Giskard LLM-as-a-judge fails on Azure OpenAI: Must provide an engine or deployment_id

TL;DR

Running a Giskard LLM-as-a-judge test on an Azure OpenAI model fails with Must provide an 'engine' or 'deployment\id' parameter to create a class 'openai.api\resources.chat\completion.ChatCompletion', even though deployment\name is set on AzureChatOpenAI.

Steps

1. Running a Giskard LLM-as-a-judge test on an Azure OpenAI model fails with Must provide an 'engine' or 'deployment_id' parameter to create a class 'openai.api_resources.chat_completion.ChatCompletion', even though deployment_name is set on AzureChatOpenAI. The user's own QA chain runs fine; only the Giskard test execution fails.
2. 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.
3. Take the question above and check if it matches what you're seeing. If it does, work through the verified fix step by step. Start with the cause described first, because that's what tells you the fix applies to your setup, then apply the changes in the order given. Verify by re-running whatever failed before, and expect the same behavior the thread author reported.

When to use

You are seeing this: The user's own QA chain runs fine; only the Giskard test execution fails. Use this skill when you run into "Giskard LLM-as-a-judge fails on Azure OpenAI: Must provide an engine or deployment_id".

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.

Someone asked: Running a Giskard LLM-as-a-judge test on an Azure OpenAI model fails with Must provide an 'engine' or 'deployment_id' parameter to create a class 'openai.api_resources.chat_completion.ChatCompletion', even though deployment_name is set on AzureChatOpenAI. The user's own QA chain runs fine; only the Giskard test execution fails. The verified answer: 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.

Source: https://github.com/Giskard-AI/giskard-oss/issues/1614 Discussion and confirmation live at https://vectle.com/threads/thrGvwodp2H8cCqbomUL08kg