### Install Semantic Kernel

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/PluginWithSK.ipynb

Installs the latest version of the semantic-kernel library using pip.

```python
! pip install semantic-kernel -U
```

--------------------------------

### Install Semantic Kernel NuGet Packages

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/05/EmbeddingsWithSK.ipynb

Installs the necessary Semantic Kernel and Qdrant connector packages using `#r` directives.

```csharp
#r "nuget: Microsoft.SemanticKernel, *-*"
#r "nuget: Microsoft.SemanticKernel.Connectors.Qdrant, *-*"
```

--------------------------------

### Python: Basic Prompt Execution

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop2/genppt_notebook.ipynb

Demonstrates how to create a kernel, load a prompt, and execute it. This is a fundamental example for getting started with Semantic Kernel in Python.

```Python
from semantic_kernel import Kernel

kernel = Kernel()

# Load a prompt from a file or string
prompt = """
Write a short poem about a {subject}.
"""

# Create a semantic function
poem_function = kernel.create_semantic_function(prompt)

# Invoke the function
result = poem_function(subject="a rainy day")

print(result)
```

--------------------------------

### Install Semantic Kernel

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/02/LearnSK.ipynb

Installs the latest version of the semantic-kernel library using pip. This is the first step to using the library.

```python
! pip install semantic-kernel -U
```

--------------------------------

### Install Semantic Kernel and Qdrant Client

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Installs the necessary Python packages for Semantic Kernel and Qdrant client. This is a prerequisite for using these libraries.

```python
! pip install semantic-kernel -U
! pip install qdrant_client -U
```

--------------------------------

### Python Setup for Machine Learning

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/data/notes/01-introduction.md

Instructions for setting up a Python environment for machine learning development, including installing Python and a text editor.

```APIDOC
Python Installation:
  - Download and install Python from the official website.
  - Recommended text editor: Visual Studio Code.

Dependencies:
  - Python 3.x
```

--------------------------------

### Python Setup for Machine Learning

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/data/notes/01-introduction.md

Instructions for setting up a Python environment for machine learning development, including installing Python and a text editor.

```APIDOC
Python Installation:
  - Download and install Python from the official website.
  - Recommended text editor: Visual Studio Code.

Dependencies:
  - Python 3.x
```

--------------------------------

### Install Semantic Kernel

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/FunctionCallWithSK.ipynb

Installs the latest version of the Semantic Kernel library using pip.

```python
! pip install semantic-kernel -U
```

--------------------------------

### Install Semantic Kernel and Qdrant Client

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/notebook.ipynb

Installs the necessary Python packages for Semantic Kernel and Qdrant client. This is a prerequisite for using these libraries.

```python
! pip install semantic-kernel -U
! pip install qdrant_client -U
```

--------------------------------

### Python Setup for Machine Learning

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notes/01-introduction.md

Instructions for setting up a Python environment for machine learning development, including installing Python and a text editor.

```APIDOC
Python Installation:
  - Download and install Python from the official website.
  - Recommended text editor: Visual Studio Code.

Dependencies:
  - Python 3.x
```

--------------------------------

### Semantic Kernel NuGet Packages

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Installs necessary Semantic Kernel NuGet packages for core functionality and Qdrant integration.

```csharp
#r "nuget: Microsoft.SemanticKernel, *-*"
#r "nuget: Microsoft.SemanticKernel.Connectors.Qdrant, *-*"
```

--------------------------------

### Install Semantic Kernel and Qdrant Client

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/05/EmbeddingsWithSK.ipynb

Installs the necessary Python packages for Semantic Kernel and Qdrant client. This is a prerequisite for using these libraries.

```python
! pip install semantic-kernel -U
! pip install qdrant_client -U
```

--------------------------------

### Install Semantic Kernel and Qdrant Client

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop2/genppt_notebook.ipynb

Installs the latest version of the semantic-kernel and qdrant-client Python packages. These are essential for using Semantic Kernel and its related functionalities.

```python
! pip install semantic-kernel -U
! pip install qdrant_client -U
```

--------------------------------

### Initialize Sequential Planner

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/java/04/PlannerWithSK.ipynb

Initializes a SequentialPlanner with a given kernel and maximum token count. This is a common setup step before creating plans.

```csharp
SequentialPlanner planner = initPlanner(kernel, 1024);

```

--------------------------------

### Semantic Kernel Chat Completion Service Setup

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/notebook.ipynb

Configures the ChatCompletionService using the initialized OpenAI client and specifies the model deployment name for chat completions.

```java
import com.microsoft.semantickernel.Kernel;
import com.microsoft.semantickernel.Kernel.Builder;
import com.microsoft.semantickernel.exceptions.ConfigurationException;
import com.microsoft.semantickernel.orchestration.FunctionResult;
import com.microsoft.semantickernel.orchestration.PromptExecutionSettings;
import com.microsoft.semantickernel.plugin.KernelPluginFactory;
import com.microsoft.semantickernel.semanticfunctions.KernelFunction;
import com.microsoft.semantickernel.semanticfunctions.KernelFunctionArguments;
import com.microsoft.semantickernel.semanticfunctions.KernelFunctionFromPrompt;
import com.microsoft.semantickernel.services.textcompletion.TextGenerationService;

import com.microsoft.semantickernel.aiservices.openai.chatcompletion.OpenAIChatCompletion;
import com.microsoft.semantickernel.services.chatcompletion.ChatCompletionService;

ChatCompletionService chatGenerationService = OpenAIChatCompletion.builder()
                        .withOpenAIAsyncClient(client)
                        .withModelId("Your Azure OpenAI Service gpt-3.5-turbo-instruct deployment name")
                        .build();
```

