### Install and Run TypeScript Examples

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/AGENTS.md

Use these commands to install dependencies, build, and start TypeScript examples.

```bash
npm install
npm run build
npm start
```

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

### Node.js/TypeScript Project Setup

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/AGENTS.md

Install root-level Node.js dependencies and then navigate to individual lesson directories to install project-specific dependencies.

```bash
# Install root-level dependencies (for documentation tooling)
npm install

# For individual lesson TypeScript examples, navigate to the specific lesson:
cd 06-text-generation-apps/typescript/recipe-app
npm install
```

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

### Setup Virtual Environment and Install OpenAI

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/pcm/06-text-generation-apps/python/oai-assigment.ipynb

Use these commands to create a virtual environment and install the OpenAI Python package. Note the Windows-specific activation command.

```bash
# Create virtual environment
! python -m venv venv
# Activate virtual environment
! source venv/bin/activate
# Install openai package
! pip install openai
```

```bash
venv\Scripts\activate
```

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

### Python Virtual Environment Setup

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/AGENTS.md

Set up a Python virtual environment and install project dependencies using pip.

```bash
# Create virtual environment
python3 -m venv venv

# Activate virtual environment
# On macOS/Linux:
source venv/bin/activate
# On Windows:
virtualenv\Scripts\activate

# Install dependencies
pip install -r requirements.txt
```

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

### Install faiss-cpu

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/20-mistral/README.md

Installs the faiss-cpu package, which is used as a vector store in the RAG example.

```python
pip install faiss-cpu
```

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

### Create Python Web API with Flask

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/05-advanced-prompts/README.md

Initial Flask application setup for API routes. Ensure Flask is installed.

```python
import flask
app = Flask(__name__)

@app.route('/products')
def products():
    return 'Products'

@app.route('/customers')
def customers():
    return 'Customers'
```

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

### Install ONNX Runtime

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/19-slm/README.md

Install the ONNX Runtime library using pip.

```Python
pip install onnxruntime
```

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

### Start JupyterHub Server

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/00-course-setup/README.md

Navigate to your course directory in the terminal and run this command to start a local JupyterHub instance.

```bash
jupyterhub
```

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

### Start Jupyter Notebook Server

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/00-course-setup/README.md

Navigate to your course directory in the terminal and run this command to start a local Jupyter Notebook instance.

```bash
jupyter notebook
```

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

### Install OpenCV

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/19-slm/python/phi35-vision-demo.ipynb

Install the OpenCV library for video processing. This is a prerequisite for the keyframe extraction function.

```python
# pip install opencv-python
```

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

### Install Flash Attention

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/19-slm/python/phi35_moe_demo.ipynb

Installs Flash Attention, an optimized attention mechanism that can speed up training and inference.

```python
# pip install flash-attn --no-build-isolation
```

```python
# ! pip install flash_attn -U
```

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

### Set up Virtual Environment and Install OpenAI

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/06-text-generation-apps/README.md

Create a virtual environment and install the necessary OpenAI Python package. Use `venv\Scripts\activate` on Windows.

```bash
python -m venv venv
source venv/bin/activate
pip install openai
```

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

### Generate Python Web API Code

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/05-advanced-prompts/README.md

Basic Python Web API generation using Flask. This example includes a simple GET route and placeholder for data processing. Ensure Flask is installed.

```python
# Import necessary modules
import flask
from flask import request, jsonify

# Create a Flask app
app = flask.Flask(__name__)

# Create a route for the API
@app.route('/api', methods=['GET'])
def api():
    # Get the data from the request
    data = request.args

    # Process the data
    result = process_data(data)

    # Return the result as JSON
    return jsonify(result)

```

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

### Clone Repository and Navigate

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/00-course-setup/02-setup-local.md

Use these commands to clone the course repository and navigate into the project directory.

```bash
git clone https://github.com/<your-github>/generative-ai-for-beginners
cd generative-ai-for-beginners
```

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

### Set up Python virtual environment and install libraries

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/09-building-image-applications/python/aoai-assignment.ipynb

