NVIDIA-NeMo / NVIDIA-NeMo/Guardrails
NeMo-Guardrails breaks Langfuse integration / Runnable config is ignored in LLM call
Open
@Pouyanpi is already working on this.
Since Nov 12, 2024.
enhancement
good first issue
status: help wanted
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 842
- Avg merge
- 3d 1h
- Merged PRs (30d)
- 25
Description
When Langfuse is used for tracing (instead of Langsmith), the usage of NeMo-Guardrails in a Langchain chain completely breaks the tracing functionality.
The reason seems to be, that the langchain runnable is not called with the runnable config, which defines callbacks for langchain.
So the LLM runnable that is wrapped in the RunnableRails object is missing the runnable config, and as such the callbacks configured there won't be called and as such the tracing isn't invoked.
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 — 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.
Assessment
This issue has not been assessed yet.