Merge branch 'Azure-Samples:main' into main

Author: slister1001

.github/scripts/build_agent_setup_bicep.py

@@ -1,3 +1,4 @@
+import os
 import sys
 from pathlib import Path
 from azure.cli.core import get_default_cli
@@ -26,6 +27,10 @@ def build_bicep_file(bicep_file: Path) -> None:
     output_file = bicep_file.with_name("azuredeploy.json")
 
     print(f"🔹 Building Bicep: {bicep_file} -> {output_file}")
+    os.environ.update({"AZURE_BICEP_USE_BINARY_FROM_PATH": "false", "AZURE_BICEP_CHECK_VERSION": "false"})
+
+    # Pin the bicep CLI to minimize pre-commit failures due to modified metadata in files.
+    run_az_command("bicep", "install", "--version", "v0.33.93")
 
     # Run az bicep build using Azure CLI SDK
     run_az_command("bicep", "build", "--file", str(bicep_file), "--outfile", str(output_file))

.pre-commit-config.yaml

@@ -43,11 +43,10 @@ repos:
     - id: bicep-build
       name: Regenerate azuredeploy.json for Agent samples
       description: "Automatically build Bicep files into azuredeploy.json before commit"
-      entry: python .github/scripts/build_agent_setup_bicep.py
       types: [text]
       files: ^scenarios/Agents/setup/.*\.bicep$
-      language: python
       require_serial: true
       pass_filenames: true
-      additional_dependencies:
-      - azure-cli
+      entry: python
+      language: system
+      args: ["-m", "tox", "-qqq", "run", "-e", "build-agent-bicep", "--"]

pyproject.toml

@@ -18,9 +18,6 @@ extend-select = [
   "ANN",
   "RUF",
 ]
-ignore = [
-  "ANN101", # missing-type-self: This can be inferred and will be deprecated by ruff
-]
 
 [tool.ruff.lint.extend-per-file-ignores]
 "*.ipynb" = [

scenarios/Agents/samples/file-search/FileSearch.cs

@@ -0,0 +1,101 @@
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+
+#nullable disable
+
+using System;
+using System.Collections.Generic;
+using System.IO;
+using System.Threading.Tasks;
+using Azure.Core.TestFramework;
+using NUnit.Framework;
+
+namespace Azure.AI.Projects.Tests;
+
+public partial class Sample_Agent_FileSearch : SamplesBase<AIProjectsTestEnvironment>
+{
+    [Test]
+    public async Task FilesSearchExample()
+    {
+        var connectionString = TestEnvironment.AzureAICONNECTIONSTRING;
+        AgentsClient client = new AgentsClient(connectionString, new DefaultAzureCredential());
+
+        #region Snippet:UploadAgentFilesToUse
+        // Upload a file and wait for it to be processed
+        File.WriteAllText(
+            path: "sample_file_for_upload.txt",
+            contents: "The word 'apple' uses the code 442345, while the word 'banana' uses the code 673457.");
+        Response<AgentFile> uploadAgentFileResponse = await client.UploadFileAsync(
+            filePath: "sample_file_for_upload.txt",
+            purpose: AgentFilePurpose.Agents);
+
+        AgentFile uploadedAgentFile = uploadAgentFileResponse.Value;
+        #endregion
+
+        #region Snippet:CreateVectorStore
+        // Create a vector store with the file and wait for it to be processed.
+        // If you do not specify a vector store, create_message will create a vector store with a default expiration policy of seven days after they were last active
+        VectorStore vectorStore = await client.CreateVectorStoreAsync(
+            fileIds:  new List<string> { uploadedAgentFile.Id },
+            name: "my_vector_store");
+        #endregion
+
+        #region Snippet:CreateAgentWithFiles
+        FileSearchToolResource fileSearchToolResource = new FileSearchToolResource();
+        fileSearchToolResource.VectorStoreIds.Add(vectorStore.Id);
+
+        // Create an agent with toolResources and process assistant run
+        Response<Agent> agentResponse = await client.CreateAgentAsync(
+                model: "gpt-4-1106-preview",
+                name: "SDK Test Agent - Retrieval",
+                instructions: "You are a helpful agent that can help fetch data from files you know about.",
+                tools: new List<ToolDefinition> { new FileSearchToolDefinition() },
+                toolResources: new ToolResources() { FileSearch = fileSearchToolResource });
+        Agent agent = agentResponse.Value;
+        #endregion
+
+        // Create thread for communication
+        Response<AgentThread> threadResponse = await client.CreateThreadAsync();
+        AgentThread thread = threadResponse.Value;
+
+        // Create message to thread
+        Response<ThreadMessage> messageResponse = await client.CreateMessageAsync(
+            thread.Id,
+            MessageRole.User,
+            "Can you give me the documented codes for 'banana' and 'orange'?");
+        ThreadMessage message = messageResponse.Value;
+
+        // Run the agent
+        Response<ThreadRun> runResponse = await client.CreateRunAsync(thread, agent);
+
+        do
+        {
+            await Task.Delay(TimeSpan.FromMilliseconds(500));
+            runResponse = await client.GetRunAsync(thread.Id, runResponse.Value.Id);
+        }
+        while (runResponse.Value.Status == RunStatus.Queued
+            || runResponse.Value.Status == RunStatus.InProgress);
+
+        Response<PageableList<ThreadMessage>> afterRunMessagesResponse
+            = await client.GetMessagesAsync(thread.Id);
+        IReadOnlyList<ThreadMessage> messages = afterRunMessagesResponse.Value.Data;
+
+        // Note: messages iterate from newest to oldest, with the messages[0] being the most recent
+        foreach (ThreadMessage threadMessage in messages)
+        {
+            Console.Write($"{threadMessage.CreatedAt:yyyy-MM-dd HH:mm:ss} - {threadMessage.Role,10}: ");
+            foreach (MessageContent contentItem in threadMessage.ContentItems)
+            {
+                if (contentItem is MessageTextContent textItem)
+                {
+                    Console.Write(textItem.Text);
+                }
+                else if (contentItem is MessageImageFileContent imageFileItem)
+                {
+                    Console.Write($"<image from ID: {imageFileItem.FileId}");
+                }
+                Console.WriteLine();
+            }
+        }
+    }
+}

