azure-ai-projects 1.0.0b1

Microsoft Azure AI Projects Client Library for Python

Azure AI Projects client library for Python

Use the AI Projects client library (in preview) to:

• Enumerate connections in your Azure AI Studio project and get connection properties. For example, get the inference endpoint URL and credentials associated with your Azure OpenAI connection.
• Get an authenticated Inference client to do chat completions, for the default Azure OpenAI or AI Services connections in your Azure AI Studio project. Supports the AzureOpenAI client from the openai package, or clients from the azure-ai-inference package.
• Develop Agents using the Azure AI Agent Service, leveraging an extensive ecosystem of models, tools, and capabilities from OpenAI, Microsoft, and other LLM providers. The Azure AI Agent Service enables the building of Agents for a wide range of generative AI use cases. The package is currently in private preview.
• Run Evaluations to assess the performance of generative AI applications using various evaluators and metrics. It includes built-in evaluators for quality, risk, and safety, and allows custom evaluators for specific needs.
• Enable OpenTelemetry tracing.

Product documentation | Samples | API reference documentation | Package (PyPI) | SDK source code | AI Starter Template

Table of contents

• Getting started
  • Prerequisite
  • Install the package
• Key concepts
  • Create and authenticate the client
• Examples
  • Enumerate connections
    • Get properties of all connections
    • Get properties of all connections of a particular type
    • Get properties of a default connection
    • Get properties of a connection by its connection name
  • Get an authenticated ChatCompletionsClient
  • Get an authenticated AzureOpenAI client
  • Agents (Private Preview)
    • Create an Agent with:
      • File Search
      • Code interpreter
      • Bing grounding
      • Azure AI Search
      • Function call
    • Create thread with
      • Tool resource
    • Create message with:
      • File search attachment
      • Code interpreter attachment
    • Execute Run, Run_and_Process, or Stream
    • Retrieve message
    • Retrieve file
    • Tear down by deleting resource
    • Tracing
  • Evaluation
    • Evaluator
    • Run Evaluation in the cloud
      • Evaluators
      • Data to be evaluated
        • [Optional] Azure OpenAI Model
        • Example Remote Evaluation
  • Tracing
    • Installation
    • Tracing example
• Troubleshooting
  • Exceptions
  • Logging
  • Reporting issues
• Next steps
• Contributing

Getting started

Prerequisite

• Python 3.8 or later.
• An Azure subscription.
• A project in Azure AI Studio.
• The project connection string. It can be found in your Azure AI Studio project overview page, under "Project details". Below we will assume the environment variable PROJECT_CONNECTION_STRING was defined to hold this value.
• Entra ID is needed to authenticate the client. Your application needs an object that implements the TokenCredential interface. Code samples here use DefaultAzureCredential. To get that working, you will need:
  • The Contributor role. Role assigned can be done via the "Access Control (IAM)" tab of your Azure AI Project resource in the Azure portal.
  • Azure CLI installed.
  • You are logged into your Azure account by running az login.
  • Note that if you have multiple Azure subscriptions, the subscription that contains your Azure AI Project resource must be your default subscription. Run az account list --output table to list all your subscription and see which one is the default. Run az account set --subscription "Your Subscription ID or Name" to change your default subscription.

Install the package

pip install azure-ai-projects

Key concepts

Create and authenticate the client

The class factory method from_connection_string is used to construct the client. To construct a synchronous client:

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

project_client = AIProjectClient.from_connection_string(
    credential=DefaultAzureCredential(),
    conn_str=os.environ["PROJECT_CONNECTION_STRING"],
)

To construct an asynchronous client, Install the additional package aiohttp:

pip install aiohttp

and update the code above to import asyncio, and import AIProjectClient from the azure.ai.projects.aio namespace:

import os
import asyncio
from azure.ai.projects.aio import AIProjectClient
from azure.core.credentials import AzureKeyCredential

project_client = AIProjectClient.from_connection_string(
    credential=DefaultAzureCredential(),
    conn_str=os.environ["PROJECT_CONNECTION_STRING"],
)

Examples

Enumerate connections

Your Azure AI Studio project has a "Management center". When you enter it, you will see a tab named "Connected resources" under your project. The .connections operations on the client allow you to enumerate the connections and get connection properties. Connection properties include the resource URL and authentication credentials, among other things.

