▶️ EXPERIMENT

Sidebar

• Lab Directory: choose the module whose lab artefacts you want to work on. The selection points at ${AGILAB_EXPORT_ABS}/<module> and initialises lab_steps.toml if it does not exist yet.

• Steps: pick the lab_steps file relative to the export directory. When you change the selection the assistant reloads the stored conversation.

• DataFrame: select which CSV (or parquet) is mounted for the assistant. The resolved absolute path lives under ${AGILAB_EXPORT_ABS}.

• Import Notebook: upload an .ipynb file to seed the conversation when working offline.

• Open MLflow UI: launches the MLflow dashboard in a new browser tab once activate_mlflow has started the local tracking server.

Main Content Area

ASSISTANT

Each lab is organised as a sequence of steps stored in lab_steps.toml. The numbered buttons at the top let you jump between them. Ask questions or describe transformations in the text area—AGILab forwards the prompt to the Responses API together with the selected DataFrame metadata. The code editor reacts to the toolbar actions:

• Save keeps the snippet as-is in the current step.

• Next persists the snippet and advances to a fresh step.

• Remove deletes the step from lab_steps.toml.

• Run writes the snippet to lab_snippet.py, executes it and stores any produced dataframe under lab_export_out.csv so the preview and the Execute/Explore pages can consume the result.

The assistant automatically reloads the most recent dataframe and shows it below the editor. If nothing has been saved yet, you will see a reminder to run a snippet first.

HISTORY

Inspect or tweak the raw lab_steps.toml via the code editor. Saving the file here immediately refreshes the assistant tab.

Regenerate Documentation

After updating this guide (or any docs surfaced in the IDE), rebuild the generated site so teammates and CI consume the same content:

./docs/gen_docs.sh

The wrapper guarantees uv runs docs/gen-docs.py with the extra build dependencies required for Sphinx and stub generation.