Create a virtual environment for your project and install the necessary Python libraries. This ensures dependency isolation.

```python
# create virtual env
! python3 -m venv venv
# activate environment
! source venv/bin/activate
# install libraries
# pip install -r requirements.txt, if using a requirements.txt file 
! pip install python-dotenv openai pillow requests
```

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

### Clone Repository and Setup Environment

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/AGENTS.md

Clone the repository, copy the environment template, and edit the .env file with your API keys and endpoints.

```bash
# Clone the repository
git clone https://github.com/microsoft/generative-ai-for-beginners.git
cd generative-ai-for-beginners

# Copy environment template
cp .env.copy .env
# Edit .env with your API keys and endpoints
```

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

### Few-Shot Prompting Example

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/05-advanced-prompts/README.md

Provide examples within the prompt to guide the LLM's output format, style, or task understanding. This is useful when you need the LLM to adhere to a specific pattern or tone.

```text
Write a poem in the style of Shakespeare. Here are a few examples of Shakespearean sonnets.:
  Sonnet 18: 'Shall I compare thee to a summer's day? Thou art more lovely and more temperate...'
  Sonnet 116: 'Let me not to the marriage of true minds Admit impediments. Love is not love Which alters when it alteration finds...'
  Sonnet 132: 'Thine eyes I love, and they, as pitying me, Knowing thy heart torment me with disdain,...
  Now, write a sonnet about the beauty of the moon.
```

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

### Build Documentation Site

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/AGENTS.md

Execute this command to generate a PDF from the documentation if needed.

```bash
# Generate PDF from documentation (if needed)
npm run convert
```

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

### Validate OpenAI API Setup

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/04-prompt-engineering-fundamentals/python/oai-assignment.ipynb

Verify your OpenAI API endpoint and key setup by sending a basic prompt and checking the completion. Ensure you have the 'openai' and 'python-dotenv' libraries installed and your API key configured.

```python
# The OpenAI SDK was updated on Nov 8, 2023 with new guidance for migration
# See: https://github.com/openai/openai-python/discussions/742

## Updated
import os
from openai import OpenAI
from dotenv import load_dotenv
load_dotenv()

client = OpenAI()

deployment="gpt-3.5-turbo"

## Updated
def get_completion(prompt):
    messages = [{"role": "user", "content": prompt}]       
    response = client.chat.completions.create(   
        model=deployment,                                         
        messages=messages,
        temperature=0, # this is the degree of randomness of the model's output
        max_tokens=1024
    )
    return response.choices[0].message.content

## ---------- Call the helper method

### 1. Set primary content or prompt text
text = f"""
oh say can you see
"""

### 2. Use that in the prompt template below
prompt = f"""
```{text}```
"""

## 3. Run the prompt
response = get_completion(prompt)
print(response)
```

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

### Few-Shot Prompt Example with Shakespearean Style

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/zh-CN/05-advanced-prompts/README.md

This prompt style guides the model by providing examples of the desired output format, context, or style. It's useful for tasks requiring specific creative or structural adherence.

```text
Write a poem in the style of Shakespeare. Here are some examples of Shakespearean sonnets:
Sonnet 18: "Shall I compare thee to a summer's day? Thou art more lovely and more temperate..."
Sonnet 116: "Let me not to the marriage of true minds Admit impediments. Love is not love Which alters when it alteration finds..."
Sonnet 132: "Thine eyes I love, and they in my love are.
My love's dear eyes in praise do nothing else...
Now write a sonnet about the beauty of the moon.
```

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

### Clone Repository and Navigate

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/00-course-setup/README.md

Clone the course repository to your local machine using git and then navigate into the cloned directory. This is the first step to running the code locally.

```shell
git clone https://github.com/microsoft/generative-ai-for-beginners
cd generative-ai-for-beginners
```

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

### Run Python Example Script

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/AGENTS.md

Navigate to the lesson directory and execute a Python script using the python interpreter.