scenarios/Agents/samples/file-search/python-file-search.py

@@ -0,0 +1,96 @@
+# ------------------------------------
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# ------------------------------------
+
+"""
+DESCRIPTION:
+    This sample demonstrates how to use agent operations with file searching from
+    the Azure Agents service using a synchronous client.
+
+USAGE:
+    python sample_agents_file_search.py
+
+    Before running the sample:
+
+    pip install azure-ai-projects azure-identity
+
+    Set these environment variables with your own values:
+    1) PROJECT_CONNECTION_STRING - The project connection string, as found in the overview page of your
+       Azure AI Foundry project.
+    2) MODEL_DEPLOYMENT_NAME - The deployment name of the AI model, as found under the "Name" column in 
+       the "Models + endpoints" tab in your Azure AI Foundry project.
+"""
+
+import os
+from azure.ai.projects import AIProjectClient
+from azure.ai.projects.models import (
+    FileSearchTool,
+)
+from azure.identity import DefaultAzureCredential
+
+
+project_client = AIProjectClient.from_connection_string(
+    credential=DefaultAzureCredential(), conn_str=os.environ["PROJECT_CONNECTION_STRING"]
+)
+
+with project_client:
+    # Upload file and create vector store
+    # [START upload_file_create_vector_store_and_agent_with_file_search_tool]
+    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-4o-mini",
+        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,
+    )
+    # [END upload_file_create_vector_store_and_agent_with_file_search_tool]
+
+    print(f"Created agent, ID: {agent.id}")
+
+    # Create thread for communication
+    thread = project_client.agents.create_thread()
+    print(f"Created thread, ID: {thread.id}")
+
+    # Create message to thread
+    message = project_client.agents.create_message(
+        thread_id=thread.id, role="user", content="Hello, what Contoso products do you know?"
+    )
+    print(f"Created message, ID: {message.id}")
+
+    # Create and process assistant run in thread with tools
+    run = project_client.agents.create_and_process_run(thread_id=thread.id, agent_id=agent.id)
+    print(f"Run finished with status: {run.status}")
+
+    if run.status == "failed":
+        # Check if you got "Rate limit is exceeded.", then you want to get more quota
+        print(f"Run failed: {run.last_error}")
+
+    # [START teardown]
+    # 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")
+    # [END teardown]
+
+    # Fetch and log all messages
+    messages = project_client.agents.list_messages(thread_id=thread.id)
+
+    # Print messages from the thread
+    for text_message in messages.text_messages:
+        print(text_message)