--------------------------------

### Semantic Kernel C# Setup with Azure OpenAI

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/03/PluginWithSK.ipynb

Demonstrates how to initialize the Semantic Kernel with Azure OpenAI chat completion services. It requires specifying the deployment name, endpoint, and API key for the Azure OpenAI service.

```csharp
#r "nuget: Microsoft.SemanticKernel, *-*"

using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Memory;
using Microsoft.SemanticKernel.Connectors.OpenAI;

Kernel kernel = Kernel.CreateBuilder()
            .AddAzureOpenAIChatCompletion("Your Azure OpenAI Service gpt-4 Deployment Name" , "Your Azure OpenAI Service Endpoint", "Your Azure OpenAI Service API Key")
            .Build();
```

--------------------------------

### Install PyPDF2

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop2/genppt_notebook.ipynb

Installs the PyPDF2 package, which is used for reading and manipulating PDF files.

```python
! pip install PyPDF2 -U
```

--------------------------------

### Semantic Kernel NuGet Packages

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop3/dotNETAgent/SKAIAgent.ipynb

Installs necessary Semantic Kernel NuGet packages for .NET development, including core functionalities and experimental agent features.

```C#
#r "nuget: Microsoft.SemanticKernel, *-*"
#r "nuget: Microsoft.SemanticKernel.Experimental.Agents, *-*"
```

--------------------------------

### Install Semantic Kernel - .NET

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/cn/02.IntroduceSemanticKernel.md

Installs the latest version of the Semantic Kernel library for .NET using NuGet.

```csharp
#r "nuget: Microsoft.SemanticKernel, *-*"
```

--------------------------------

### Node.js and JavaScript Setup for Web Apps

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/data/notes/01-introduction.md

Guidance on setting up Node.js and npm for JavaScript development, particularly for building web applications.

```APIDOC
Node.js and npm Installation:
  - Download and install Node.js and npm from the official website.
  - Recommended IDE: Visual Studio Code.

Usage:
  - Used for building web applications alongside Python in ML courses.
```

--------------------------------

### Node.js and JavaScript Setup for Web Apps

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notes/01-introduction.md

Guidance on setting up Node.js and npm for JavaScript development, particularly for building web applications.

```APIDOC
Node.js and npm Installation:
  - Download and install Node.js and npm from the official website.
  - Recommended IDE: Visual Studio Code.

Usage:
  - Used for building web applications alongside Python in ML courses.
```

--------------------------------

### Node.js and JavaScript Setup for Web Apps

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/data/notes/01-introduction.md

Guidance on setting up Node.js and npm for JavaScript development, particularly for building web applications.

```APIDOC
Node.js and npm Installation:
  - Download and install Node.js and npm from the official website.
  - Recommended IDE: Visual Studio Code.

Usage:
  - Used for building web applications alongside Python in ML courses.
```

--------------------------------

### Create Plugins from Directory

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Loads plugins (FilePlugin and AnswerPlugin) from specified directories.

```csharp
var filePlugin = kernel.CreatePluginFromPromptDirectory(Path.Combine(pluginDirectory, "FilePlugin"));
var answerPlugin = kernel.CreatePluginFromPromptDirectory(Path.Combine(pluginDirectory, "AnswerPlugin"));
```

--------------------------------

### Semantic Kernel: Prompt Engineering (C#)

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates prompt engineering best practices in C# for Semantic Kernel. This example shows how to structure prompts with examples and variables for better AI responses.

```csharp
using Microsoft.SemanticKernel;

var kernel = Kernel.CreateBuilder().Build();

var prompt = """
Translate the following English text to French:

English: Hello world
French: Bonjour le monde

English: How are you?
French: Comment ça va?

English: {english_text}
French:
""";

var translateFunction = kernel.CreateFunctionFromPrompt(prompt);

var result = await kernel.InvokeAsync(translateFunction, new() { { "english_text", "I love Semantic Kernel." } });

Console.WriteLine(result);
```

--------------------------------

### Install Semantic Kernel NuGet Package

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/03/FunctionCallWithSK.ipynb

This snippet shows how to reference the Semantic Kernel NuGet package using the '#r' directive in a C# environment, typically within a .NET interactive context.

```csharp
#r "nuget: Microsoft.SemanticKernel, *-*"
```

--------------------------------

### Initialize and Create Qdrant Collection

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Initializes the QdrantMemoryStore with a specified vector size and connection details, then creates a new collection asynchronously.

```python
qdrant_store = QdrantMemoryStore(vector_size=1536, url="http://localhost",port=6333)
await qdrant_store.create_collection_async(base_vectordb)
```

--------------------------------

### Install Semantic Kernel - Python

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/cn/02.IntroduceSemanticKernel.md

Installs the latest version of the Semantic Kernel library for Python using pip.

```python
! pip install semantic-kernel -U
```

--------------------------------

### Semantic Kernel Initialization

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/notebook.ipynb

Builds a Semantic Kernel instance and configures it with the ChatCompletionService for text generation.

```java
import com.microsoft.semantickernel.Kernel;
import com.microsoft.semantickernel.Kernel.Builder;
import com.microsoft.semantickernel.exceptions.ConfigurationException;
import com.microsoft.semantickernel.orchestration.FunctionResult;
import com.microsoft.semantickernel.orchestration.PromptExecutionSettings;
import com.microsoft.semantickernel.plugin.KernelPluginFactory;
import com.microsoft.semantickernel.semanticfunctions.KernelFunction;
import com.microsoft.semantickernel.semanticfunctions.KernelFunctionArguments;
import com.microsoft.semantickernel.semanticfunctions.KernelFunctionFromPrompt;
import com.microsoft.semantickernel.services.textcompletion.TextGenerationService;

import com.microsoft.semantickernel.aiservices.openai.chatcompletion.OpenAIChatCompletion;
import com.microsoft.semantickernel.services.chatcompletion.ChatCompletionService;

Kernel kernel = Kernel.builder()
    .withAIService(ChatCompletionService.class, chatGenerationService)
    .build();
```