```bash
# Navigate to lesson directory
cd 06-text-generation-apps/python

# Run a Python script
python aoai-app.py
```

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

### Initialize OpenAI Client and Generate Recipes

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/06-text-generation-apps/python/oai-assigment.ipynb

Loads environment variables, initializes the OpenAI client, and prompts the user for recipe details. It then constructs a prompt and uses the client to generate recipes.

```python
from dotenv import load_dotenv
import os
from openai import OpenAI

# load environment variables from .env file
load_dotenv()

client = OpenAI(
  api_key = os.environ['OPENAI_API_KEY']
)

deployment = "gpt-3.5-turbo"

no_recipes = input("No of recipes (for example, 5: ")

ingredients = input("List of ingredients (for example, chicken, potatoes, and carrots: ")

# interpolate the number of recipes into the prompt an ingredients
prompt = f"Show me {no_recipes} recipes for a dish with the following ingredients: {ingredients}. Per recipe, list all the ingredients used"
messages = [{"role": "user", "content": prompt}]  

# make completion
completion = client.chat.completions.create(model=deployment, messages=messages, max_tokens=600)

# print response
print(completion.choices[0].message.content)
```

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

### Generate Product Names using OpenAI Chat API

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/07-building-chat-applications/python/oai-assignment.ipynb

This example demonstrates generating creative product names based on a description and seed words. The prompt includes examples to guide the model. 'client' and 'model' must be initialized.

```python
prompt = "Product description: A home milkshake maker\nSeed words: fast, healthy, compact.\nProduct names: HomeShaker, Fit Shaker, QuickShake, Shake Maker\n\nProduct description: A pair of shoes that can fit any foot size.\nSeed words: adaptable, fit, omni-fit."
```

```python
#Setting a few additional, typical parameters during API Call

response = client.chat.completions.create(
  model=model,
  messages = [{"role":"system", "content":"You are a helpful assistant."},
               {"role":"user","content":prompt}])

response.choices[0].message.content
```

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

### Initialize OpenAI Client and Load Environment Variables

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/08-building-search-applications/python/oai-solution.ipynb

Sets up the OpenAI client by loading the API key from a .env file. Asserts that the API key is present before proceeding. Defines model and constants for similarity threshold and dataset name.

```python
import os
import pandas as pd
import numpy as np
from openai import OpenAI
from dotenv import load_dotenv

load_dotenv()

API_KEY = os.getenv("OPENAI_API_KEY","")
assert API_KEY, "ERROR: OpenAI Key is missing"

client = OpenAI(
    api_key=API_KEY
    )

model = 'text-embedding-ada-002'

SIMILARITIES_RESULTS_THRESHOLD = 0.75
DATASET_NAME = "../embedding_index_3m.json"
```

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

### Instruction-Based Prompting for Summarization

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/pcm/04-prompt-engineering-fundamentals/python/oai-assignment.ipynb

Use the 'text' variable for content and the 'prompt' variable for instructions to guide the model. This example demonstrates summarizing text for a specific audience (a second-grader).

```python
# Test Example
# https://platform.openai.com/playground/p/default-summarize

## Example text
text = f"""
Jupiter is the fifth planet from the Sun and the \             largest in the Solar System. It is a gas giant with \             a mass one-thousandth that of the Sun, but two-and-a-half \             times that of all the other planets in the Solar System combined. \             Jupiter is one of the brightest objects visible to the naked eye \             in the night sky, and has been known to ancient civilizations since \             before recorded history. It is named after the Roman god Jupiter.[19] \             When viewed from Earth, Jupiter can be bright enough for its reflected \             light to cast visible shadows,[20] and is on average the third-brightest \             natural object in the night sky after the Moon and Venus.
"""


```

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

### Initialize OpenAI Client

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/08-building-search-applications/python/oai-assignment.ipynb

Sets up the OpenAI client by loading the API key from environment variables. Ensure your OPENAI_API_KEY is set in your .env file.

