Help Needed: Import Issues with Phoenix Notebook Version Guidance

·Nov 12, 2024 08:30 PM

Hello everyone. I am hoping to get some help with this notebook. There seems to be issues with the imports. Which phoenix version should I be using? https://colab.research.google.com/github/Arize-ai/phoenix/blob/b107d9bc848efd38f030a8c72954e89616c43723/tutorials/evals/evaluate_tool_calling.ipynb

10 comments

· Sorted by Oldest

RunLLM
APP
·
To resolve import issues with the Phoenix library in your notebook, ensure you are using a compatible version. According to the Phoenix installation guide, you should install the latest stable version of arize-phoenix using pip install arize-phoenix. If you encounter specific issues, it might be helpful to check if there are any known bugs or fixes related to the version you are using, as seen in this GitHub issue.Would you like more details on troubleshooting specific import errors? Sources: - Phoenix installation guide - this GitHub issue
💡 Hint: Mention RunLLM in the thread for followups.
Xander S.
·
hey roberta g., this link appears to be out of date. where did you find it?
Xander S.
·
please try this link instead https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_tool_calling.ipynb#scrollTo=KvBTXtxRt26b
Xander S.
·
if that link was copied from our documentation, please let us know and we will update
Xander S.
·
found the link, it has been updated in our docs
roberta g.
·
Hello Xander S., thank you for the quick response. Is this excepted to be seen? I as running the link that you shared
Xander S.
·
that looks like a type error, it should not affect the runtime behavior of the notebook
roberta g.
·
any ideas of why this error could have occured? I just ran it as it is, from the very begining
Xander S.
·
are you referring to the error in the previous screenshot? that error looks like it is just a type error, so not a runtime error. you can make it disappear by adding an assertion on the line above the invocation of llm_classify
assert isinstance(trace_df, pd.DataFrame)
Xander S.
·
we do not run type checks on our tutorial notebooks, so it is possible that they contain type errors