--------------------------------

### Get Notes Files

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Retrieves all files from the './data/notes' directory.

```csharp
DirectoryInfo notesFolder = new DirectoryInfo(@"./data/notes");    
FileInfo[] notesFiles = notesFolder.GetFiles();
```

--------------------------------

### Import Semantic Kernel Library

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/en/02.IntroduceSemanticKernel.md

Installs the latest Semantic Kernel library for .NET and Python projects. For .NET, it uses NuGet package management. For Python, it uses pip for installation.

```.NET
#r "nuget: Microsoft.SemanticKernel, *-*"
```

```Python
! pip install semantic-kernel -U
```

--------------------------------

### Add Azure OpenAI Text Completion Service (Commented Out)

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/02/LearnSK.ipynb

A commented-out example showing how to add an Azure OpenAI text completion service. It requires deployment name, endpoint, and API key.

```python
# kernel.add_text_completion_service("azure_text_competion_service", skaoai.AzureTextCompletion(deployment,endpoint,api_key=api_key))
```

--------------------------------

### Getting Plan as String

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/04/PlannerWithSK.ipynb

Converts the created plan object into its string representation.

```C#
originalPlan.ToString()
```

--------------------------------

### Initialize Qdrant Client

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/notebook.ipynb

Initializes a Qdrant client instance connecting to a local Qdrant service on the default gRPC port.

```java
QdrantClient qdrantClient = 
  new QdrantClient(QdrantGrpcClient.newBuilder("localhost",6334,false).build());
```

--------------------------------

### Install OpenAI SDK for .NET

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/01/dotNETSDKAOAIDemo.ipynb

Installs the necessary Azure OpenAI and Azure Identity NuGet packages for .NET development. These packages are essential for authenticating and interacting with Azure OpenAI services.

```C#
#r "nuget: Azure.AI.OpenAI, *-*"
#r "nuget: Azure.Identity,*-*"
#r "nuget: Azure.Core,*-*"
```

--------------------------------

### Import Qdrant Memory Store

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Imports the QdrantMemoryStore class for interacting with a Qdrant vector database.

```python
from semantic_kernel.connectors.memory.qdrant import QdrantMemoryStore
```

--------------------------------

### Semantic Kernel C# Prompt Template

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/03/PluginWithSK.ipynb

Defines a system prompt template for a C# function within Semantic Kernel. This template guides the AI's behavior and includes a placeholder for user input.

```csharp
string promptTemplate = @"System: You are a python developer 。 User:{{$input}}";
```

--------------------------------

### Semantic Kernel Usings

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Imports essential namespaces for Semantic Kernel, Qdrant, and OpenAI connectors.

```csharp
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Embeddings;
using Microsoft.SemanticKernel.Memory;
using Microsoft.SemanticKernel.Connectors.Qdrant;
using Microsoft.SemanticKernel.Connectors.OpenAI;
```

--------------------------------

### Initialize Semantic Kernel and Azure OpenAI Settings

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Initializes the Semantic Kernel instance and retrieves Azure OpenAI deployment details, API key, and endpoint from environment variables.

```python
kernel = sk.Kernel()
deployment, api_key, endpoint = sk.azure_openai_settings_from_dot_env()
```

--------------------------------

### Get Dressing Tips and Translate

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/plugins/WriterPlugin/Tips/skprompt.txt

This C# code snippet shows how to use Semantic Kernel to generate dressing tips based on an input topic and then translate those tips into a target language. It utilizes prompt engineering to define the desired output format and language.

```C#
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Connectors.OpenAI;

var kernel = Kernel.CreateBuilder()
    .AddOpenAIChatCompletion(
        modelId: "gpt-3.5-turbo",
        apiKey: "YOUR_API_KEY")
    .Build();

string inputTopic = "casual summer";
string targetLanguage = "French";

var prompt = $"Get dressing tips for {inputTopic} and translate them into {targetLanguage}.";

var result = await kernel.InvokePromptAsync(prompt);

Console.WriteLine(result);

```

--------------------------------

### Displaying the Created Plan

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/04/PlannerWithSK.ipynb

Prints the string representation of the created plan to the console.

```C#
Console.WriteLine(originalPlan);
```

--------------------------------

### Semantic Kernel Initialization with Azure OpenAI

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/04/PlannerWithSK.ipynb

Initializes the Semantic Kernel with Azure OpenAI chat completion service. Requires deployment name, endpoint, and API key.

```C#
Kernel kernel = Kernel.CreateBuilder()
            .AddAzureOpenAIChatCompletion("Your Azure OpenAI Service gpt-35-turbo-16k Deployment Name", "Your Azure OpenAI Service Endpoint", "Your Azure OpenAI Service API Key")
            .Build();
```

--------------------------------

### Create Prompt Template Configuration

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/PluginWithSK.ipynb

Configures the prompt template with its name, format, input variables, and execution settings.

```python
prompt_template_config = PromptTemplateConfig(
    template=prompt,
    name="summarize",
    template_format="semantic-kernel",
    input_variables=[
        InputVariable(name="input", description="The user input", is_required=True),
    ],
    execution_settings=execution_settings,
)
```

--------------------------------

### Creating a Plan with Handlebars Planner

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/04/PlannerWithSK.ipynb

Creates a plan asynchronously using the HandlebarsPlanner based on the defined goal and the initialized kernel. Suppresses a specific SKEXP0060 warning.

```C#
#pragma warning disable SKEXP0060

var originalPlan = await planner.CreatePlanAsync(kernel, goal);
```

--------------------------------

### Import Answer Plugin

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Imports the 'AnswerPlugin' from the specified directory into the Semantic Kernel.

```python
answer_plugin = kernel.import_semantic_skill_from_directory(base_plugin , "AnswerPlugin")
```

