Merge branch 'main' into feature_agent_serialization

python/samples/concepts/README.md

@@ -7,6 +7,7 @@ This section contains code snippets that demonstrate the usage of Semantic Kerne
 | Agents | Creating and using [agents](../../semantic_kernel/agents/) in Semantic Kernel |
 | AutoFunctionCalling | Using `Auto Function Calling` to allow function call capable models to invoke Kernel Functions automatically |
 | ChatCompletion | Using [`ChatCompletion`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/connectors/ai/chat_completion_client_base.py) messaging capable service with models  |
+| ChatHistory | Using and serializing the [`ChatHistory`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/contents/chat_history.py) |
 | Filtering | Creating and using Filters |
 | Functions | Invoking [`Method`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/functions/kernel_function_from_method.py) or [`Prompt`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/functions/kernel_function_from_prompt.py) functions with [`Kernel`](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/kernel.py) |
 | Grounding | An example of how to perform LLM grounding |

python/samples/concepts/chat_history/serialize_chat_history.py

@@ -0,0 +1,95 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+import os
+from typing import TYPE_CHECKING
+
+from semantic_kernel import Kernel
+from semantic_kernel.connectors.ai.function_choice_behavior import FunctionChoiceBehavior
+from semantic_kernel.connectors.ai.open_ai.prompt_execution_settings.azure_chat_prompt_execution_settings import (
+    AzureChatPromptExecutionSettings,
+)
+from semantic_kernel.connectors.ai.open_ai.services.azure_chat_completion import AzureChatCompletion
+from semantic_kernel.contents import ChatHistory
+from semantic_kernel.core_plugins.math_plugin import MathPlugin
+from semantic_kernel.core_plugins.time_plugin import TimePlugin
+from semantic_kernel.functions import KernelArguments
+
+if TYPE_CHECKING:
+    pass
+
+
+system_message = """
+You are a chat bot. Your name is Mosscap and
+you have one goal: figure out what people need.
+Your full name, should you need to know it, is
+Splendid Speckled Mosscap. You communicate
+effectively, but you tend to answer with long
+flowery prose. You are also a math wizard,
+especially for adding and subtracting.
+You also excel at joke telling, where your tone is often sarcastic.
+Once you have the answer I am looking for,
+you will return a full answer to me as soon as possible.
+"""
+
+kernel = Kernel()
+
+# Note: the underlying gpt-35/gpt-4 model version needs to be at least version 0613 to support tools.
+kernel.add_service(AzureChatCompletion(service_id="chat"))
+
+plugins_directory = os.path.join(__file__, "../../../../../prompt_template_samples/")
+# adding plugins to the kernel
+kernel.add_plugin(MathPlugin(), plugin_name="math")
+kernel.add_plugin(TimePlugin(), plugin_name="time")
+
+# Enabling or disabling function calling is done by setting the `function_choice_behavior` attribute for the
+# prompt execution settings. When the function_call parameter is set to "auto" the model will decide which
+# function to use, if any.
+#
+# There are two ways to define the `function_choice_behavior` parameter:
+# 1. Using the type string as `"auto"`, `"required"`, or `"none"`. For example:
+#   configure `function_choice_behavior="auto"` parameter directly in the execution settings.
+# 2. Using the FunctionChoiceBehavior class. For example:
+#   `function_choice_behavior=FunctionChoiceBehavior.Auto()`.
+# Both of these configure the `auto` tool_choice and all of the available plugins/functions
+# registered on the kernel. If you want to limit the available plugins/functions, you must
+# configure the `filters` dictionary attribute for each type of function choice behavior.
+# For example:
+#
+# from semantic_kernel.connectors.ai.function_choice_behavior import FunctionChoiceBehavior
+
+# function_choice_behavior = FunctionChoiceBehavior.Auto(
+#     filters={"included_functions": ["time-date", "time-time", "math-Add"]}
+# )
+#
+# The filters attribute allows you to specify either: `included_functions`, `excluded_functions`,
+#  `included_plugins`, or `excluded_plugins`.
+
+# Note: the number of responses for auto invoking tool calls is limited to 1.
+# If configured to be greater than one, this value will be overridden to 1.
+execution_settings = AzureChatPromptExecutionSettings(
+    service_id="chat",
+    max_tokens=2000,
+    temperature=0.7,
+    top_p=0.8,
+    function_choice_behavior=FunctionChoiceBehavior.Auto(),
+)
+
+arguments = KernelArguments(settings=execution_settings)
+
+
+async def main() -> None:
+    user_input = "What is the current hour plus 10?"
+    print(f"User:> {user_input}")
+
+    result = await kernel.invoke_prompt(prompt=user_input, arguments=arguments)
+
+    print(f"Mosscap:> {result}")
+
+    print("\nChat history:")
+    chat_history: ChatHistory = result.metadata["messages"]
+    print(chat_history.serialize())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

python/semantic_kernel/contents/kernel_content.py

@@ -13,7 +13,9 @@
 class KernelContent(KernelBaseModel, ABC):
     """Base class for all kernel contents."""
 
-    inner_content: Any | None = None
+    # NOTE: if you wish to hold on to the inner content, you are responsible
+    # for saving it before serializing the content/chat history as it won't be included.
+    inner_content: Any | None = Field(None, exclude=True)
     ai_model_id: str | None = None
     metadata: dict[str, Any] = Field(default_factory=dict)
 

python/tests/unit/contents/test_chat_history.py

@@ -2,6 +2,8 @@
 
 
 import pytest
+from openai.types.chat.chat_completion import ChatCompletion, Choice
+from openai.types.chat.chat_completion_message import ChatCompletionMessage
 
 from semantic_kernel.contents.chat_history import ChatHistory
 from semantic_kernel.contents.chat_message_content import ChatMessageContent
@@ -18,6 +20,19 @@
 from semantic_kernel.prompt_template.prompt_template_config import PromptTemplateConfig
 
 
+@pytest.fixture
+def mock_chat_completion_response() -> ChatCompletion:
+    return ChatCompletion(
+        id="test_id",
+        choices=[
+            Choice(index=0, message=ChatCompletionMessage(content="test", role="assistant"), finish_reason="stop")
+        ],
+        created=0,
+        model="test",
+        object="chat.completion",
+    )
+
+
 def test_init_with_system_message_only():
     system_msg = "test message"
     chat_history = ChatHistory(system_message=system_msg)
@@ -264,13 +279,26 @@ def test_serialize():
     )
 
 
-def test_serialize_and_deserialize_to_chat_history():
+def test_serialize_and_deserialize_to_chat_history(mock_chat_completion_response: ChatCompletion):
     system_msg = "a test system prompt"
-    msgs = [ChatMessageContent(role=AuthorRole.USER, content=f"Message {i}") for i in range(3)]
+    msgs = [
+        ChatMessageContent(
+            role=AuthorRole.USER,
+            content=f"Message {i}",
+            inner_content=mock_chat_completion_response,
+        )
+        for i in range(3)
+    ]
     chat_history = ChatHistory(messages=msgs, system_message=system_msg)
+
     json_str = chat_history.serialize()
     new_chat_history = ChatHistory.restore_chat_history(json_str)
-    assert new_chat_history == chat_history
+
+    assert len(new_chat_history.messages) == len(chat_history.messages)
+
+    for original_msg, restored_msg in zip(chat_history.messages, new_chat_history.messages):
+        assert original_msg.role == restored_msg.role
+        assert original_msg.content == restored_msg.content
 
 
 def test_deserialize_invalid_json_raises_exception():