Below are code examples of the connection operations. Full samples can be found under the "connetions" folder in the package samples.

Get properties of all connections

To list the properties of all the connections in the Azure AI Studio project:

connections = project_client.connections.list()
for connection in connections:
    print(connection)

Get properties of all connections of a particular type

To list the properties of connections of a certain type (here Azure OpenAI):

connections = project_client.connections.list(
    connection_type=ConnectionType.AZURE_OPEN_AI,
)
for connection in connections:
    print(connection)

Get properties of a default connection

To get the properties of the default connection of a certain type (here Azure OpenAI), with its authentication credentials:

connection = project_client.connections.get_default(
    connection_type=ConnectionType.AZURE_OPEN_AI,
    include_credentials=True,  # Optional. Defaults to "False".
)
print(connection)

If the call was made with include_credentials=True, depending on the value of connection.authentication_type, either connection.key or connection.token_credential will be populated. Otherwise both will be None.

Get properties of a connection by its connection name

To get the connection properties of a connection named connection_name:

connection = project_client.connections.get(
    connection_name=connection_name,
    include_credentials=True  # Optional. Defaults to "False"
)
print(connection)

Get an authenticated ChatCompletionsClient

Your Azure AI Studio project may have one or more AI models deployed that support chat completions. These could be OpenAI models, Microsoft models, or models from other providers. Use the code below to get an already authenticated ChatCompletionsClient from the azure-ai-inference package, and execute a chat completions call.

First, install the package:

pip install azure-ai-inference

Then run this code (replace "gpt-4o" with your model deployment name):

inference_client = project_client.inference.get_chat_completions_client()

response = inference_client.complete(
    model="gpt-4o", # Model deployment name
    messages=[UserMessage(content="How many feet are in a mile?")]
)

print(response.choices[0].message.content)

See the "inference" folder in the package samples for additional samples, including getting an authenticated EmbeddingsClient.

Get an authenticated AzureOpenAI client

Your Azure AI Studio project may have one or more OpenAI models deployed that support chat completions. Use the code below to get an already authenticated AzureOpenAI from the openai package, and execute a chat completions call.

First, install the package:

pip install openai

Then run the code below. Replace gpt-4o with your model deployment name, and update the api_version value with one found in the "Data plane - inference" row in this table.

aoai_client = project_client.inference.get_azure_openai_client(api_version="2024-06-01")

response = aoai_client.chat.completions.create(
    model="gpt-4o", # Model deployment name
    messages=[
        {
            "role": "user",
            "content": "How many feet are in a mile?",
        },
    ],
)

print(response.choices[0].message.content)

See the "inference" folder in the package samples for additional samples.

Agents (Private Preview)

Agents in the Azure AI Projects client library are designed to facilitate various interactions and operations within your AI projects. They serve as the core components that manage and execute tasks, leveraging different tools and resources to achieve specific goals. The following steps outline the typical sequence for interacting with Agents. See the "agents" folder in the package samples for additional Agent samples.

Agents are actively being developed. A sign-up form for private preview is coming soon.

Create Agent

Here is an example of how to create an Agent:

agent = project_client.agents.create_agent(
    model="gpt-4-1106-preview",
    name="my-assistant",
    instructions="You are helpful assistant",
)

To allow Agents to access your resources or custom functions, you need tools. You can pass tools to create_agent by either toolset or combination of tools and tool_resources.

Here is an example of toolset:

functions = FunctionTool(user_functions)
code_interpreter = CodeInterpreterTool()

toolset = ToolSet()
toolset.add(functions)
toolset.add(code_interpreter)

agent = project_client.agents.create_agent(
    model="gpt-4-1106-preview", name="my-assistant", instructions="You are a helpful assistant", toolset=toolset
)

Also notices that if you use asynchronous client, you use AsyncToolSet instead. Additional information related to AsyncFunctionTool be discussed in the later sections.