--------------------------------

### Setup New .NET Console Project

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop3/dotNETAgent/plugins/CodePlugin/dotNET/skprompt.txt

Generates a new .NET console application project in a specified directory. This command initializes the project structure required for a .NET application.

```bash
dotnet new console -o {{projectName}}
```

--------------------------------

### Handlebars Planner Initialization

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/04/PlannerWithSK.ipynb

Initializes the HandlebarsPlanner, a planner that uses Handlebars templating for plan creation. Suppresses a specific SKEXP0060 warning.

```C#
using Microsoft.SemanticKernel.Planning.Handlebars;

#pragma warning disable SKEXP0060

var planner = new HandlebarsPlanner();
```

--------------------------------

### Select Summary Function from Plugin

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/notebook.ipynb

Selects the 'Summary' function from the imported 'AnswerPlugin'.

```python
answerFunc = answer_plugin["Summary"]
```

--------------------------------

### Build Kernel with Chat Completion Service in Java

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/java/03/PluginWithSK.ipynb

Initializes a Semantic Kernel builder and configures it with a chat completion service.

```java
Builder kernelBuilder = Kernel.builder()
            .withAIService(ChatCompletionService.class, chatGenerationService);
```

--------------------------------

### Initialize KB List

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Initializes an empty list to store KB objects.

```csharp
IList<KB> kbList = new List<KB>();
```

--------------------------------

### Import Semantic Kernel Libraries

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/PluginWithSK.ipynb

Imports necessary classes and modules from the semantic-kernel library for AI and prompt management.

```python
import semantic_kernel as sk
import semantic_kernel.connectors.ai.open_ai as skaoai
from semantic_kernel.connectors.ai.open_ai import AzureChatPromptExecutionSettings, OpenAIChatPromptExecutionSettings
from semantic_kernel.prompt_template import InputVariable, PromptTemplateConfig
```

--------------------------------

### Import System Namespaces

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/05/EmbeddingsWithSK.ipynb

Imports essential .NET system namespaces for general programming tasks.

```csharp
using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.IO;
using System.Net.Http;
using System.Text.Json;
using System.Threading.Tasks;
```

--------------------------------

### System Usings

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Imports standard .NET namespaces for system operations, file handling, and JSON serialization.

```csharp
using System;
using System.IO;
using System.Text.Json;
```

--------------------------------

### Initialize Kernel and Azure OpenAI Settings

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/FunctionCallWithSK.ipynb

Initializes the Semantic Kernel and retrieves Azure OpenAI deployment, API key, and endpoint settings from environment variables.

```python
kernel = sk.Kernel()
deployment, api_key, endpoint = sk.azure_openai_settings_from_dot_env()
```

--------------------------------

### Get Transcript Files

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Retrieves all files from the './data/transcripts' directory.

```csharp
DirectoryInfo transcriptsFolder = new DirectoryInfo(@"./data/transcripts");    
FileInfo[] transcriptsFiles = transcriptsFolder.GetFiles();
```

--------------------------------

### Import Semantic Kernel Libraries

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/04/PlannerWithSK.ipynb

Imports necessary modules from the semantic_kernel library, including core components, AI connectors (OpenAI, Azure OpenAI), and prompt template configurations.

```python
import os
import sys

import semantic_kernel as sk
import semantic_kernel.connectors.ai.open_ai as skaoai
from semantic_kernel.connectors.ai.open_ai import AzureChatPromptExecutionSettings, OpenAIChatPromptExecutionSettings
from semantic_kernel.prompt_template import InputVariable, PromptTemplateConfig
```

--------------------------------

### Install .NET Azure OpenAI SDK

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/en/01.UsingAzureOpenAIServiceWithSDK.md

Installs the latest Azure.AI.OpenAI NuGet package for .NET. This package provides the necessary classes to interact with Azure OpenAI Service.

```csharp
#r "nuget: Azure.AI.OpenAI, *-*"
```

--------------------------------

### Get Summary Function from Answer Plugin

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Retrieves the 'Summary' function from the imported 'AnswerPlugin'.

```python
answerFunc = answer_plugin["Summary"]
```

--------------------------------

### Install and Run Qdrant

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/java/05/EmbeddingsWithSK.ipynb

This snippet shows how to pull the Qdrant Docker image and run it, mounting a local directory for persistent storage.

```bash
docker pull qdrant/qdrant
docker run -p 6333:6333 -p 6334:6334 \
    -v $(pwd)/qdrant_storage:/qdrant/storage:z \
    qdrant/qdrant
```

--------------------------------

### Get Translation Result (C#)

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/02/LearnSK.ipynb

Retrieves the string result from the asynchronous operation of invoking a Semantic Kernel function. This is typically the translated text.

```csharp
transalteContent.GetValue<string>()
```

--------------------------------

### Initialize Kernel and Add Azure Chat Service

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/PluginWithSK.ipynb

Initializes the Semantic Kernel and adds an Azure OpenAI chat completion service using environment variables for configuration.

```python
service_id = "default"

kernel = sk.Kernel()

kernel.add_service(
        skaoai.AzureChatCompletion(
                service_id=service_id,
                env_file_path=".env"
        ),
)
```

--------------------------------

### Scikit-learn User Guide Reference

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/data/notes/03-techniques-ml.md

Provides a reference to the Scikit-learn user guide for exploring various model training methods and techniques. This is crucial for understanding different algorithms and their applications.

```APIDOC
Scikit-learn User Guide:
  URL: https://scikit-learn.org/stable/user_guide.html
  Description: Comprehensive documentation for Scikit-learn, covering algorithms, preprocessing, model selection, and evaluation.
  Key Sections:
    - "Estimator basics": Understanding the API of estimators.
    - "Preprocessing data": Techniques for scaling, encoding, and imputation.
    - "Model selection": Cross-validation, hyperparameter tuning, and metrics.
    - "Supervised learning": Algorithms like regression, classification, and clustering.
    - "Unsupervised learning": Algorithms like dimensionality reduction and clustering.
```

