How to define your inference set(s), launch a session, open the UI in your notebook or browser, and close your session when you're done
To define inferences, you must load your data into a pandas dataframe and create a matching schema. If you have a dataframe prim_df and a matching prim_schema, you can define inferences named "primary" with
prim_ds = px.Inferences(prim_df, prim_schema, "primary")If you additionally have a dataframe ref_df and a matching ref_schema, you can define a inference set named "reference" with
ref_ds = px.Inferences(ref_df, ref_schema, "reference")See Corpus Data if you have corpus data for an Information Retrieval use case.
Use phoenix.launch_app to start your Phoenix session in the background. You can launch Phoenix with zero, one, or two inference sets.
You can view and interact with the Phoenix UI either directly in your notebook or in a separate browser tab or window.
In a notebook cell, run
session.urlCopy and paste the output URL into a new browser tab or window.
In a notebook cell, run
session.view()The Phoenix UI will appear in an inline frame in the cell output.
When you're done using Phoenix, gracefully shut down your running background session with
px.close_app()No Inferences
session = px.launch_app()Run Phoenix in the background to collect OpenInference traces emitted by your instrumented LLM application.
Single Inference Set
session = px.launch_app(ds)Analyze a single cohort of data, e.g., only training data.
Check model performance and data quality, but not drift.
Primary and Reference Inference Sets
session = px.launch_app(prim_ds, ref_ds)Compare cohorts of data, e.g., training vs. production.
Analyze drift in addition to model performance and data quality.
Primary and Corpus Inference Sets
session = px.launch_app(query_ds, corpus=corpus_ds)Compare a query inference set to a corpus dataset to analyze your retrieval-augmented generation applications.