need to maintain a separate list of...
We can enumerate directories, we can also go the other way and maintain a list of notebooks we *don't* test.