Python: Introduce the OpenAI Responses Agent

python/pyproject.toml

@@ -34,7 +34,7 @@ dependencies = [
     "numpy >= 1.25.0; python_version < '3.12'",
     "numpy >= 1.26.0; python_version >= '3.12'",
     # openai connector
-    "openai ~= 1.61",
+    "openai >= 1.67",
     # openapi and swagger
     "openapi_core >= 0.18,<0.20",
     "websockets >= 13, < 16",

python/samples/concepts/README.md

@@ -59,6 +59,15 @@
 - [OpenAI Assistant Templating Streaming](./agents/openai_assistant/openai_assistant_templating_streaming.py)
 - [OpenAI Assistant Vision Streaming](./agents/openai_assistant/openai_assistant_vision_streaming.py)
 
+#### [OpenAI Responses Agent](../../semantic_kernel/agents/open_ai/openai_responses_agent.py)
+
+- [OpenAI Responses Message Callback Streaming](./agents/openai_responses/responses_agent_message_callback_streaming.py)
+- [OpenAI Responses Message Callback](./agents/openai_responses/responses_agent_message_callback.py)
+- [OpenAI Responses File Search Streaming](./agents/openai_responses/responses_agent_file_search_streaming.py)
+- [OpenAI Responses Plugins Streaming](./agents/openai_responses/responses_agent_plugins_streaming.py)
+- [OpenAI Responses Reuse Existing Thread ID](./agents/openai_responses/responses_agent_reuse_existing_thread_id.py)
+- [OpenAI Responses Web Search Streaming](./agents/openai_responses/responses_agent_web_search_streaming.py)
+
 ### Audio - Using services that support audio-to-text and text-to-audio conversion
 
 - [Chat with Audio Input](./audio/01-chat_with_audio_input.py)
@@ -157,6 +166,7 @@
 
 - [Cycles with Fan-In](./processes/cycles_with_fan_in.py)
 - [Nested Process](./processes/nested_process.py)
+- [Plan and Execute](./processes/plan_and_execute.py)
 
 ### PromptTemplates - Using [`Templates`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/prompt_template/prompt_template_base.py) with parametrization for `Prompt` rendering
 

python/samples/concepts/agents/README.md

@@ -10,6 +10,7 @@ This project contains a step by step guide to get started with _Semantic Kernel
 - For the use of Streaming OpenAI Assistant agents, the minimum allowed Semantic Kernel pypi version is 1.11.0.
 - For the use of AzureAI and Bedrock agents, the minimum allowed Semantic Kernel pypi version is 1.21.0.
 - For the use of Crew.AI as a plugin, the minimum allowed Semantic Kernel pypi version is 1.21.1.
+- For the use of OpenAI Responses agents, the minimum allowed Semantic Kernel pypi version is 1.27.0.
 
 
 ## Source
@@ -28,6 +29,7 @@ chat_completion_agent|How to use Semantic Kernel Chat Completion agents that lev
 bedrock|How to use [AWS Bedrock agents](https://aws.amazon.com/bedrock/agents/) in Semantic Kernel.
 mixed_chat|How to combine different agent types.
 openai_assistant|How to use [OpenAI Assistants](https://platform.openai.com/docs/assistants/overview) in Semantic Kernel.
+openai_responses|How to use [OpenAI Responses](https://platform.openai.com/docs/api-reference/responses) in Semantic Kernel.
 