--------------------------------

### Scikit-learn User Guide Reference

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notes/03-techniques-ml.md

Provides a reference to the Scikit-learn user guide for exploring various model training methods and techniques. This is crucial for understanding different algorithms and their applications.

```APIDOC
Scikit-learn User Guide:
  URL: https://scikit-learn.org/stable/user_guide.html
  Description: Comprehensive documentation for Scikit-learn, covering algorithms, preprocessing, model selection, and evaluation.
  Key Sections:
    - "Estimator basics": Understanding the API of estimators.
    - "Preprocessing data": Techniques for scaling, encoding, and imputation.
    - "Model selection": Cross-validation, hyperparameter tuning, and metrics.
    - "Supervised learning": Algorithms like regression, classification, and clustering.
    - "Unsupervised learning": Algorithms like dimensionality reduction and clustering.
```

--------------------------------

### Scikit-learn User Guide Reference

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/data/notes/03-techniques-ml.md

Provides a reference to the Scikit-learn user guide for exploring various model training methods and techniques. This is crucial for understanding different algorithms and their applications.

```APIDOC
Scikit-learn User Guide:
  URL: https://scikit-learn.org/stable/user_guide.html
  Description: Comprehensive documentation for Scikit-learn, covering algorithms, preprocessing, model selection, and evaluation.
  Key Sections:
    - "Estimator basics": Understanding the API of estimators.
    - "Preprocessing data": Techniques for scaling, encoding, and imputation.
    - "Model selection": Cross-validation, hyperparameter tuning, and metrics.
    - "Supervised learning": Algorithms like regression, classification, and clustering.
    - "Unsupervised learning": Algorithms like dimensionality reduction and clustering.
```

--------------------------------

### Display KB List

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Outputs the current content of the kbList.

```csharp
kbList
```

--------------------------------

### Semantic Kernel Core and Agent Usings

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop3/dotNETAgent/SKAIAgent.ipynb

Imports essential namespaces from the Semantic Kernel library for agent creation, configuration, and OpenAI connectors.

```C#
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Experimental.Agents;
using Microsoft.SemanticKernel.Connectors.OpenAI;
```

--------------------------------

### Get Available Functions

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/FunctionCallWithSK.ipynb

Retrieves a list of available functions from the kernel, optionally filtering out specific skills. This prepares the kernel to use functions for completion.

```python
filter = {"exclude_skill": ["ChatBot"]}
functions = get_function_calling_object(kernel, filter)
```

--------------------------------

### Install and Run Qdrant Docker Container

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/cn/05.Embeddings.md

Commands to pull the Qdrant Docker image and run a Qdrant container locally.

```Bash
docker pull qdrant/qdrant

docker run -p 6333:6333 qdrant/qdrant
```

--------------------------------

### Import File Plugin

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Imports the 'FilePlugin' from the specified directory into the Semantic Kernel.

```python
files_plugin = kernel.import_semantic_skill_from_directory(base_plugin , "FilePlugin")
```

--------------------------------

### Java: Basic Prompt Execution

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop2/genppt_notebook.ipynb

Shows how to initialize a Semantic Kernel instance, define a prompt, and execute a semantic function in Java. This example is essential for Java developers new to the SDK.

```Java
import com.microsoft.semantickernel.Kernel;

Kernel kernel = Kernel.builder().build();

// Load a prompt from a file or string
String prompt = "Write a short poem about a {subject}.";

// Create a semantic function
var poemFunction = kernel.createFunctionFromPrompt(prompt);

// Invoke the function
var result = kernel.invokeAsync(poemFunction, java.util.Map.of("subject", "a gentle breeze")).block();

System.out.println(result);
```

--------------------------------

### LINQ and Task Usings

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop3/dotNETAgent/SKAIAgent.ipynb

Imports namespaces for Language Integrated Query (LINQ) and asynchronous programming patterns using Tasks.

```C#
using System;
using System.Collections.Generic;
using System.Linq;
using System.Threading.Tasks;
```

--------------------------------

### List Data Files

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Retrieves lists of files from the './data/notes' and './data/transcripts' directories.

```python
nodes_files = os.listdir("./data/notes")
transcripts_files = os.listdir("./data/transcripts")
```

--------------------------------

### Semantic Kernel NuGet Package References

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/04/PlannerWithSK.ipynb

Specifies the NuGet packages required for Semantic Kernel and its Handlebars planner integration.

```C#
#r "nuget: Microsoft.SemanticKernel, *-*"
#r "nuget: Microsoft.SemanticKernel.Planners.Handlebars, *-*"
```

--------------------------------

### Semantic Kernel Core Concepts

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates fundamental concepts of the Semantic Kernel, including creating a kernel, loading plugins, and invoking functions. Essential for understanding the basic building blocks of the framework.

```csharp
using Microsoft.SemanticKernel;

// Initialize the kernel
var kernel = Kernel.CreateBuilder().Build();

// Load a plugin (e.g., from a directory)
// kernel.ImportPluginFromPromptDirectory("Plugins", "MySkill");

// Invoke a function
// var result = await kernel.InvokeAsync("MySkill", "MyFunction", new() { ["input"] = "Hello" });
// Console.WriteLine(result);
```

--------------------------------

### Initialize Semantic Kernel

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/04/PlannerWithSK.ipynb

Initializes an instance of the Semantic Kernel, which serves as the central orchestrator for AI operations.

```python
kernel = sk.Kernel()
```