Here is an example to use tools and tool_resources:

file_search_tool = FileSearchTool(vector_store_ids=[vector_store.id])

# notices that FileSearchTool as tool and tool_resources must be added or the assistant unable to search the file
agent = project_client.agents.create_agent(
    model="gpt-4-1106-preview",
    name="my-assistant",
    instructions="You are helpful assistant",
    tools=file_search_tool.definitions,
    tool_resources=file_search_tool.resources,
)

In the following sections, we show you sample code in either toolset or combination of tools and tool_resources.

Create Agent with File Search

To perform file search by an Agent, we first need to upload a file, create a vector store, and associate the file to the vector store. Here is an example:

file = project_client.agents.upload_file_and_poll(file_path="product_info_1.md", purpose="assistants")
print(f"Uploaded file, file ID: {file.id}")

vector_store = project_client.agents.create_vector_store_and_poll(file_ids=[file.id], name="my_vectorstore")
print(f"Created vector store, vector store ID: {vector_store.id}")

# Create file search tool with resources followed by creating agent
file_search = FileSearchTool(vector_store_ids=[vector_store.id])

agent = project_client.agents.create_agent(
    model="gpt-4-1106-preview",
    name="my-assistant",
    instructions="Hello, you are helpful assistant and can search information from uploaded files",
    tools=file_search.definitions,
    tool_resources=file_search.resources,
)

Create Agent with Code Interpreter

Here is an example to upload a file and use it for code interpreter by an Agent:

file = project_client.agents.upload_file_and_poll(
    file_path="nifty_500_quarterly_results.csv", purpose=FilePurpose.AGENTS
)
print(f"Uploaded file, file ID: {file.id}")

code_interpreter = CodeInterpreterTool(file_ids=[file.id])

# create agent with code interpreter tool and tools_resources
agent = project_client.agents.create_agent(
    model="gpt-4-1106-preview",
    name="my-assistant",
    instructions="You are helpful assistant",
    tools=code_interpreter.definitions,
    tool_resources=code_interpreter.resources,
)

Create Agent with Bing Grounding

To enable your Agent to perform search through Bing search API, you use BingGroundingTool along with a connection.

Here is an example:

bing_connection = project_client.connections.get(connection_name=os.environ["BING_CONNECTION_NAME"])
conn_id = bing_connection.id

print(conn_id)

# Initialize agent bing tool and add the connection id
bing = BingGroundingTool(connection_id=conn_id)

# Create agent with the bing tool and process assistant run
with project_client:
    agent = project_client.agents.create_agent(
        model="gpt-4-1106-preview",
        name="my-assistant",
        instructions="You are a helpful assistant",
        tools=bing.definitions,
        headers={"x-ms-enable-preview": "true"},
    )

Create Agent with Azure AI Search

Azure AI Search is an enterprise search system for high-performance applications. It integrates with Azure OpenAI Service and Azure Machine Learning, offering advanced search technologies like vector search and full-text search. Ideal for knowledge base insights, information discovery, and automation

Here is an example to integrate Azure AI Search:

conn_list = project_client.connections.list()
conn_id = ""
for conn in conn_list:
    if conn.connection_type == "CognitiveSearch":
        conn_id = conn.id
        break

print(conn_id)

# Initialize agent AI search tool and add the search index connection id
ai_search = AzureAISearchTool()
ai_search.add_index(conn_id, "sample_index")

# Create agent with AI search tool and process assistant run
with project_client:
    agent = project_client.agents.create_agent(
        model="gpt-4-1106-preview",
        name="my-assistant",
        instructions="You are a helpful assistant",
        tools=ai_search.definitions,
        headers={"x-ms-enable-preview": "true"},
    )

Create Agent with Function Call

You can enhance your Agents by defining callback functions as function tools. These can be provided to create_agent via either the toolset parameter or the combination of tools and tool_resources. Here are the distinctions:

• toolset: When using the toolset parameter, you provide not only the function definitions and descriptions but also their implementations. The SDK will execute these functions within create_and_run_process or streaming . These functions will be invoked based on their definitions.
• tools and tool_resources: When using the tools and tool_resources parameters, only the function definitions and descriptions are provided to create_agent, without the implementations. The Run or event handler of stream will raise a requires_action status based on the function definitions. Your code must handle this status and call the appropriate functions.

