[chrisk314]

OpenAI has deprecated gpt-3.5-turbo — LlamaIndex's OpenAI default — so the tutorial's LLM call now returns 404 model_not_found and the smoke test fails on every CI run (main will hit this too on its next push).

• Pass llm_kwargs={"model": "gpt-4o-mini"} explicitly in the tutorial.
• Note the deprecation in the tutorial's docs prose.

Verified locally that the call now reaches OpenAI (401 without a key, rather than 404 for the dead model); CI's smoke job holds the real key.

[github-actions]

Benchmark comparison for 2cf84111 (base) vs 4c2bab88 (PR)

------------------------------------------------------------------------------------------------------------------ benchmark: 2 tests -----------------------------------------------------------------------------------------------------------------
Name (time in ms)                                                                         Min                 Max                Mean            StdDev              Median               IQR            Outliers     OPS            Rounds  Iterations
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
test_benchmark_process_run (pr/.benchmarks/Linux-CPython-3.14-64bit/0001_pr)         303.6822 (1.0)      311.0885 (1.01)     308.0595 (1.01)     3.0360 (1.77)     309.2915 (1.01)     4.6593 (1.80)          1;0  3.2461 (0.99)          5           1
test_benchmark_process_run (main/.benchmarks/Linux-CPython-3.14-64bit/0001_base)     304.2964 (1.00)     308.5834 (1.0)      306.1156 (1.0)      1.7176 (1.0)      306.2816 (1.0)      2.5874 (1.0)           2;0  3.2667 (1.0)           5           1
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Legend:
  Outliers: 1 Standard Deviation from Mean; 1.5 IQR (InterQuartile Range) from 1st Quartile and 3rd Quartile.
  OPS: Operations Per Second, computed as 1 / Mean

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!