import semantic_kernel as sk
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion

# Create kernel
kernel = sk.Kernel()

# Add AI service
kernel.add_service(
    OpenAIChatCompletion(
        service_id="chat",
        ai_model_id="gpt-4o"
    )
)

# Create a semantic function
prompt = """
Summarize the following text in {{$style}} style:
{{$input}}
"""

summarize = kernel.create_function_from_prompt(
    function_name="summarize",
    plugin_name="TextPlugin",
    prompt=prompt
)

# Invoke the function
result = await kernel.invoke(
    summarize,
    input="Long text here...",
    style="professional"
)

print(result)

from semantic_kernel.functions import kernel_function

class MathPlugin:
    @kernel_function(
        name="add",
        description="Adds two numbers together"
    )
    def add(self, a: float, b: float) -> float:
        return a + b
    
    @kernel_function(
        name="multiply", 
        description="Multiplies two numbers"
    )
    def multiply(self, a: float, b: float) -> float:
        return a * b

# Add plugin to kernel
kernel.add_plugin(MathPlugin(), plugin_name="math")

# Use in prompts or planners
result = await kernel.invoke(
    kernel.plugins["math"]["add"],
    a=5, b=3
)

# Create prompt template
prompt_config = sk.PromptTemplateConfig(
    template="""
    You are a helpful assistant.
    
    User: {{$user_input}}
    
    Respond in a {{$tone}} tone.
    """,
    input_variables=[
        {"name": "user_input", "description": "User's message"},
        {"name": "tone", "description": "Response tone", "default": "friendly"}
    ]
)

# Register function
chat = kernel.create_function_from_prompt(
    function_name="chat",
    plugin_name="Assistant",
    prompt_template_config=prompt_config
)

from semantic_kernel.memory import SemanticTextMemory
from semantic_kernel.connectors.memory.chroma import ChromaMemoryStore

# Create memory with vector store
memory = SemanticTextMemory(
    storage=ChromaMemoryStore(persist_directory="./memory"),
    embeddings_generator=OpenAITextEmbedding(model_id="text-embedding-3-small")
)

# Save information
await memory.save_information(
    collection="docs",
    id="doc1",
    text="Semantic Kernel is Microsoft's AI SDK."
)

# Search memory
results = await memory.search(
    collection="docs",
    query="What is Semantic Kernel?",
    limit=5
)

from semantic_kernel.planners import SequentialPlanner

# Create planner
planner = SequentialPlanner(kernel)

# Generate plan from goal
plan = await planner.create_plan(
    goal="Research AI trends and write a summary email"
)

# Execute the plan
result = await plan.invoke(kernel)