For more details about calling functions by code, refer to sample_agents_stream_eventhandler_with_functions.py and sample_agents_functions.py.

Here is an example to use user functions in toolset:

functions = FunctionTool(user_functions)
toolset = ToolSet()
toolset.add(functions)

agent = project_client.agents.create_agent(
    model="gpt-4-1106-preview", name="my-assistant", instructions="You are a helpful assistant", toolset=toolset
)

For asynchronous functions, you must import AIProjectClient from azure.ai.projects.aio and use AsyncFunctionTool. Here is an example using asynchronous user functions:

from azure.ai.projects.aio import AIProjectClient

functions = AsyncFunctionTool(user_async_functions)

toolset = AsyncToolSet()
toolset.add(functions)

agent = await project_client.agents.create_agent(
    model="gpt-4-1106-preview", name="my-assistant", instructions="You are a helpful assistant", toolset=toolset
)

Create Thread

For each session or conversation, a thread is required. Here is an example:

thread = project_client.agents.create_thread()

Create Thread with Tool Resource

In some scenarios, you might need to assign specific resources to individual threads. To achieve this, you provide the tool_resources argument to create_thread. In the following example, you create a vector store and upload a file, enable an Agent for file search using the tools argument, and then associate the file with the thread using the tool_resources argument.

file = project_client.agents.upload_file_and_poll(file_path="product_info_1.md", purpose="assistants")
print(f"Uploaded file, file ID: {file.id}")

vector_store = project_client.agents.create_vector_store_and_poll(file_ids=[file.id], name="my_vectorstore")
print(f"Created vector store, vector store ID: {vector_store.id}")

# Create file search tool with resources followed by creating agent
file_search = FileSearchTool(vector_store_ids=[vector_store.id])

agent = project_client.agents.create_agent(
    model="gpt-4-1106-preview",
    name="my-assistant",
    instructions="Hello, you are helpful assistant and can search information from uploaded files",
    tools=file_search.definitions,
)

print(f"Created agent, ID: {agent.id}")

# Create thread with file resources.
# If the agent has multiple threads, only this thread can search this file.
thread = project_client.agents.create_thread(tool_resources=file_search.resources)

Create Message

To create a message for assistant to process, you pass user as role and a question as content:

message = project_client.agents.create_message(thread_id=thread.id, role="user", content="Hello, tell me a joke")

Create Message with File Search Attachment

To attach a file to a message for content searching, you use MessageAttachment and FileSearchTool:

attachment = MessageAttachment(file_id=file.id, tools=FileSearchTool().definitions)
message = project_client.agents.create_message(
    thread_id=thread.id, role="user", content="What feature does Smart Eyewear offer?", attachments=[attachment]
)

Create Message with Code Interpreter Attachment

To attach a file to a message for data analysis, you use MessageAttachment and CodeInterpreterTool. You must pass CodeInterpreterTool as tools or toolset in create_agent call or the file attachment cannot be opened for code interpreter.

Here is an example to pass CodeInterpreterTool as tool:

# notice that CodeInterpreter must be enabled in the agent creation,
# otherwise the agent will not be able to see the file attachment for code interpretation
agent = project_client.agents.create_agent(
    model="gpt-4-1106-preview",
    name="my-assistant",
    instructions="You are helpful assistant",
    tools=CodeInterpreterTool().definitions,
)
print(f"Created agent, agent ID: {agent.id}")

thread = project_client.agents.create_thread()
print(f"Created thread, thread ID: {thread.id}")

# create an attachment
attachment = MessageAttachment(file_id=file.id, tools=CodeInterpreterTool().definitions)

# create a message
message = project_client.agents.create_message(
    thread_id=thread.id,
    role="user",
    content="Could you please create bar chart in TRANSPORTATION sector for the operating profit from the uploaded csv file and provide file to me?",
    attachments=[attachment],
)

Create Run, Run_and_Process, or Stream

To process your message, you can use create_run, create_and_process_run, or create_stream.

create_run requests the Agent to process the message without polling for the result. If you are using function tools regardless as toolset or not, your code is responsible for polling for the result and acknowledging the status of Run. When the status is requires_action, your code is responsible for calling the function tools. For a code sample, visit sample_agents_functions.py.

