Merge pull request #4549 from MicrosoftDocs/main

05/05/2025 PM Publishing

Author: v-alje

.openpublishing.publish.config.json

@@ -92,6 +92,12 @@
       "branch": "main",
       "branch_mapping": {}
     },
+    {
+      "path_to_root": "azure-functions-ai-services-agent-javascript",
+      "url": "https://github.com/Azure-Samples/azure-functions-ai-services-agent-javascript",
+      "branch": "main",
+      "branch_mapping": {}
+    },
     {
       "path_to_root": "samples-cognitive-services-speech-sdk",
       "url": "https://github.com/Azure-Samples/cognitive-services-speech-sdk",

articles/ai-services/agents/how-to/tools/azure-functions.md

@@ -6,7 +6,7 @@ services: azure-ai-agent-service
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 01/30/2025
+ms.date: 04/15/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
@@ -138,7 +138,9 @@ To use all features of function calling including parallel functions, you need t
 
 ## Define a function for your agent to call
 
-Start by defining an Azure Function queue trigger function that will process function calls from the queue. 
+Start by defining an Azure Function queue trigger function that will process AI function calls from the queue. 
+
+# [Python](#tab/python)
 
 ```python
 # Function to get the weather from an Azure Storage queue where the AI Agent will send function call information
@@ -172,12 +174,27 @@ def process_queue_message(msg: func.QueueMessage) -> None:
     logging.info(f"Sent message to output queue with message {result_message}")
 ```
 
+# [TypeScript](#tab/typescript)
+
+:::code language="TypeScript" source="~/azure-functions-ai-services-agent-javascript/app/src/functions/queueGetWeather.ts" :::
+
+# [REST API](#tab/rest)
+
+No REST equivalent provided.
+
+
+---
+
 
 ## Create an AI project client and agent
 
-In the sample below we create a client and an agent that has the tools definition for the Azure Function
+In the sample below we create a client and an agent that has the AI tools definition for the Azure Function. The term `function` is used in two contexts within the AI tool definition: 
+
+* Azure Function: the type of tool. This is the Azure Functions app.
+* Function: the Http trigger function `GetWeather` within the Azure Function to call when the tool is invoked in the AI Project. 
 
 # [Python](#tab/python)
+
 ```python
 # Initialize the client and create agent for the tools Azure Functions that the agent can use
 
@@ -231,7 +248,12 @@ agent = project_client.agents.create_agent(
 )
 ```
 
+# [TypeScript](#tab/typescript)
+
+:::code language="TypeScript" source="~/azure-functions-ai-services-agent-javascript/app/src/azureProjectInit.ts" id="CreateAgent" :::
+
 # [REST API](#tab/rest)
+
 Follow the [REST API Quickstart](../../quickstart.md?pivots=rest-api) to set the right values for the environment variables `AZURE_AI_AGENTS_TOKEN` and `AZURE_AI_AGENTS_ENDPOINT`. Then create the agent using:
 ```console
 curl $AZURE_AI_AGENTS_ENDPOINT/assistants?api-version=2024-12-01-preview \
@@ -276,6 +298,7 @@ curl $AZURE_AI_AGENTS_ENDPOINT/assistants?api-version=2024-12-01-preview \
   }'
 ```
 
+
 ---
 
 ## Create a thread for the agent
@@ -287,13 +310,18 @@ thread = project_client.agents.create_thread()
 print(f"Created thread, thread ID: {thread.id}")
 ```
 
+# [TypeScript](#tab/typescript)
+
+:::code language="TypeScript" source="~/azure-functions-ai-services-agent-javascript/app/src/azureProjectInit.ts" id="CreateThread" :::
+
 # [REST API](#tab/rest)
 ```console
 curl $AZURE_AI_AGENTS_ENDPOINT/threads?api-version=2024-12-01-preview \
   -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
   -H "Content-Type: application/json" \
   -d ''
 ```
+
 ---
 
 ## Create a run and check the output
@@ -320,6 +348,11 @@ while run.status in ["queued", "in_progress", "requires_action"]:
 
 print(f"Run finished with status: {run.status}")
 ```
+
+# [TypeScript](#tab/typescript)
+
+:::code language="TypeScript" source="~/azure-functions-ai-services-agent-javascript/app/src/functions/httpPrompt.ts" id="CreateMessage" :::
+
 # [REST API](#tab/rest)
 ```console
 curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/messages?api-version=2024-12-01-preview \
@@ -364,10 +397,34 @@ project_client.agents.delete_agent(agent.id)
 print("Deleted agent")
 ```
 
+# [TypeScript](#tab/typescript)
+
+:::code language="TypeScript" source="~/azure-functions-ai-services-agent-javascript/app/src/functions/httpPrompt.ts" id="ListMessages" :::
+
 # [REST API](#tab/rest)
 ```console
 curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/messages?api-version=2024-12-01-preview \
   -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN"
 ```
 