scenarios/Agents/samples/file-search/readme.md

@@ -0,0 +1,38 @@
+# File Search
+
+File Search augments the Agent with knowledge from outside its model, such as proprietary product information or documents provided by your users. 
+
+To access your files, the file search tool uses the vector store object. Upload your files and create a vector store to contain them. Once the vector store is created, you should poll its status until all files are out of the in_progress state to ensure that all content has finished processing. The SDK provides helpers for uploading and polling. 
+
+### File Sources  
+- Uploading local files
+- [Coming Soon] Azure Blob Storage
+
+### Basic Agent Setup <br> 
+The File Search tool has the same functionality as AOAI Assistants. Microsoft managed search and storage resources are used. 
+- Uploaded files get stored in Microsoft managed storage
+- A vector store is created using a Microsoft managed search resource
+
+### Standard Agent Setup 
+The File Search tool uses the Azure AI Search and Azure Blob Storage resources you connected during agent setup.  
+- Uploaded files get stored in your connected Azure Blob Storage account
+- Vector stores get created using your connected Azure AI Seach resource
+<br> </br>
+
+For both Agent setups, OpenAI handles the entire ingestion process, including automatically parsing and chunking documents, generating and storing embeddings, and utilizing both vector and keyword searches to retrieve relevant content for user queries. 
+
+There is no difference in the code between the two setups; the only variation is in where your files and created vector stores are stored.
+
+## Examples
+
+Run the code samples below and view the output. 
+
+>[!NOTE]
+> Be sure that you've [installed the SDK](../../quickstart.md#install-the-sdk-package) for your language.
+
+* [Python](./python-file-search.py)
+* [C#](./FileSearch.cs)
+
+## Additional samples
+
+* [Python Quart app](https://github.com/Azure-Samples/azureai-assistant-tool/tree/main/samples/FileSearch)

scenarios/Agents/samples/tracing/async/agents_basics_async_with_azure_monitor_tracing.py

@@ -0,0 +1,90 @@
+# ------------------------------------
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# ------------------------------------
+
+"""
+FILE: sample_agents_basics_async_with_azure_monitor_tracing.py
+
+DESCRIPTION:
+    This sample demonstrates how to use basic agent operations from
+    the Azure Agents service using a asynchronous client with Azure Monitor tracing.
+    View the results in the "Tracing" tab in your Azure AI Studio project page.
+
+USAGE:
+    python sample_agents_basics_async_with_azure_monitor_tracing.py
+
+    Before running the sample:
+
+    pip install azure-ai-projects azure-identity opentelemetry-sdk azure-monitor-opentelemetry
+
+    Set these environment variables with your own values:
+    * PROJECT_CONNECTION_STRING - The Azure AI Project connection string, as found in your AI Studio Project.
+    * AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED - Optional. Set to `true` to trace the content of chat
+      messages, which may contain personal data. False by default.
+"""
+import asyncio
+import time
+from azure.ai.projects.aio import AIProjectClient
+from azure.identity.aio import DefaultAzureCredential
+from opentelemetry import trace
+import os
+from azure.monitor.opentelemetry import configure_azure_monitor
+
+
+tracer = trace.get_tracer(__name__)
+
+
+@tracer.start_as_current_span(__file__)
+async def main() -> None:
+    # Create an Azure AI Project Client from a connection string, copied from your AI Studio project.
+    # At the moment, it should be in the format "<HostName>;<AzureSubscriptionId>;<ResourceGroup>;<HubName>"
+    # Customer needs to login to Azure subscription via Azure CLI and set the environment variables
+
+    project_client = AIProjectClient.from_connection_string(
+        credential=DefaultAzureCredential(), conn_str=os.environ["PROJECT_CONNECTION_STRING"]
+    )
+
+    # 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)
+
+    async with project_client:
+        agent = await project_client.agents.create_agent(
+            model="gpt-4o", name="my-assistant", instructions="You are helpful assistant"
+        )
+        print(f"Created agent, agent ID: {agent.id}")
+
+        thread = await project_client.agents.create_thread()
+        print(f"Created thread, thread ID: {thread.id}")
+
+        message = await project_client.agents.create_message(
+            thread_id=thread.id, role="user", content="Hello, tell me a joke"
+        )
+        print(f"Created message, message ID: {message.id}")
+
+        run = await 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 = await project_client.agents.get_run(thread_id=thread.id, run_id=run.id)
+
+            print(f"Run status: {run.status}")
+
+        print(f"Run completed with status: {run.status}")
+
+        await project_client.agents.delete_agent(agent.id)
+        print("Deleted agent")
+
+        messages = await project_client.agents.list_messages(thread_id=thread.id)
+        print(f"Messages: {messages}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())