Foundry Config Setup

Usage

Some samples (notably those under 01-get-started) hardcode the Foundry

project endpoint and model directly in the FoundryChatClient constructor

using placeholder values, for example:

client = FoundryChatClient(
    project_endpoint="https://your-project.services.ai.azure.com",
    model="gpt-4o",
    credential=AzureCliCredential(),
)

These placeholder values are not real and the sample cannot run as written.

The validation environment provides the real values through environment

variables, so the sample must read them from the environment instead.

When you detect a hardcoded/placeholder project_endpoint (or model) that

is causing the sample to fail with missing or invalid setup:

• Replace the hardcoded project_endpoint value with a read from the

FOUNDRY_PROJECT_ENDPOINT environment variable.

• Replace the hardcoded model value with a read from the FOUNDRY_MODEL

environment variable.

• Ensure import os is present at the top of the file.

The corrected constructor should look like:

import os

client = FoundryChatClient(
    project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
    model=os.environ["FOUNDRY_MODEL"],
    credential=AzureCliCredential(),
)

These samples are intentionally written with hardcoded placeholders, so this

is expected setup—not a defect in the sample. After applying the change,

re-run the sample and report the result as a success if it now runs.