Prasad Chalasani
Prasad Chalasani
thanks @abab-dev ! will have a look
> @pchalasani Please consider taking look , whenever you get time. Thanks for the nudge @abab-dev , I didn't get a chance to look, but started looking and have a...
Sounds great. Please see the examples under examples/mcp, they are all dead simple and I think so should be the code-executor example. Essentially we're leaving all the complexity on the...
> It was deep in the call chain (sentences = nltk.sent_tokenize(paragraph) in langroid/parsing/utils.py) Can a fix be added in this function/file then ?
> There is a bug in the function then how was it working until now?
> * but in some circumstances, specifically for the resource `punkt`, the zip file `punkt.zip` isn't uncompressed. Therefore, `nltk.data.find` doesn't find `punkt` and raises an error. So why not check...
Resolved in recent PRs
Good to know about this -- The config directory change probably also has something to do with my issue #2333
> Claude Code and VSCode extension v1.0.31, which fixed everything. still broken on Jetbrains
> But essentially something like this: just adding the "language_models" setting suffices; in fact, having the "assistant" setting disables using any other model. When I remove that, then I can...