Here is an example of create_run and poll until the run is completed:

run = project_client.agents.create_run(thread_id=thread.id, assistant_id=agent.id)

# poll the run as long as run status is queued or in progress
while run.status in ["queued", "in_progress", "requires_action"]:
    # wait for a second
    time.sleep(1)
    run = project_client.agents.get_run(thread_id=thread.id, run_id=run.id)

To have the SDK poll on your behalf and call function tools, use the create_and_process_run method. Note that function tools will only be invoked if they are provided as toolset during the create_agent call.

Here is an example:

run = project_client.agents.create_and_process_run(thread_id=thread.id, assistant_id=agent.id)

With streaming, polling also need not be considered. If function tools are provided as toolset during the create_agent call, they will be invoked by the SDK.

Here is an example:

with project_client.agents.create_stream(
    thread_id=thread.id, assistant_id=agent.id, event_handler=MyEventHandler()
) as stream:
    stream.until_done()

The event handler is optional. Here is an example:

class MyEventHandler(AgentEventHandler):
    def on_message_delta(self, delta: "MessageDeltaChunk") -> None:
        for content_part in delta.delta.content:
            if isinstance(content_part, MessageDeltaTextContent):
                text_value = content_part.text.value if content_part.text else "No text"
                print(f"Text delta received: {text_value}")

    def on_thread_message(self, message: "ThreadMessage") -> None:
        print(f"ThreadMessage created. ID: {message.id}, Status: {message.status}")

    def on_thread_run(self, run: "ThreadRun") -> None:
        print(f"ThreadRun status: {run.status}")

    def on_run_step(self, step: "RunStep") -> None:
        print(f"RunStep type: {step.type}, Status: {step.status}")

    def on_error(self, data: str) -> None:
        print(f"An error occurred. Data: {data}")

    def on_done(self) -> None:
        print("Stream completed.")

    def on_unhandled_event(self, event_type: str, event_data: Any) -> None:
        print(f"Unhandled Event Type: {event_type}, Data: {event_data}")

Retrieve Message

To retrieve messages from agents, use the following example:

messages = project_client.agents.list_messages(thread_id=thread.id)

# The messages are following in the reverse order,
# we will iterate them and output only text contents.
for data_point in reversed(messages.data):
    last_message_content = data_point.content[-1]
    if isinstance(last_message_content, MessageTextContent):
        print(f"{data_point.role}: {last_message_content.text.value}")

Depending on the use case, if you expect the Agents to return only text messages, list_messages should be sufficient. If you are using tools, consider using the get_messages function instead. This function classifies the message content and returns properties such as text_messages, image_contents, file_citation_annotations, and file_path_annotations.

Retrieve File

Files uploaded by Agents cannot be retrieved back. If your use case need to access the file content uploaded by the Agents, you are advised to keep an additional copy accessible by your application. However, files generated by Agents are retrievable by save_file or get_file_content.

Here is an example retrieving file ids from messages and save to the local drive:

messages = project_client.agents.get_messages(thread_id=thread.id)
print(f"Messages: {messages}")

for image_content in messages.image_contents:
    file_id = image_content.image_file.file_id
    print(f"Image File ID: {file_id}")
    file_name = f"{file_id}_image_file.png"
    project_client.agents.save_file(file_id=file_id, file_name=file_name)
    print(f"Saved image file to: {Path.cwd() / file_name}")

for file_path_annotation in messages.file_path_annotations:
    print(f"File Paths:")
    print(f"Type: {file_path_annotation.type}")
    print(f"Text: {file_path_annotation.text}")
    print(f"File ID: {file_path_annotation.file_path.file_id}")
    print(f"Start Index: {file_path_annotation.start_index}")
    print(f"End Index: {file_path_annotation.end_index}")

Here is an example to use get_file_content:

from pathlib import Path

async def save_file_content(client, file_id: str, file_name: str, target_dir: Optional[Union[str, Path]] = None):
    # Determine the target directory
    path = Path(target_dir).expanduser().resolve() if target_dir else Path.cwd()
    path.mkdir(parents=True, exist_ok=True)

    # Retrieve the file content
    file_content_stream = await client.get_file_content(file_id)
    if not file_content_stream:
        raise RuntimeError(f"No content retrievable for file ID '{file_id}'.")