 ## Configuring the Kernel
 
@@ -57,6 +59,9 @@ You can explicitly create a specific implementation for the desired `Agent` that
 Below is a sample code snippet demonstrating thread management:
 
 ```python
+from semantic_kernel.agents import ChatCompletionAgent
+from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
+
 USER_INPUTS = [
     "Why is the sky blue?",
 ]
@@ -71,7 +76,7 @@ agent = ChatCompletionAgent(
 # 2. Create a thread to hold the conversation
 # If no thread is provided, a new thread will be
 # created and returned with the initial response
-thread: ChatCompletionAgentThread = None
+thread = None
 
 for user_input in USER_INPUTS:
     print(f"# User: {user_input}")

python/samples/concepts/agents/openai_responses/responses_agent_file_search_streaming.py

@@ -0,0 +1,94 @@
+# Copyright (c) Microsoft. All rights reserved.
+import asyncio
+import os
+
+from semantic_kernel.agents import OpenAIResponsesAgent
+from semantic_kernel.contents.streaming_chat_message_content import StreamingChatMessageContent
+
+"""
+The following sample demonstrates how to create an OpenAI Responses Agent.
+The sample shows how to have the agent answer questions about the provided
+document with streaming responses.
+
+The interaction with the agent is via the `get_response` method, which sends a
+user input to the agent and receives a response from the agent. The conversation
+history is maintained by the agent service, i.e. the responses are automatically
+associated with the thread. Therefore, client code does not need to maintain the
+conversation history.
+"""
+
+
+# Simulate a conversation with the agent
+USER_INPUTS = [
+    "By birthday, who is the youngest employee?",
+    "Who works in sales?",
+    "I have a customer request, who can help me?",
+]
+
+
+async def main():
+    # 1. Create the client using OpenAI resources and configuration
+    client, model = OpenAIResponsesAgent.setup_resources()
+
+    pdf_file_path = os.path.join(
+        os.path.dirname(os.path.dirname(os.path.realpath(__file__))), "resources", "employees.pdf"
+    )
+
+    with open(pdf_file_path, "rb") as file:
+        file = await client.files.create(file=file, purpose="assistants")
+
+    vector_store = await client.vector_stores.create(
+        name="step4_assistant_file_search",
+        file_ids=[file.id],
+    )
+
+    file_search_tool = OpenAIResponsesAgent.configure_file_search_tool(vector_store.id)
+
+    # 2. Create a Semantic Kernel agent for the OpenAI Responses API
+    agent = OpenAIResponsesAgent(
+        ai_model_id=model,
+        client=client,
+        instructions="Find answers to the user's questions in the provided file.",
+        name="FileSearch",
+        tools=[file_search_tool],
+    )
+
+    # 3. Create a thread for the agent
+    # If no thread is provided, a new thread will be
+    # created and returned with the initial response
+    thread = None
+
+    response_chunks: list[StreamingChatMessageContent] = []
+    for user_input in USER_INPUTS:
+        print(f"# User: '{user_input}'")
+        # 4. Invoke the agent for the current message and print the response
+        first_chunk = True
+        async for response in agent.invoke_stream(messages=user_input, thread=thread):
+            thread = response.thread
+            response_chunks.append(response)
+            if first_chunk:
+                print(f"# {response.name}: ", end="", flush=True)
+                first_chunk = False
+            print(response.content, end="", flush=True)
+        print()
+
+    """
+    # User: 'By birthday, who is the youngest employee?'
+    # Agent: The youngest employee by birthday is Teodor Britton, born on January 9, 1997.
+    # User: 'Who works in sales?'
+    # Agent: The employees who work in sales are:
+
+    - Mariam Jaslyn, Sales Representative
+    - Hicran Bea, Sales Manager
+    - Angelino Embla, Sales Representative.
+    # User: 'I have a customer request, who can help me?'
+    # Agent: For a customer request, you could reach out to the following people in the sales department:
+
+    - Mariam Jaslyn, Sales Representative
+    - Hicran Bea, Sales Manager
+    - Angelino Embla, Sales Representative.
+     """
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

python/samples/concepts/agents/openai_responses/responses_agent_message_callback.py

@@ -0,0 +1,130 @@
+# Copyright (c) Microsoft. All rights reserved.
+import asyncio
+from typing import Annotated
+
+from semantic_kernel.agents import AzureResponsesAgent
+from semantic_kernel.contents import AuthorRole, FunctionCallContent, FunctionResultContent
+from semantic_kernel.contents.chat_message_content import ChatMessageContent
+from semantic_kernel.functions import kernel_function
+
+"""
