Azure AI Projects

https://learn.microsoft.com/python/api/overview/azure/
Admin
Azure AI Projects is a Python client library for Microsoft Foundry that enables developers to build...
Tokens:1,715
Snippets:29
Trust Score:10
Update:1 month ago
Show doc for...
Tokens:
Raw
### Install azure-ai-projects package

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Install the required client library using pip.

```bash
pip install azure-ai-projects
```

--------------------------------

### Verify package installation

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Check the installed version of the azure-ai-projects package.

```bash
pip show azure-ai-projects
```

--------------------------------

### Install aiohttp for asynchronous support

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Install the aiohttp package required for asynchronous client operations.

```bash
pip install aiohttp
```

--------------------------------

### Example error output

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Sample output for an unauthorized credential error.

```text
Status code: 401 (Unauthorized)
Operation returned an invalid status 'Unauthorized'
```

--------------------------------

### Initialize synchronous AIProjectClient

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Construct a synchronous client using a context manager and DefaultAzureCredential.

```python
import os
from azure.ai.projects import AIProjectClient
from azure.identity import DefaultAzureCredential

with (
    DefaultAzureCredential() as credential,
    AIProjectClient(
        endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
        credential=credential
    ) as project_client,
):
```

--------------------------------

### Initialize asynchronous AIProjectClient

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Construct an asynchronous client using an async context manager.

```python
import os
import asyncio
from azure.ai.projects.aio import AIProjectClient
from azure.identity.aio import DefaultAzureCredential

async with (
    DefaultAzureCredential() as credential,
    AIProjectClient(
        endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
        credential=credential
    ) as project_client,
):
```

--------------------------------

### Configure custom logging

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Manually configure the Python logging library to output client logs to stdout or a file.

```python
import sys
import logging

# Acquire the logger for this client library. Use 'azure' to affect both
# `azure.core` and `azure.ai.projects' libraries.
logger = logging.getLogger("azure")

# Set the desired logging level. logging.INFO or logging.DEBUG are good options.
logger.setLevel(logging.DEBUG)

# Direct logging output to stdout:
handler = logging.StreamHandler(stream=sys.stdout)
# Or direct logging output to a file:
# handler = logging.FileHandler(filename="sample.log")
logger.addHandler(handler)

# Optional: change the default logging format. Here we add a timestamp.
#formatter = logging.Formatter("%(asctime)s:%(levelname)s:%(name)s:%(message)s")
#handler.setFormatter(formatter)
```

--------------------------------

### Perform operations with OpenAI client

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Obtain an authenticated OpenAI client from the project client to perform response operations.

```python
with project_client.get_openai_client() as openai_client:
    response = openai_client.responses.create(
        model=os.environ["FOUNDRY_MODEL_NAME"],
        input="What is the size of France in square miles?",
    )
    print(f"Response output: {response.output_text}")

    response = openai_client.responses.create(
        model=os.environ["FOUNDRY_MODEL_NAME"],
        input="And what is the capital city?",
        previous_response_id=response.id,
    )
    print(f"Response output: {response.output_text}")
```

--------------------------------

### Enable non-redacted logging

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Configure the client constructor to disable redaction of sensitive information in logs. Requires logging level to be set to DEBUG.

```python
project_client = AIProjectClient(
    credential=DefaultAzureCredential(),
    endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
    logging_enable=True
)
```

--------------------------------

### Handle HttpResponseError exceptions

Source: https://learn.microsoft.com/python/api/overview/azure/ai-projects-readme

Catch and inspect service call errors to retrieve status codes and detailed error messages.

```python
from azure.core.exceptions import HttpResponseError

...

try:
    result = project_client.connections.list()
except HttpResponseError as e:
    print(f"Status code: {e.status_code} ({e.reason})")
    print(e.message)
```
Tokens:
Raw