mihirchdev
mihirchdev
Bumping down the version of uvicorn is fine, which should take care of the dependency conflict. I think having liteLLM could vert useful long term to add support for cloud...
One thing we can do to reduce bloated dependencies in the future is use python package extras. We could support devon_agent[litellm], however for now we want to add support for...
https://github.com/BerriAI/liteLLM-proxy LiteLLM proxy seems to be deprecated
So i got ollama to work with litellm without the proxy. All I had to do was set completion (in LiteLLM) to this. ``` model_completion = completion( messages=[{"role": "system", "content":...
@antoninoLorenzo hopefully that helps
Yeah, the agent does try to open files that don't exist which is fine (it generally recovers from its mistake). However, it should not hang. Thanks for bringing it up,...
What OS are you using?
Really excited to see how well Gemini 1.5 does specially with its insane context window. I wonder if it is able to reason through all of its context window
That's a actually really cool way to persist workflows!Adding persistence is definitely on the roadmap. Rate limit is strange as I added exponential backoff. I'll increase backoff period so those...
working on making a basic set of regression tests. Will merge once we have those. #40