+---
+
+## Troubleshooting
+
+# [Python](#tab/python)
+
+For any issues with the Python code, create an issue on the [sample code repository](https://github.com/Azure-Samples/azure-functions-ai-services-agent-python/issues)
+
+# [TypeScript](#tab/typescript)
+
+For any issues with the TypeScript code, create an issue on the [sample code repository](https://github.com/Azure-Samples/azure-functions-ai-services-agent-javascript/issues)
+
+# [REST API](#tab/rest)
+
+No REST equivalent provided.
+
+---
+
 ::: zone-end
+
+

articles/ai-services/agents/how-to/virtual-networks.md

@@ -113,11 +113,11 @@ Azure AI Agent Service offers a standard agent configuration with private networ
 
 | Template | Description   | Autodeploy |
 | ------------------- | -----------------------------------------------| -----------------------|
-| `network-secured-agent.bicep`  | Deploy a network secured agent setup that uses user-managed identity authentication on the Agent connections. | [![Deploy to Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2FAzure-Samples%2Fazureai-samples%2Fmain%2Fscenarios%2FAgents%2Fsetup%2Fnetwork-secured-agent%2Fazuredeploy.json)
+| `network-secured-agent.bicep`  | Deploy a network secured agent setup that uses user-managed identity authentication on the Agent connections. | [![Deploy to Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2FAzure-Samples%2Fazureai-samples%2Fmain%2Fscenarios%2FAgents%2Fsetup%2Fnetwork-secured-agent-thread-storage%2Fazuredeploy.json)
 
 ### Option 2: manually deploy the bicep template
 
-1. To manually run the bicep templates, [download the template from GitHub](https://github.com/Azure-Samples/azureai-samples/tree/main/scenarios/Agents/setup/network-secured-agent). Download the following from the `network-secured-agent` folder:
+1. To manually run the bicep templates, [download the template from GitHub](https://github.com/Azure-Samples/azureai-samples/tree/main/scenarios/Agents/setup/network-secured-agent-thread-storage). Download the following from the `network-secured-agent` folder:
     1. `main.bicep`
     1. `azuredeploy.parameters.json`
     1. `modules-network-secured folder`

articles/ai-services/computer-vision/index.yml

@@ -32,27 +32,6 @@ highlightedContent:
 
 conceptualContent:
   items:
-    - title: Optical character recognition
-      links:
-        - itemType: overview
-          text: About OCR
-          url: overview-ocr.md
-        - itemType: quickstart
-          text: Get started with OCR
-          url: quickstarts-sdk/client-library.md
-        - itemType: how-to-guide
-          text: Call the Read API
-          url: how-to/call-read-api.md
-        - itemType: deploy
-          text: Use the Read OCR container
-          url: computer-vision-how-to-install-containers.md
-        - itemType: learn
-          text: Microsoft Learn training
-          url: /training/modules/read-text-images-documents-with-computer-vision-service/
-        - itemType: reference
-          text: OCR API reference
-          url: /rest/api/computervision/recognize-printed-text?view=rest-computervision-v3.2
-
     - title: Image Analysis
       links:
         - itemType: overview
@@ -119,6 +98,27 @@ conceptualContent:
         - itemType: how-to-guide
           text: Call the Video Retrieval APIs
           url: how-to/video-retrieval.md
+    - title: Optical character recognition (legacy)
+      links:
+        - itemType: overview
+          text: About OCR
+          url: overview-ocr.md
+        - itemType: quickstart
+          text: Get started with OCR
+          url: quickstarts-sdk/client-library.md
+        - itemType: how-to-guide
+          text: Call the Read API
+          url: how-to/call-read-api.md
+        - itemType: deploy
+          text: Use the Read OCR container
+          url: computer-vision-how-to-install-containers.md
+        - itemType: learn
+          text: Microsoft Learn training
+          url: /training/modules/read-text-images-documents-with-computer-vision-service/
+        - itemType: reference
+          text: OCR API reference
+          url: /rest/api/computervision/recognize-printed-text?view=rest-computervision-v3.2
+
 
 tools:
   title: Software development kits (SDKs)

articles/ai-services/computer-vision/overview-ocr.md

@@ -16,6 +16,12 @@ ms.custom: devx-track-csharp
 
 # OCR - Optical Character Recognition
 
+> [!WARNING]
+> This service, including the Azure AI Vision legacy [OCR API in v3.2](/rest/api/computervision/recognize-printed-text?view=rest-computervision-v3.2) and [RecognizeText API in v2.1](/rest/api/computervision/recognize-printed-text/recognize-printed-text?view=rest-computervision-v2.1), is not recommended for use.
+
+[!INCLUDE [read-editions](includes/read-editions.md)]
+
+
 OCR or Optical Character Recognition is also referred to as text recognition or text extraction. Machine-learning-based OCR techniques allow you to extract printed or handwritten text from images such as posters, street signs and product labels, as well as from documents like articles, reports, forms, and invoices. The text is typically extracted as words, text lines, and paragraphs or text blocks, enabling access to digital version of the scanned text. This eliminates or significantly reduces the need for manual data entry.
 
 
@@ -24,10 +30,8 @@ OCR or Optical Character Recognition is also referred to as text recognition or
 
 Microsoft's **Read** OCR engine is composed of multiple advanced machine-learning based models supporting [global languages](./language-support.md). It can extract printed and handwritten text including mixed languages and writing styles. **Read** is available as cloud service and on-premises container for deployment flexibility. It's also available as a synchronous API for single, non-document, image-only scenarios with performance enhancements that make it easier to implement OCR-assisted user experiences.
 
-> [!WARNING]
-> The Azure AI Vision legacy [OCR API in v3.2](/rest/api/computervision/recognize-printed-text?view=rest-computervision-v3.2) and [RecognizeText API in v2.1](/rest/api/computervision/recognize-printed-text/recognize-printed-text?view=rest-computervision-v2.1) operations are not recommended for use.
 
-[!INCLUDE [read-editions](includes/read-editions.md)]
+
 
 ## How is OCR related to Intelligent Document Processing (IDP)?