Christopher Brooks

I'm happy to add debug info or the like fwiw, just need a couple of pointers to docs/repos where this might have been done to better understand how to debug...

Just a note that the `ChatBedrock.with_structure_output()` hard codes everything to claude, unless I'm reading this wrong: https://github.com/langchain-ai/langchain-aws/blob/feb8f09134e383827f343ef81534679b691f0406/libs/aws/langchain_aws/chat_models/bedrock.py#L789 Maybe that's a red herring on the tools use, but that's what I...

Hi @ccurme , > Hi @rsgrewal-aws, > > For (1), could you confirm you're using `meta.llama3-1-70b-instruct-v1:0`? This snippet returns tool calls for me (using langchain-aws==0.1.17): ~~Does Bedrock support llama 3.1?...

Just an update that I can confirm that using bedrock `ChatBedrockConverse` does seem to work, while `ChatBedrock` does not. Here's my MWE's with output: 

Yes, I'm building a wrapper for nbclient to make available some of the notebook functions to an LLM agent. More specifically, I'm making a few high level functions like `execute_cell()`...

That code likely won't run nicely fwiw, it's sort of ripped out of the stuff I'm building now, and it's possible that code does actually run and initialization of a...

Here is a better MWE: ``` from nbclient import NotebookClient import nbformat notebook = nbformat.reads(open('test.ipynb','r').read(), as_version=4) client = NotebookClient(notebook, kernel_name="python3") for index, cell in enumerate(notebook.cells): result = client.execute_cell(cell, index) ```...

Odd to me is that I can actually execute the whole notebook it appears, so maybe I am misusing the cell execution api? This code seems to work (and at...

Just an update for those who might be running into a similar problem or are trying to use the nbclient package in a similar way, this is how I create...

I'm not @3coins but I'm happy to share my frustrations @Forma-Lin . For instance, I use llama models on bedrock, but right now the `langchain_aws` module doesn't include support for...