--------------------------------

### Semantic Kernel Core Concepts

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates fundamental concepts of the Semantic Kernel, including creating a kernel, loading plugins, and invoking functions. Essential for understanding the basic building blocks of the framework.

```python
from semantic_kernel import Kernel

# Initialize the kernel
kernel = Kernel()

# Load a plugin (e.g., from a directory)
# kernel.import_semantic_skill_from_directory("plugins", "MySkill")

# Invoke a function
# result = await kernel.run_async("MySkill", "MyFunction", input_str="Hello")
# print(result)
```

--------------------------------

### Load Plugin from Directory (C#)

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/02/LearnSK.ipynb

Creates a Semantic Kernel plugin instance by loading it from a specified directory. Assumes the directory contains a valid plugin structure.

```csharp
var plugin = kernel.CreatePluginFromPromptDirectory(Path.Combine(pluginDirectory, "TranslatePlugin"));
```

--------------------------------

### Importing Plugins from Prompt Directory

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/04/PlannerWithSK.ipynb

Imports plugins from specified directories within the plugin directory. This allows loading plugins defined by prompt templates.

```C#
var writetPlugin =  kernel.ImportPluginFromPromptDirectory(Path.Combine(pluginDirectory, "WriterPlugin"));
var emailPlugin =  kernel.ImportPluginFromPromptDirectory(Path.Combine(pluginDirectory, "EmailPlugin"));
var translatePlugin =  kernel.ImportPluginFromPromptDirectory(Path.Combine(pluginDirectory, "TranslatePlugin"));
```

--------------------------------

### Kernel Initialization with Azure OpenAI

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/notebook.ipynb

Initializes the Semantic Kernel with Azure OpenAI chat completion service, requiring deployment name, endpoint, and API key.

```csharp
Kernel kernel = Kernel.CreateBuilder()
            .AddAzureOpenAIChatCompletion("Your Azure OpenAI Service Deployment Name" , "Your Azure OpenAI Service Endpoint", "Your Azure OpenAI Service API Key")
            .Build();
```

--------------------------------

### Initialize Qdrant Memory Store and Collection

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/05/EmbeddingsWithSK.ipynb

Initializes a Qdrant memory store and creates a collection named 'aboutMe'. This sets up the persistent storage for semantic data.

```python
qdrant_store = QdrantMemoryStore(vector_size=1536, url="http://localhost",port=6333)
await qdrant_store.create_collection('aboutMe')
```

--------------------------------

### Define Prompt Template

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/PluginWithSK.ipynb

Creates a prompt template string with a system message and a user input variable.

```python
prompt = "System: You are a python developer 。 User:{{$input}}"
```

--------------------------------

### Import Semantic Kernel and Connectors

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/02/LearnSK.ipynb

Imports the core Semantic Kernel library and its connectors for AI services, specifically focusing on OpenAI.

```python
import semantic_kernel as sk
import semantic_kernel.connectors.ai.open_ai as skaoai
```

--------------------------------

### Semantic Kernel Core Concepts

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates fundamental concepts of the Semantic Kernel, including creating a kernel, loading plugins, and invoking functions. Essential for understanding the basic building blocks of the framework.

```csharp
using Microsoft.SemanticKernel;

// Initialize the kernel
var kernel = Kernel.CreateBuilder().Build();

// Load a plugin (e.g., from a directory)
// kernel.ImportPluginFromPromptDirectory("Plugins", "MySkill");

// Invoke a function
// var result = await kernel.InvokeAsync("MySkill", "MyFunction", new() { ["input"] = "Hello" });
// Console.WriteLine(result);
```

--------------------------------

### Initialize Kernel

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/02/LearnSK.ipynb

Initializes a new instance of the Semantic Kernel. This object serves as the central point for orchestrating AI capabilities.

```python
kernel = sk.Kernel()
```

--------------------------------

### DALL-E Features and Applications

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/en/00.IntroduceLLM.md

DALL-E, specifically DALL-E 3, is an AI model that generates images from text descriptions. It is known for its creativity, flexibility, and ability to produce detailed and varied image styles. DALL-E has applications in artistic creation, advertising, media, education, and research.

```en
Text to Image Conversion: Generates images based on user-provided text descriptions.
Creativity and Flexibility: Combines concepts to create unique visual works.
Variety and Detail: Produces multiple styles and handles complex, detailed descriptions.
Application Potential:
  - Artistic Creation: Exploring new ideas and visual expressions.
  - Advertising and Media: Generating theme-specific images.
  - Education and Entertainment: Creating instructional or entertainment content.
  - Research and Exploration: Investigating AI in visual arts.
```

--------------------------------

### Load and Import Plugins

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/04/PlannerWithSK.ipynb

Loads and imports various plugins (custom, writer, email, translate) into the Semantic Kernel. It demonstrates both importing native plugins and semantic plugins from specified directories.

```python
#custom_plugin = kernel.import_native_skill_from_directory(base_skills_directory , "APIPlugin")
# custom_plugin = kernel.import_plugin(custom_plugin.CustomPlugin(), plugin_name="CustomPlugin")  #.import_native_skill_from_directory(base_plugin , "APIPlugin")
# writer_plugin = kernel.import_semantic_plugin_from_directory(base_skills_directory, "WriterPlugin")
# email_plugin = kernel.import_semantic_plugin_from_directory(base_skills_directory, "EmailPlugin")
# translate_plugin = kernel.import_semantic_plugin_from_directory(base_skills_directory, "TranslatePlugin")


custom_plugin = kernel.add_plugin(custom_plugin.CustomPlugin(), "CustomPlugin")
writer_plugin = kernel.add_plugin(parent_directory=base_skills_directory,plugin_name ="WriterPlugin")
email_plugin = kernel.add_plugin(parent_directory=base_skills_directory,plugin_name ="EmailPlugin")
translate_plugin = kernel.add_plugin(parent_directory=base_skills_directory,plugin_name ="TranslatePlugin")
```

--------------------------------

### Register Memory Store with Kernel

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Registers the initialized Qdrant memory store with the Semantic Kernel instance.

```python
kernel.register_memory_store(memory_store=qdrant_store)
```

