How to Use Semantic Kernel Prompt Template in Agentic Framework Using Python?

[lovedeepatsgit]

I have referred to Semantic Kernel's Documentation (https://learn.microsoft.com/en-us/semantic-kernel/concepts/semantic-kernel-components?pivots=programming-language-python), And cam across Prompt Templates, Below are the few points which I have captured from this Documentation:

In, the below code I am created native functions, How I can replace that by creating function using Prompt Templates.

I want to do this with Both Ways, First Render in Prompt Template and Also by Plugin Functions.

Below is my Whole code which includes my prompts, classes I have made, and native functions, please provide me method and also explain how I can use Prompt Template.
from semantic_kernel.kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
from semantic_kernel.agents import ChatCompletionAgent
from semantic_kernel.connectors.ai.function_choice_behavior import FunctionChoiceBehavior

class Agent:
def init(self, api_key, azure_ai_model, azure_ai_endpoint, kernel):
"""
Initialize the class with Azure OpenAI credentials and Kernel.
"""
self.api_key = api_key
self.azure_ai_model = azure_ai_model
self.azure_ai_endpoint = azure_ai_endpoint
self.kernel = kernel

def build_agent(self, service_id, agent_name, agent_description, agent_instructions):
    """
    Integrates the Azure Chat Completion service and creates a Chat Completion Agent.

    :param service_id: The unique identifier for the service.
    :param agent_name: The name of the agent.
    :param agent_description: The description of the agent.
    :param agent_instructions: The instructions for the agent.
    """
    chat_service = AzureChatCompletion(
        service_id=service_id,
        api_key=self.api_key,
        deployment_name=self.azure_ai_model,
        endpoint=self.azure_ai_endpoint,
    )
    self.kernel.add_service(chat_service)

    settings = self.kernel.get_prompt_execution_settings_from_service_id(service_id)
    settings.function_choice_behavior = FunctionChoiceBehavior.Auto()

    agent = ChatCompletionAgent(
        service_id=service_id,
        kernel=self.kernel,
        name=agent_name,
        execution_settings=settings,
        description=agent_description,
        instructions=agent_instructions,
    )
    return agent

---

from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
from semantic_kernel.functions import kernel_function
from typing import Annotated
from typing import List

class Plugins:
def init(self):
self.service_endpoint = "ABC"
self.api_key = "ABC"

    self.hmh_search_client = SearchClient(
        endpoint=self.service_endpoint,
        index_name="hmh-blob-w-schedule",
        credential=AzureKeyCredential(self.api_key)
    )

    self.kagan_search_client = SearchClient(
        endpoint=self.service_endpoint,
        index_name="kagan-image-index",
        credential=AzureKeyCredential(self.api_key)
    )

@kernel_function(description="""
                This function retrieves data related to a specific educational standard or multiple standards.

                      ### Guidelines:
                - Extract the value of standard and use it as the input for this function.
                - Ensure you **only use the exact value from the first parenthesis** without any additional context or formatting.

                ### Common Mistakes to Avoid:
                - Do not process or alter the extracted standard value.
                """
)
def hmh(self, query: Annotated[str,"Provide the exact standard code(s) extracted from the  the query."

]) -> List[str]:
search_options = {
"query_type": "semantic",
"semantic_configuration_name": "azureml-default",
"top": 5
}
search_results = self.hmh_search_client.search(query, **search_options)
results = []
for result in search_results:
results.append(result['content'])

    return tuple(results)

@kernel_function(description="Performs a search on the study material to get content related to Kagan Activities. Always provide 'Kagan Coaching Form' as input")
def kagan(self,query : str) -> List[str]:
    query="Kagan Coaching Form"
    search_options = {
        "top": 16
    }
    search_results = self.kagan_search_client.search(query, **search_options)
    results = []
    for result in search_results:
        results.append(result['merged_content'])

    return tuple(results)

---

############################################################################################################

TEACHER_AGENT_DESCRIPTION = "Teacher Assigned for Generation of Lesson Plan for specific day."

