Alex Reibman

> I made a rewrite (not a fork!) for for llama-fs out of fun, it's aiming to fix some problems I faced trying to toy with llama-fs here. Still useless...

Unfortunate timing for this PR. @bboynton97 is currently splitting llm_tracker.py into multiple files for readability. When that merge goes through, we'll make some changes to make this one work

> > Unfortunate timing for this PR. @bboynton97 is currently splitting llm_tracker.py into multiple files for readability. When that merge goes through, we'll make some changes to make this one...

@HowieG Can you add the Anthropic notebook to the smoke test suite?

> I suspect it's related to the re-intiailising of these variables. It seems to work if i restart the kernel and run it the first time. But I cannot run...

> Hello, > > I'm using Ollama via Groq, can I track those LLM calls with agentops? > > Thank you We support Groq via our LiteLLM integration: https://docs.agentops.ai/v1/integrations/litellm Also,...

1. Assistants mode- Currently not looking at this capability. Would be a great function to add, but I must admit I'm not an expert with the assistants API 2. Indeed-...

> Thank you very much for your response. This feature is already great. > > As for your mention that GPT-4O currently does not have a dedicated token segmentation tool,...

Would be a cool feature but I haven't put much thought into how multi-modal APIs handle images in general. From my narrow understanding, OpenAI does things differently than other providers....

This would be great, actually. The main considerations are around how to manage the cost dictionary: The big challenge is that we rely on a 3rd party cost dictionary manager...