    # Collect all chunks asynchronously
    chunks = []
    async for chunk in file_content_stream:
        if isinstance(chunk, (bytes, bytearray)):
            chunks.append(chunk)
        else:
            raise TypeError(f"Expected bytes or bytearray, got {type(chunk).__name__}")

    target_file_path = path / file_name

    # Write the collected content to the file synchronously
    with open(target_file_path, "wb") as file:
        for chunk in chunks:
            file.write(chunk)

Teardown

To remove resources after completing tasks, use the following functions:

# Delete the file when done
project_client.agents.delete_vector_store(vector_store.id)
print("Deleted vector store")

project_client.agents.delete_file(file_id=file.id)
print("Deleted file")

# Delete the agent when done
project_client.agents.delete_agent(agent.id)
print("Deleted agent")

Evaluation

Evaluation in Azure AI Project client library is designed to assess the performance of generative AI applications in the cloud. The output of Generative AI application is quantitively measured with mathematical based metrics, AI-assisted quality and safety metrics. Metrics are defined as evaluators. Built-in or custom evaluators can provide comprehensive insights into the application's capabilities and limitations.

Evaluator

Evaluators are custom or prebuilt classes or functions that are designed to measure the quality of the outputs from language models or generative AI applications.

Evaluators are made available via azure-ai-evaluation SDK for local experience and also in Evaluator Library in Azure AI Studio for using them in the cloud.

More details on built-in and custom evaluators can be found here.

Run Evaluation in the cloud

To run evaluation in the cloud the following are needed:

• Evaluators
• Data to be evaluated
• [Optional] Azure Open AI model.

Evaluators

For running evaluator in the cloud, evaluator ID is needed. To get it via code you use azure-ai-evaluation

# pip install azure-ai-evaluation

from azure.ai.evaluation import RelevanceEvaluator

evaluator_id = RelevanceEvaluator.id

Data to be evaluated

Evaluation in the cloud supports data in form of jsonl file. Data can be uploaded via the helper method upload_file on the project client.

# Upload data for evaluation and get dataset id
data_id, _ = project_client.upload_file("<data_file.jsonl>")

[Optional] Azure OpenAI Model

Azure AI Studio project comes with a default Azure Open AI endpoint which can be easily accessed using following code. This gives you the endpoint details for you Azure OpenAI endpoint. Some of the evaluators need model that supports chat completion.

default_connection = project_client.connections.get_default(connection_type=ConnectionType.AZURE_OPEN_AI)

Example Remote Evaluation

import os
from azure.ai.projects import AIProjectClient
from azure.identity import DefaultAzureCredential
from azure.ai.projects.models import Evaluation, Dataset, EvaluatorConfiguration, ConnectionType
from azure.ai.evaluation import F1ScoreEvaluator, RelevanceEvaluator, HateUnfairnessEvaluator


# Create project client
project_client = AIProjectClient.from_connection_string(
    credential=DefaultAzureCredential(),
    conn_str=os.environ["PROJECT_CONNECTION_STRING"],
)

# Upload data for evaluation and get dataset id
data_id, _ = project_client.upload_file("<data_file.jsonl>")

deployment_name = "<deployment_name>"
api_version = "<api_version>"

# Create an evaluation
evaluation = Evaluation(
    display_name="Remote Evaluation",
    description="Evaluation of dataset",
    data=Dataset(id=data_id),
    evaluators={
        "f1_score": EvaluatorConfiguration(
            id=F1ScoreEvaluator.id,
        ),
        "relevance": EvaluatorConfiguration(
            id=RelevanceEvaluator.id,
            init_params={
                "model_config": default_connection.to_evaluator_model_config(
                    deployment_name=deployment_name, api_version=api_version
                )
            },
        ),
        "violence": EvaluatorConfiguration(
            id=ViolenceEvaluator.id,
            init_params={"azure_ai_project": project_client.scope},
        ),
    },
)


evaluation_response = project_client.evaluations.create(
    evaluation=evaluation,
)

