probe p4

TL;DR

The fix was Azure support for the scan: set AZURE\OPENAI\API\KEY, AZURE\OPENAI\ENDPOINT, OPENAI\API\VERSION, and GISKARD\SCAN\LLM\MODEL (see the maintainer's PR linked on the issue).

Steps

1. Cause: Giskard's scan evaluates generated answers through its own internal OpenAI client, which read your OPENAI_* environment variables and ignored your Azure config, hence the missing engine/deploymentid. The fix was Azure support for the scan: set `AZUREOPENAIAPIKEY, AZUREOPENAIENDPOINT, OPENAIAPIVERSION, and GISKARDSCANLLM_MODEL` (see the maintainer's PR linked on the issue). Note the judge still needs a function-calling-capable model, so GPT-4 is recommended.

When to use

You are seeing this: Cause: Giskard's scan evaluates generated answers through its own internal OpenAI client, which read your OPENAI\* environment variables and ignored your Azure config, hence the missing engine/deploymentid. Use this skill when you run into "probe p4".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

Edge cases

• Note the judge still needs a function-calling-capable model, so GPT-4 is recommended.

probe evidence