Merge pull request #6389 from MicrosoftDocs/main

Auto Publish – main to live - 2025-08-05 17:05 UTC

Author: learn-build-service-prod[bot]

.openpublishing.redirection.json

@@ -6,6 +6,11 @@
       "redirect_document_id": false
     },
     {
+      "source_path": "articles/ai-foundry/how-to/develop/vscode.md",
+      "redirect_url": "/azure/ai-foundry/how-to/develop/get-started-projects-vs-code",
+      "redirect_document_id": false
+    },
+        {
       "source_path": "articles/ai-foundry/azure-openai-in-azure-ai-foundry.md",
       "redirect_url": "/azure/ai-foundry/what-is-azure-ai-foundry",
       "redirect_document_id": false

articles/ai-foundry/agents/how-to/connected-agents.md

@@ -275,11 +275,11 @@ To create a multi-agent setup, follow these steps:
 1. Create a thread and add a message to it.
 
     ```python
-    thread = project_client.agents.create_thread()
+    thread = project_client.agents.threads.create()
     print(f"Created thread, ID: {thread.id}")
 
     # Create message to thread
-    message = project_client.agents.create_message(
+    message = project_client.agents.messages.create(
         thread_id=thread.id,
         role=MessageRole.USER,
         content="What is the stock price of Microsoft?",
@@ -293,7 +293,7 @@ To create a multi-agent setup, follow these steps:
     ```python
 
     # Create and process Agent run in thread with tools
-    run = project_client.agents.create_and_process_run(thread_id=thread.id, agent_id=agent.id)
+    run = project_client.agents.runs.create_and_process(thread_id=thread.id, agent_id=agent.id)
     print(f"Run finished with status: {run.status}")
 
     if run.status == "failed":
@@ -312,7 +312,7 @@ To create a multi-agent setup, follow these steps:
 
     ```python
     # Print the Agent's response message with optional citation
-    response_message = project_client.agents.list_messages(thread_id=thread.id).get_last_message_by_role(
+    response_message = project_client.agents.messages.list(thread_id=thread.id).get_last_message_by_role(
         MessageRole.AGENT
     )
     if response_message:

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

@@ -89,7 +89,7 @@ When you add the Grounding with Bing Search tool to your agent, you can pass the
 According to Grounding with Bing's [terms of use and use and display requirements](https://www.microsoft.com/en-us/bing/apis/grounding-legal#use-and-display-requirements), you need to display both website URLs and Bing search query URLs in your custom interface. You can find website URLs through `annotations` parameter in API response and Bing search query URLs through `runstep` details. To render the webpage, we recommend you replace the endpoint of Bing search query URLs with `www.bing.com` and your Bing search query URL would look like "https://www.bing.com/search?q={search query}"
 
 ```python
-run_steps = project_client.agents.list_run_steps(run_id=run.id, thread_id=thread.id)
+run_steps = project_client.agents.runs_steps.list(run_id=run.id, thread_id=thread.id)
 run_steps_data = run_steps['data']
 print(f"Last run step detail: {run_steps_data}")
 ```

articles/ai-foundry/agents/how-to/tools/code-interpreter-samples.md

@@ -66,7 +66,7 @@ project_client = AIProjectClient(
 The sample uploads a data file for analysis:
 
 ```python
-file = project_client.agents.upload_file_and_poll(
+file = project_client.agents.files.upload_and_poll(
     file_path="nifty_500_quarterly_results.csv", 
     purpose=FilePurpose.AGENTS
 )
@@ -122,7 +122,7 @@ messages = project_client.agents.messages.list(thread_id=thread.id)
 for image_content in messages.image_contents:
     file_id = image_content.image_file.file_id
     file_name = f"{file_id}_image_file.png"
-    project_client.agents.save_file(file_id=file_id, file_name=file_name)
+    project_client.agents.files.save(file_id=file_id, file_name=file_name)
 
 # Process file path annotations
 for file_path_annotation in messages.file_path_annotations:
@@ -136,7 +136,7 @@ for file_path_annotation in messages.file_path_annotations:
 After completing the interaction, the code properly cleans up resources:
 
 ```python
-project_client.agents.delete_file(file.id)
+project_client.agents.files.delete(file.id)
 project_client.agents.delete_agent(agent.id)
 ```
 

articles/ai-foundry/agents/how-to/tools/file-search-upload-files.md

@@ -136,7 +136,7 @@ if run.status == "failed":
 project_client.agents.vector_stores.delete(vector_store.id)
 print("Deleted vector store")
 
-project_client.agents.delete_file(file_id=file.id)
+project_client.agents.files.delete(file_id=file.id)
 print("Deleted file")
 
 project_client.agents.delete_agent(agent.id)

articles/ai-foundry/agents/how-to/tools/file-search.md

@@ -98,11 +98,11 @@ Files can also be added to a vector store after it's created by creating vector
 ```python
 