# Get evaluation
get_evaluation_response = project_client.evaluations.get(evaluation_response.id)

print("----------------------------------------------------------------")
print("Created evaluation, evaluation ID: ", get_evaluation_response.id)
print("Evaluation status: ", get_evaluation_response.status)
if isinstance(get_evaluation_response.properties, dict):
    print("AI Studio URI: ", get_evaluation_response.properties["AiStudioEvaluationUri"])
print("----------------------------------------------------------------")

NOTE: For running evaluators locally refer to Evaluate with the Azure AI Evaluation SDK.

Tracing

You can add an Application Insights Azure resource to your Azure AI Studio project. See the Tracing tab in your studio. If one was enabled, you can get the Application Insights connection string, configure your Agents, and observe the full execution path through Azure Monitor. Typically, you might want to start tracing before you create an Agent.

Installation

Make sure to install OpenTelemetry and the Azure SDK tracing plugin via

pip install opentelemetry
pip install azure-core-tracing-opentelemetry

You will also need an exporter to send telemetry to your observability backend. You can print traces to the console or use a local viewer such as Aspire Dashboard.

To connect to Aspire Dashboard or another OpenTelemetry compatible backend, install OTLP exporter:

pip install opentelemetry-exporter-otlp

Tracing example

Here is a code sample to be included above create_agent:

from opentelemetry import trace
from azure.monitor.opentelemetry import configure_azure_monitor

# Enable Azure Monitor tracing
application_insights_connection_string = project_client.telemetry.get_connection_string()
if not application_insights_connection_string:
    print("Application Insights was not enabled for this project.")
    print("Enable it via the 'Tracing' tab in your AI Studio project page.")
    exit()
configure_azure_monitor(connection_string=application_insights_connection_string)

scenario = os.path.basename(__file__)
tracer = trace.get_tracer(__name__)

with tracer.start_as_current_span(scenario):
    with project_client:

In additional, you might find helpful to see the tracing logs in console. You can achieve by the following code:

project_client.telemetry.enable(destination=sys.stdout)

Troubleshooting

Exceptions

Client methods that make service calls raise an HttpResponseError exception for a non-success HTTP status code response from the service. The exception's status_code will hold the HTTP response status code (with reason showing the friendly name). The exception's error.message contains a detailed message that may be helpful in diagnosing the issue:

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)

For example, when you provide wrong credentials:

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

Logging

The client uses the standard Python logging library. The SDK logs HTTP request and response details, which may be useful in troubleshooting. To log to stdout, add the following:

import sys
import logging

# Acquire the logger for this client library. Use 'azure' to affect both
# 'azure.core` and `azure.ai.inference' 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)

By default logs redact the values of URL query strings, the values of some HTTP request and response headers (including Authorization which holds the key or token), and the request and response payloads. To create logs without redaction, add logging_enable = True to the client constructor:

project_client = AIProjectClient.from_connection_string(
    credential=DefaultAzureCredential(),
    conn_str=os.environ["PROJECT_CONNECTION_STRING"],
    logging_enable = True
)

Note that the log level must be set to logging.DEBUG (see above code). Logs will be redacted with any other log level.

Be sure to protect non redacted logs to avoid compromising security.

For more information, see Configure logging in the Azure libraries for Python

Reporting issues

To report issues with the client library, or request additional features, please open a GitHub issue here

Next steps

Have a look at the Samples folder, containing fully runnable Python code for synchronous and asynchronous clients.

Explore the AI Starter Template. This template creates an Azure AI Studio hub, project and connected resources including Azure OpenAI Service, AI Search and more. It also deploys a simple chat application to Azure Container Apps.

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.microsoft.com.

When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information, see the Code of Conduct FAQ or contact [e-mail] with any additional questions or comments.