############################################################################################################

TEACHER_AGENT_PROMPT = """
You are an expert educator tasked with developing a detailed lesson plan for a specific grade and standard. You have to create Lesson Plan for the four days of a 4-day curriculum. The students are weak in the specified standard and need additional time to study. The 4-day curriculum has already been planned, and now you need to prepare detailed content for the particular specified day, do not generate lesson simultaneously in one for all 4-days, which should include:

                            1. **Activity Task**:  
                            
                                -The title of the activity should reference the relevant Standard(s) requested by the user. 
                                -Provide a complete explanation of the activity. 

                            2. **Content**:  

                                - Like a concept or specific teaching content (around 2000 words) 

                            3. **Story**: 

                                - Imaginary Story to build the interest of students (around 2500 words) 

                            4. **Vocabulary Builder**:  

                                - Meanings of 5 words related to today's lesson 

                            5. **Homework Sample**: 

                                - Homework, along with its answers so that teacher get a reference to check the homework of students. 
                                - First provide the questions only, after that provide the answer key.
                            
                            6. **Assessment**:  

                                - A minimum of 10 questions (mix of subjective and objective) along their answer key .
                                - Answer key should be after the questions.

                            7.. **List of Websites**:  

                                - Related to the concepts for this day, according to Kagan Coaching Form. 

                    After, the generation of the lesson plan for the 4th day, you have to ask for the assessment generation on the basis of 4 days content.
                    If the user asks or agress for assessment then Your task is to analyze the context and information provided to you, which pertains to a specific 
                    grade and standard. Based on the teaching conducted over previous days, you need to create an assessment comprising 50 questions. This assessment 
                    should include a mix of subjective and objective questions. Remember, this assessment will be posted on an online portal, so avoid using phrases 
                    like "circle the correct answer." Instead, use "select the correct answer" to make the assessment more suitable for an online format.
                 """

---

BELOW IS THE MAIN CODE

from Classes.Agent import Agent
from Classes.Plugins import Plugins
from Classes.Prompts_Latest import TEACHER_AGENT_DESCRIPTION,TEACHER_AGENT_PROMPT
from semantic_kernel.kernel import Kernel
from semantic_kernel.contents.chat_history import ChatHistory
from semantic_kernel.contents.chat_message_content import ChatMessageContent
from semantic_kernel.contents.utils.author_role import AuthorRole
from semantic_kernel.contents.chat_message_content import ChatMessageContent
from semantic_kernel.contents.utils.author_role import AuthorRole
import asyncio

azure_ai_endpoint = "ABC"
azure_ai_api_key = "ABC"
azure_ai_model = 'ABC'

async def main():
kernel = Kernel()
kernel.add_plugin(plugin=Plugins(), plugin_name="AiSearchPlugin")
agent = Agent(azure_ai_api_key, azure_ai_model, azure_ai_endpoint,kernel).build_agent("TeacherService","TeacherAgent", TEACHER_AGENT_DESCRIPTION, TEACHER_AGENT_PROMPT)

history = ChatHistory()
is_complete: bool = False
while not is_complete:
    user_input = input("User:> ")
    if not user_input:
        continue

    if user_input.lower() == "exit":
        is_complete = True
        break

    history.add_message(ChatMessageContent(role=AuthorRole.USER, content=user_input))

    async for response in agent.invoke(history=history):
        print(f"{response.name}")
        print(f"{response.content}")
        print("*" * 100)

if name == "main":
asyncio.run(main())

[moonbox3]

@lovedeepatsgit support for prompt template config in SK Python is pending: #8699 and #8022.

[moonbox3]

@lovedeepatsgit this is supported as of #10298 and will be included in our next release this week. FYI.

[lovedeepatsgit]

@lovedeepatsgit this is supported as of #10298 and will be included in our next release this week. FYI.

Okay @moonbox3 Thanks for your reply.