--------------------------------

### Semantic Kernel Core Concepts

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates fundamental concepts of the Semantic Kernel, including creating a kernel, loading plugins, and invoking functions. Essential for understanding the basic building blocks of the framework.

```java
import com.microsoft.semantickernel.Kernel;

// Initialize the kernel
Kernel kernel = Kernel.builder().build();

// Load a plugin (e.g., from a directory)
// kernel.importSemanticSkillFromDirectory("plugins", "MySkill");

// Invoke a function
// var result = kernel.invoke("MySkill", "MyFunction", "Hello");
// System.out.println(result);
```

--------------------------------

### GPT-4V Capabilities

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/en/00.IntroduceLLM.md

GPT-4 Turbo with Vision (GPT-4V) is an advanced multimodal model capable of understanding and analyzing images. It excels at object detection, text recognition (OCR), face recognition, solving CAPTCHAs, and geolocation. However, it may struggle with complex scientific diagrams or images with overlapping text.

```en
Object Detection: Identifies common objects like cars, animals, and household items.
Text Recognition: Extracts printed or handwritten text from images (OCR).
Face Recognition: Detects and analyzes facial features, including gender, age, and racial attributes.
CAPTCHA Solving: Solves text- and image-based CAPTCHAs, demonstrating visual reasoning.
Geolocation: Identifies geographical locations from landscape images.
Limitations: Performs poorly on complex scientific diagrams, medical scans, or images with multiple overlapping text components.
```

--------------------------------

### Semantic Kernel Core Concepts

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates fundamental concepts of the Semantic Kernel, including creating a kernel, loading plugins, and invoking functions. Essential for understanding the basic building blocks of the framework.

```java
import com.microsoft.semantickernel.Kernel;

// Initialize the kernel
Kernel kernel = Kernel.builder().build();

// Load a plugin (e.g., from a directory)
// kernel.importSemanticSkillFromDirectory("plugins", "MySkill");

// Invoke a function
// var result = kernel.invoke("MySkill", "MyFunction", "Hello");
// System.out.println(result);
```

--------------------------------

### Import Custom Plugin

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/04/PlannerWithSK.ipynb

Imports a custom plugin into the Semantic Kernel. This example shows importing a plugin defined in a local Python file.

```python
import APIPlugin.CustomPlugin as custom_plugin
```

--------------------------------

### Initializing Sequential Planner

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/java/04/PlannerWithSK.ipynb

This Java code initializes a `SequentialPlanner` with a given `Kernel` instance and specific `SequentialPlannerRequestSettings`. The planner is used to create execution plans for AI tasks.

```Java
private static SequentialPlanner initPlanner(Kernel kernel, int maxTokens) {
    return new SequentialPlanner(kernel, new SequentialPlannerRequestSettings(
            null,
            100,

```

--------------------------------

### Qdrant VectorParams Import

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/notebook.ipynb

Imports the VectorParams class for configuring vector storage in Qdrant.

```java
import io.qdrant.client.grpc.Collections.VectorParams;
```

--------------------------------

### Install Python OpenAI SDK

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/en/01.UsingAzureOpenAIServiceWithSDK.md

Installs or upgrades the OpenAI Python SDK to the latest version. This is a prerequisite for using the OpenAI Python client.

```python
! pip install openai -U
```

--------------------------------

### Semantic Kernel Core Concepts

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates fundamental concepts of the Semantic Kernel, including creating a kernel, loading plugins, and invoking functions. Essential for understanding the basic building blocks of the framework.

```python
from semantic_kernel import Kernel

# Initialize the kernel
kernel = Kernel()

# Load a plugin (e.g., from a directory)
# kernel.import_semantic_skill_from_directory("plugins", "MySkill")

# Invoke a function
# result = await kernel.run_async("MySkill", "MyFunction", input_str="Hello")
# print(result)
```

--------------------------------

### Define Plugin Directory

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Specifies the base directory where Semantic Kernel plugins are located.

```python
base_plugin = "./plugins"
```

--------------------------------

### Initialize Semantic Text Memory

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/notebook.ipynb

Initializes SemanticTextMemory, linking the Qdrant storage with the previously configured embedding generator.

```python
memory = SemanticTextMemory(storage=qdrant_store, embeddings_generator=embedding_gen)
```

--------------------------------

### Importing Sequential Planner Libraries

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/java/04/PlannerWithSK.ipynb

This snippet imports necessary classes for using the Sequential Planner in Semantic Kernel, including `SequentialPlanner` and `SequentialPlannerRequestSettings`.

```Java
import com.microsoft.semantickernel.planner.sequentialplanner.SequentialPlanner;
import com.microsoft.semantickernel.planner.sequentialplanner.SequentialPlannerRequestSettings;


```

--------------------------------

### Run .NET Project

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop3/dotNETAgent/plugins/CodePlugin/dotNET/skprompt.txt

Executes a .NET project. This command builds the project if necessary and then runs the compiled output.

```bash
dotnet run --project ./{{projectName}}
```

--------------------------------

### Initialize Knowledge Base List

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/notebook.ipynb

Initializes an empty list that will be used to store processed data from files.

```python
kblist = []
```

--------------------------------

### Print Plan Steps

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/04/PlannerWithSK.ipynb

Iterates through the steps of a generated plan and prints a description of each step, including the function it uses and its parameters. This helps in understanding the execution flow.

```python
for step in original_plan._steps:
    print(
        f"- {step.description.replace('.', '') if step.description else 'No description'} using {step.metadata.fully_qualified_name} with parameters: {step.parameters}"
    )
```

