traceloop / traceloop/openllmetry
๐ Bug Report: LiteLLM tracing when not using openAI models not complete
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.4k
- Forks
- 1.1k
- Avg merge
- 8d 14h
- Merged PRs (30d)
- 2
Description
Which component is this bug for?
Traceloop SDK
๐ Description
When using the litellm with anthropic models, the proper/full tracing expected isn't showing up.
This is the information that I see
๐ Reproduction steps
Use litellm with an anthropic model.
๐ Expected behavior
I should expect something similar to openai for openllmetry supported models through litellm, like openai
๐ Actual Behavior with Screenshots
See screenshot above
๐ค Python Version
Python 3.11
๐ Provide any additional context for the Bug.
No response
๐ Have you spent some time to check if this bug has been raised before?
- I checked and didn't find similar issue
Are you willing to submit PR?
None
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up โ it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the Traceloop SDK's LiteLLM instrumentation entry point and reproduce the issue with Python 3.11 using LiteLLM and an Anthropic model. Compare its trace with the OpenAI-model example; done means supported non-OpenAI models produce the expected complete tracing.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, observability-sre
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100