+The following sample demonstrates how to create an OpenAI
+Responses Agent using either Azure OpenAI or OpenAI. The 
+Responses Agent allow for function calling, the use of file search and a
+web search tool. Responses Agent Threads are used to manage the
+conversation state, similar to a Semantic Kernel Chat History.
+Additionally, the invoke configures a message callback 
+to receive the conversation messages during invocation.
+"""
+
+
+# Define a sample plugin for the sample
+class MenuPlugin:
+    """A sample Menu Plugin used for the concept sample."""
+
+    @kernel_function(description="Provides a list of specials from the menu.")
+    def get_specials(self) -> Annotated[str, "Returns the specials from the menu."]:
+        return """
+        Special Soup: Clam Chowder
+        Special Salad: Cobb Salad
+        Special Drink: Chai Tea
+        """
+
+    @kernel_function(description="Provides the price of the requested menu item.")
+    def get_item_price(
+        self, menu_item: Annotated[str, "The name of the menu item."]
+    ) -> Annotated[str, "Returns the price of the menu item."]:
+        return "$9.99"
+
+
+intermediate_steps: list[ChatMessageContent] = []
+
+
+async def handle_intermediate_steps(message: ChatMessageContent) -> None:
+    intermediate_steps.append(message)
+
+
+async def main():
+    # 1. Create the client using Azure OpenAI resources and configuration
+    client, model = AzureResponsesAgent.setup_resources()
+
+    # 2. Create a Semantic Kernel agent for the OpenAI Responses API
+    agent = AzureResponsesAgent(
+        ai_model_id=model,
+        client=client,
+        name="Host",
+        instructions="Answer questions about the menu.",
+        plugins=[MenuPlugin()],
+    )
+
+    # 3. Create a thread for the agent
+    # If no thread is provided, a new thread will be
+    # created and returned with the initial response
+    thread = None
+
+    user_inputs = ["Hello", "What is the special soup?", "What is the special drink?", "How much is that?", "Thank you"]
+
+    try:
+        for user_input in user_inputs:
+            print(f"# {AuthorRole.USER}: '{user_input}'")
+            async for response in agent.invoke(
+                messages=user_input,
+                thread=thread,
+                on_intermediate_message=handle_intermediate_steps,
+            ):
+                thread = response.thread
+                print(f"# {response.name}: {response.content}")
+    finally:
+        await thread.delete() if thread else None
+
+    # Print the final chat history
+    print("\nIntermediate Steps:")
+    for msg in intermediate_steps:
+        if any(isinstance(item, FunctionResultContent) for item in msg.items):
+            for fr in msg.items:
+                if isinstance(fr, FunctionResultContent):
+                    print(f"Function Result:> {fr.result} for function: {fr.name}")
+        elif any(isinstance(item, FunctionCallContent) for item in msg.items):
+            for fcc in msg.items:
+                if isinstance(fcc, FunctionCallContent):
+                    print(f"Function Call:> {fcc.name} with arguments: {fcc.arguments}")
+        else:
+            print(f"{msg.role}: {msg.content}")
+
+    """
+    Sample Output:
+
+    # AuthorRole.USER: 'Hello'
+    # Host: Hi there! How can I assist you with the menu today?
+    # AuthorRole.USER: 'What is the special soup?'
+    # Host: The special soup is Clam Chowder.
+    # AuthorRole.USER: 'What is the special drink?'
+    # Host: The special drink is Chai Tea.
+    # AuthorRole.USER: 'How much is that?'
+    # Host: Could you please specify the menu item you are asking about?
+    # AuthorRole.USER: 'Thank you'
+    # Host: You're welcome! If you have any questions about the menu or need assistance, feel free to ask.
+
+    Intermediate Steps:
+    AuthorRole.ASSISTANT: Hi there! How can I assist you with the menu today?
+    AuthorRole.ASSISTANT: 
+    Function Result:> 
+            Special Soup: Clam Chowder
+            Special Salad: Cobb Salad
+            Special Drink: Chai Tea
+            for function: MenuPlugin-get_specials
+    AuthorRole.ASSISTANT: The special soup is Clam Chowder.
+    AuthorRole.ASSISTANT: 
+    Function Result:> 
+            Special Soup: Clam Chowder
+            Special Salad: Cobb Salad
+            Special Drink: Chai Tea
+            for function: MenuPlugin-get_specials
+    AuthorRole.ASSISTANT: The special drink is Chai Tea.
+    AuthorRole.ASSISTANT: Could you please specify the menu item you are asking about?
+    AuthorRole.ASSISTANT: You're welcome! If you have any questions about the menu or need assistance, feel free to ask.
+    """
+
+
+if __name__ == "__main__":
+    asyncio.run(main())