Add REST API quickstart and documentation for Azure Ai Agents

Author: vangarp

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

@@ -34,9 +34,9 @@ Use an existing Azure AI Search index with the agent's Azure AI Search tool.
 
 ## Usage support
 
-|Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | Basic agent setup | Standard agent setup |
-|---------|---------|---------|---------|---------|---------|
-| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+|Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | REST API | Basic agent setup | Standard agent setup |
+|---------|---------|---------|---------|---------|---------|---------|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
 
 [!INCLUDE [setup](../../includes/azure-search/setup.md)]
 

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

@@ -37,9 +37,9 @@ You can find the template and code used here on [GitHub](https://github.com/Azur
 
 ## Usage support
 
-|Azure AI foundry support  | Python SDK |	C# SDK | Basic agent setup | Standard agent setup |
-|---------|---------|---------|---------|---------|
-|  | ✔️ |  | | ✔️ |
+|Azure AI foundry support  | Python SDK |	C# SDK | REST API | Basic agent setup | Standard agent setup |
+|---------|---------|---------|---------|---------|---------|
+|  | ✔️ |  | ✔️ | | ✔️ |
 
 ### Create Azure resources for local and cloud dev-test
 
@@ -177,6 +177,7 @@ def process_queue_message(msg: func.QueueMessage) -> None:
 
 In the sample below we create a client and an agent that has the tools definition for the Azure Function
 
+# [Python](#tab/python)
 ```python
 # Initialize the client and create agent for the tools Azure Functions that the agent can use
 
@@ -230,16 +231,73 @@ agent = project_client.agents.create_agent(
 )
 ```
 
+# [REST API](#tab/rest)
+Follow the [REST API Quickstart](../quickstart-rest.md) to set the right values for the environment variables `AZURE_AI_AGENTS_TOKEN` and `AZURE_AI_AGENTS_ENDPOINT`. The create the agent using:
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/assistants?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "instructions": "You are a helpful support agent. Answer the user's questions to the best of your ability.",
+    "name": "azure-function-agent-get-weather",
+    "model": "gpt-4o-mini",
+    "tools": [
+      { 
+        "type": "azure_function",
+        "azure_function": {
+            "function": {
+                "name": "GetWeather",
+                "description": "Get the weather in a location.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {"type": "string", "description": "The location to look up."}
+                    },
+                    "required": ["location"]
+                }
+            },
+            "input_binding": {
+                "type": "storage_queue",
+                "storage_queue": {
+                    "queue_service_uri": storage_connection_string,
+                    "queue_name": "input"
+                }
+            },
+            "output_binding": {
+                "type": "storage_queue",
+                "storage_queue": {
+                    "queue_service_uri": storage_connection_string,
+                    "queue_name": "output"
+                }
+            }
+        }
+      }
+    ]
+  }'
+```
+
+---
+
 ## Create a thread for the agent
 
+# [Python](#tab/python)
 ```python
 # Create a thread
 thread = project_client.agents.create_thread()
 print(f"Created thread, thread ID: {thread.id}")
 ```
 
+# [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
 
+# [Python](#tab/python)
 ```python
 # Send the prompt to the agent
 message = project_client.agents.create_message(
@@ -261,9 +319,34 @@ while run.status in ["queued", "in_progress", "requires_action"]:
 
 print(f"Run finished with status: {run.status}")
 ```
+# [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" \
+  -H "Content-Type: application/json" \
+  -d '{
+      "role": "user",
+      "content": "What is the weather in Seattle, WA?"
+    }'
+```
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/runs \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "assistant_id": "asst_abc123",
+  }'
+```
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/runs/run_abc123 \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN"
+```
 
 ### Get the result of the run
 
+# [Python](#tab/python)
 ```python
 # Get messages from the assistant thread
 messages = project_client.agents.get_messages(thread_id=thread.id)
@@ -279,4 +362,10 @@ project_client.agents.delete_agent(agent.id)
 print("Deleted agent")
 ```
 
+# [REST API](#tab/rest)
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/messages \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN"
+```
+
 ::: zone-end

articles/ai-services/agents/how-to/tools/bing-grounding.md

@@ -30,9 +30,9 @@ Developers and end users don't have access to raw content returned from Groundin
 
 ## Usage support
 
-|Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK |Basic agent setup | Standard agent setup |
-|---------|---------|---------|---------|---------|---------|
-| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+|Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | REST API |Basic agent setup | Standard agent setup |
+|---------|---------|---------|---------|---------|---------|---------|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
 
 ## Setup  
 
@@ -97,7 +97,7 @@ Your use of Grounding with Bing Search will be governed by the Terms of Use. By
 
 ::: zone pivot="code-example"
 
-## Step 1: Create an agent with Grounding with Bing Search
+## Step 1: Create a project client
 
 Create a client object, which will contain the connection string for connecting to your AI project and other resources.
 
@@ -155,9 +155,12 @@ const client = AIProjectsClient.fromConnectionString(
 );
 ```
 
+# [REST API](#tab/rest)
+Follow the [REST API Quickstart](../quickstart-rest.md) to set the right values for the environment variables `AZURE_AI_AGENTS_TOKEN` and `AZURE_AI_AGENTS_ENDPOINT`.
+
 ---
 
-## Step 2: Enable the Grounding with Bing search tool
+## Step 2: Create an Agent with the Grounding with Bing search tool enabled
 
 To make the Grounding with Bing search tool available to your agent, use a connection to initialize the tool and attach it to the agent. You can find your connection in the **connected resources** section of your project in the Azure AI Foundry portal.
 
@@ -224,6 +227,30 @@ const agent = await client.agents.createAgent("gpt-4o", {
 console.log(`Created agent, agent ID : ${agent.id}`);
 ```
 
+# [REST API](#tab/rest)
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/assistants?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+        "instructions": "You are a helpful agent.",
+        "name": "my-agent",
+        "model": "gpt-4o",
+        "tools": [
+          {
+            "type": "bing_grounding",
+            "bing_grounding": {
+                "connections": [
+                    {
+                        "connection_id": "/subscriptions/<your-subscription-id>/resourceGroups/<your-resource-group>/providers/Microsoft.MachineLearningServices/workspaces/<your-project-name>/connections/<your-bing-connection-name>"
+                    }
+                ]
+            }
+          }
+        ]
+      }'
+```
+
 ---
 
 
@@ -274,6 +301,28 @@ await client.agents.createMessage(
 });
 ```
 
+# [REST API](#tab/rest)
+### Create a thread
+
+```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 ''
+```
+
+### Add a user question to the thread
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/messages?api-version=2024-12-01-preview \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+      "role": "user",
+      "content": "What is the weather in Seattle?"
+    }'
+```
+
 ---
 
 ## Step 4: Create a run and check the output
@@ -390,6 +439,32 @@ foreach (ThreadMessage threadMessage in messages)
   }
 ```
 
+# [REST API](#tab/rest)
+### Run the thread
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/runs \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "assistant_id": "asst_abc123",
+  }'
+```
+
+### Retrieve the status of the run
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/runs/run_abc123 \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN"
+```
+
+### Retrieve the agent response
+
+```console
+curl $AZURE_AI_AGENTS_ENDPOINT/threads/thread_abc123/messages \
+  -H "Authorization: Bearer $AZURE_AI_AGENTS_TOKEN"
+```
+
 ---
 
 ::: zone-end