--------------------------------

### Semantic Kernel: Orchestration (C#)

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates orchestration in Semantic Kernel using C#. This example shows how to define a sequence of operations and execute them as a plan.

```csharp
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Orchestration;

var kernel = Kernel.CreateBuilder().Build();

// Define functions (e.g., summarize, translate)
kernel.ImportPluginFromFunctions(
    new[] {
        kernel.CreateFunctionFromPrompt("Summarize: {{$input}}", description: "Summarize the input text."),
        kernel.CreateFunctionFromPrompt("Translate to French: {{$input}}", description: "Translate the input text to French.")
    },
    pluginName: "MyFunctions"
);

// Create a plan
var plan = kernel.CreateNewPlan();
plan.AddFunction("MyFunctions", "Summarize");
plan.AddFunction("MyFunctions", "Translate");

// Execute the plan
var context = new ContextVariables("This is a long piece of text that needs to be summarized and translated.");
var result = await kernel.RunAsync(plan, context);

Console.WriteLine(result);
```

--------------------------------

### Install OpenAI Python SDK

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/cn/01.UsingAzureOpenAIServiceWithSDK.md

Installs the latest version of the OpenAI Python SDK, which is used to interact with both OpenAI and Azure OpenAI Service.

```python
! pip install openai -U
```

--------------------------------

### Create Formatted KB List

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/notebook.ipynb

Creates a new list of strings where each string is a concatenation of 'kb' and 'content' from the KBInfo objects.

```java
List<String> kbResultList =  new ArrayList<String>();

for (KBInfo info : kbList) {
    kbResultList.add(info.kb+"-"+info.content);
}
```

--------------------------------

### Defining Plugin Directory

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/dotNET/04/PlannerWithSK.ipynb

Specifies the relative path to the directory containing Semantic Kernel plugins.

```C#
var pluginDirectory = Path.Combine("../../..", "plugins");
```

--------------------------------

### Initialize Knowledge Base List

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/dotNET/workshop1/data/notebook.ipynb

Initializes an empty list to store processed data for the knowledge base.

```python
kblist = []
```

--------------------------------

### Initialize Semantic Kernel and AI Services

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/05/EmbeddingsWithSK.ipynb

Initializes the Semantic Kernel and configures Azure OpenAI chat and embedding services. It demonstrates how to add these services to the kernel instance.

```python
kernel = sk.Kernel()

chat_service_id = "default"
embed_service_id="embedding"

oai_chat_service = AzureChatCompletion(
        service_id=chat_service_id,
        env_file_path=".env"
)
embedding_gen = AzureTextEmbedding(
        service_id=embed_service_id,
        env_file_path=".env"
)



kernel.add_service(oai_chat_service)
kernel.add_service(embedding_gen)



# kernel.add_chat_service("azure_chat_competion_service", AzureChatCompletion("Your Azure OpenAI Service gpt-35-turbo-16k Model Delployment Name",endpoint,api_key=api_key,api_version = "2023-12-01-preview"))


# kernel.add_text_embedding_generation_service(
#         "embeddings_services", AzureTextEmbedding("Your Azure OpenAI Service text-embedding-ada-002 Model Delployment Name", endpoint,api_key=api_key,api_version = "2023-12-01-preview")
# )
```

--------------------------------

### Initialize Sequential Planner

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/04/PlannerWithSK.ipynb

Creates an instance of the SequentialPlanner, which is used to create plans for executing a series of AI tasks. It requires the initialized Kernel and a service ID.

```python
from semantic_kernel.planners import SequentialPlanner

planner = SequentialPlanner(kernel, service_id)
```

--------------------------------

### skprompt.txt Example

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/docs/en/03.Plugins.md

Defines a prompt template for a plugin, specifying input parameters using double curly braces.

```txt
Translate {{$input}} into {{$language}}
```

--------------------------------

### Semantic Kernel Core Concepts

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/java/workshop1/plugins/AnswerPlugin/Summary/skprompt.txt

Demonstrates fundamental concepts of the Semantic Kernel, including creating a kernel, loading plugins, and invoking functions. Essential for understanding the basic building blocks of the framework.

```typescript
import { Kernel } from "@microsoft/semantic-kernel";

// Initialize the kernel
const kernel = new Kernel();

// Load a plugin (e.g., from a directory)
// await kernel.importSemanticSkillFromDirectory("plugins", "MySkill");

// Invoke a function
// const result = await kernel.invoke("MySkill", "MyFunction", { input: "Hello" });
// console.log(result);
```

--------------------------------

### Define Function Tools for AI

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/notebooks/python/03/FunctionCallWithSK.ipynb

Defines a list of tools (functions) that the AI model can use, including their names, descriptions, and parameters. This example defines a 'search_hotels' function.

```python
tools = [
    {
        "type": "function",
        "function": {
            "name": "search_hotels",
            "description": "Retrieves hotels from the search index based on the parameters provided",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The location of the hotel (i.e. Seattle, WA)"
                    },
                    "max_price": {
                        "type": "number",
                        "description": "The maximum price for the hotel"
                    },
                    "features": {
                        "type": "string",
                        "description": "A comma separated list of features (i.e. beachfront, free wifi, etc.)"
                    }
                },
                "required": ["location"]
            }
        },
    }
]
```

--------------------------------

### Initialize Semantic Kernel and Azure OpenAI Settings

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop1/notebook.ipynb

Initializes the Semantic Kernel instance and retrieves Azure OpenAI service settings (deployment name, API key, endpoint) from environment variables.

```python
kernel = sk.Kernel()
deployment, api_key, endpoint = sk.azure_openai_settings_from_dot_env()
```

--------------------------------

### Convert Markdown to PPTX using Marp

Source: https://github.com/microsoft/semantickernelcookbook/blob/main/workshop/python/workshop2/genppt_notebook.ipynb

Uses the Marp CLI tool to convert the 'myfile.md' Markdown file into a PowerPoint presentation ('myfile.pptx').

```bash
! marp myfile.md -o myfile.pptx
```