search

langchain-ai / langchain

🦜🔗 Build context-aware reasoning applications
https://python.langchain.com
MIT License
94.92k stars 15.37k forks source link

LLMOps integration of Aim and Wandb breaks when trying to parse agent output into dashboard for experiment tracking... #3441

Closed tosi-n closed 1 year ago

tosi-n commented 1 year ago

Aim:: aim.Text(outputs_res["output"]), name="on_chain_end", context=resp KeyError: 'output'

Wandb:: resp.update({"action": "on_chain_end", "outputs": outputs["output"]}) KeyError: 'output'

Has anyone dealt with this issue yet while building custom agents with LLMSingleActionAgent, thank you

dosubot[bot] commented 1 year ago

Hi, @tosi-n! I'm here to help the LangChain team manage their backlog and I wanted to let you know that we are marking this issue as stale.

Based on my understanding, you are experiencing a KeyError for the 'output' key when integrating LLMOps with Aim and Wandb. You mentioned that you are looking for assistance from anyone who has encountered this issue while building custom agents with LLMSingleActionAgent.

Before we proceed, could you please confirm if this issue is still relevant to the latest version of the LangChain repository? If it is, please let the LangChain team know by commenting on this issue. Otherwise, feel free to close the issue yourself or it will be automatically closed in 7 days.

Thank you for your understanding and we appreciate your contribution to the LangChain project!