 # create a vector store with no file and wait for it to be processed
-vector_store = project_client.agents.create_vector_store_and_poll(data_sources=[], name="sample_vector_store")
+vector_store = project_client.agents.vector_stores.create_and_poll(data_sources=[], name="sample_vector_store")
 print(f"Created vector store, vector store ID: {vector_store.id}")
 
 # add the file to the vector store or you can supply file ids in the vector store creation
-vector_store_file_batch = project_client.agents.create_vector_store_file_batch_and_poll(
+vector_store_file_batch = project_client.agents.vector_store_file_batches.create_and_poll(
     vector_store_id=vector_store.id, file_ids=[file.id]
 )
 print(f"Created vector store file batch, vector store file batch ID: {vector_store_file_batch.id}")
@@ -112,7 +112,7 @@ print(f"Created vector store file batch, vector store file batch ID: {vector_sto
 Alternatively, you can add several files to a vector store by creating batches of up to 500 files.
 
 ```python
-batch = project_client.agents.create_vector_store_file_batch_and_poll(
+batch = project_client.agents.vector_store_file_batches.create_and_poll(
   vector_store_id=vector_store.id,
   file_ids=[file_1.id, file_2.id, file_3.id, file_4.id, file_5.id]
 )
@@ -144,7 +144,7 @@ print(f"Updated agent, agent ID: {agent.id}")
 
 ## Deleting vector stores
 ```python
-project_client.agents.delete_vector_store(vector_store.id)
+project_client.agents.vector_stores.delete(vector_store.id)
 print("Deleted vector store")
 ```
 
@@ -155,7 +155,7 @@ For basic agent setup, the `file_search` tool uses the `vector_stores`  object a
 To help you manage the costs associated with these vector_store objects, we added support for expiration policies in the `vector_store` object. You can set these policies when creating or updating the `vector_store` object.
 
 ```python
-vector_store = project_client.agents.create_vector_store_and_poll(
+vector_store = project_client.agents.vector_stores.create_and_poll(
   name="Product Documentation",
   file_ids=[file_1.id],
   expires_after={

articles/ai-foundry/agents/how-to/tools/model-context-protocol-samples.md

@@ -139,7 +139,7 @@ Create the run, check the output, and examine what tools were called during the
 
 ## Perform cleanup
 
-After the interaction is complete, the script performs cleanup by deleting the created agent resource via `agents_client.delete_agent()` to avoid leaving unused resources. It also fetches and prints the entire message history from the thread by using `agents_client.list_messages()` for review or logging.
+After the interaction is complete, the script performs cleanup by deleting the created agent resource via `agents_client.delete_agent()` to avoid leaving unused resources. It also fetches and prints the entire message history from the thread by using `agents_client.messages.list()` for review or logging.
 
 ```python
         # Delete the agent resource to clean up

articles/ai-foundry/agents/how-to/tools/openapi-spec-samples.md

@@ -155,7 +155,7 @@ Create the run, check the output, and examine what tools were called during the
 
 
 ## Cleanup
-After the interaction is complete, the script performs cleanup by deleting the created agent resource using `agents_client.delete_agent()` to avoid leaving unused resources. It also fetches and prints the entire message history from the thread using `agents_client.list_messages()` for review or logging.
+After the interaction is complete, the script performs cleanup by deleting the created agent resource using `agents_client.delete_agent()` to avoid leaving unused resources. It also fetches and prints the entire message history from the thread using `agents_client.messages.list()` for review or logging.
 
 ```python
         # Delete the agent resource to clean up

articles/ai-foundry/concepts/retrieval-augmented-generation.md

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: concept-article
-ms.date: 06/09/2025
+ms.date: 08/05/2025
 ms.reviewer: sgilley
 ms.author: sgilley
 author: sdgilley

articles/ai-foundry/foundry-local/get-started.md

@@ -70,10 +70,22 @@ Get started with Foundry Local quickly:
     You should see a response from the model in the terminal:
     :::image type="content" source="media/get-started-output.png" alt-text="Screenshot of output from foundry local run command." lightbox="media/get-started-output.png":::
 
-
 > [!TIP]
 > You can replace `phi-3.5-mini` with any model name from the catalog (see `foundry model list` for available models). Foundry Local downloads the model variant that best matches your system's hardware and software configuration. For example, if you have an NVIDIA GPU, it downloads the CUDA version of the model. If you have a Qualcomm NPU, it downloads the NPU variant. If you have no GPU or NPU, it downloads the CPU version.
 
+## Run the latest OpenAI open-source model
+
+To run the latest OpenAI open-source model - `GPT-OSS-20B` - use the following command:
+
+```bash
+foundry model run gpt-oss-20b
+```
+
+> [!IMPORTANT]
+> Requirements for running GPT-OSS-20B:
+> - Nvidia GPU with 16GB VRAM or more.
+> - Foundry Local version 0.6.0 or above.
+
 ## Explore commands
 
 The Foundry CLI organizes commands into these main categories: