William FH
William FH
Could you share al angsmith trace of this behavior to help me debug?
One way to have them end more reliably is to include reminders/instructions in responses after a tool is invoked. Like after a tool is used, return the tool result and...
We need to relax the default model-matching rules we have for cost estimation. (I think azure openai returns gpt-35-turbo instead of gpt-3.5-turbo for instance) You can customize the cost rules...
Thanks for raising - will pass this on. If you click on the `metadata` tab for one of those llm runs, what does it show? Any chance you could share...
Ack - Open to pointers, but I'm not aware of a super great way to annotate this type of behavior: ``` def traceable(callable: Callable[P, R]) -> Callable[Concat[("langsmith_extra", LangSmithExtra), P], R]:...
Do you have a code snippet for what you are using when you get this error? Are you targeting the public `https://api.smith.langchain.com` endpoint or are you using a self-hosted instance?
How frequent are you running into this? Is it on every call? (i'm having a hard time reproducing)
What version of langsmith are you using? (and langchain, if you're using this)
We fixed a couple issues with pending runs in more recent versions. Could you let me know if the issue persists after upgrading?
@vishal-git this is because the span end never made it to the server. they will never be marked finished unless they are patched with an end time.