```python
import os
from openai import OpenAI
from dotenv import load_dotenv
import numpy as np
load_dotenv()

API_KEY = os.getenv("OPENAI_API_KEY","")
assert API_KEY, "ERROR: OpenAI Key is missing"

client = OpenAI(
    api_key=API_KEY
    )
```

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

### Study Buddy Prompt Example

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/06-text-generation-apps/README.md

A starter prompt for a 'study buddy' application focused on the Python language. This prompt guides the AI to provide lessons, explanations, and code exercises.

```text
- "You're an expert on the Python language

    Suggest a beginner lesson for Python in the following format:

    Format:
    - concepts:
    - brief explanation of the lesson:
    - exercise in code with solutions"
```

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

### Initialize OpenAI Client

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/07-building-chat-applications/python/oai-assigment-simple.ipynb

Sets up the OpenAI client using an API key loaded from environment variables. Ensure the OPENAI_API_KEY is set.

```python
import os
from openai import OpenAI
from dotenv import load_dotenv

load_dotenv()

API_KEY = os.getenv("OPENAI_API_KEY","").strip()
assert API_KEY, "ERROR: OpenAI Key is missing"
client = OpenAI(
    api_key=API_KEY
    )

model = "gpt-3.5-turbo"
```

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

### Instruction-Based LLM Tasks

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/04-prompt-engineering-fundamentals/python/aoai-assignment.ipynb

Utilize the 'text' variable for primary content and the 'prompt' variable for instructions to guide the LLM. This example demonstrates summarizing text for a specific audience (second-grade student).

```python
# Test Example
# https://platform.openai.com/playground/p/default-summarize

```

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

### Generate Product Names Prompt

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/07-building-chat-applications/python/aoai-assignment.ipynb

Constructs a prompt for generating product names by providing a product description and seed words, along with examples. Use this to guide the model's creative output.

```python
prompt = "Product description: A home milkshake maker\nSeed words: fast, healthy, compact.\nProduct names: HomeShaker, Fit Shaker, QuickShake, Shake Maker\n\nProduct description: A pair of shoes that can fit any foot size.\nSeed words: adaptable, fit, omni-fit."

print(prompt)
```

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

### Chain-of-Thought Prompting for Mathematical Problems

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/zh-CN/05-advanced-prompts/README.md

This technique guides the LLM by showing it how to break down a problem into steps, similar to providing a worked example. Use this for complex reasoning or calculation tasks where intermediate steps are crucial for accuracy.

```text
Lisa has 7 apples, threw away 1 apple, gave 4 apples to Bart, and Bart gave one back:
7 - 1 = 6
6 - 4 = 2
2 + 1 = 3  
Alice has 5 apples, threw away 3 apples, gave 2 apples to Bob, and Bob gave one back: Alice has how many apples?
```

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

### Initialize OpenAI Client and Load Environment Variables

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/11-integrating-with-function-calling/python/oai-assignment.ipynb

Import necessary libraries (os, json, OpenAI, dotenv) and load environment variables for API key management. Initialize the OpenAI client and set the deployment model.

```python
import os
import json
from openai import OpenAI
from dotenv import load_dotenv
load_dotenv()

client = OpenAI()

deployment="gpt-3.5-turbo"
```

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

### System Message for Agent

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/fr/19-slm/python/phi35_moe_demo.ipynb

Defines a system message that guides an AI agent, outlining available tools and the required JSON format for tool usage. This message includes examples for using 'Blog' and 'Translate' tools.

```python
sys_msg = """You are a helpful AI assistant, you are an agent capable of using a variety of tools to answer a question. Here are a few of the tools available to you:

- Blog: This tool helps you describe a certain knowledge point and content, and finally write it into Twitter or Facebook style content
- Translate: This is a tool that helps you translate into any language, using plain language as required

To use these tools you must always respond in JSON format containing \"tool_name\" and \"input\" key-value pairs. For example, to answer the question, \"Build Muliti Agents with MOE models\" you must use the calculator tool like so:

```json

{
    \"tool_name\": \"Blog\",
    \"input\": \"Build Muliti Agents with MOE models\"
}

```

Or to translate the question \"can you introduce yourself in Chinese\" you must respond:

```json

{
    \"tool_name\": \"Search\",
    \"input\": \"can you introduce yourself in Chinese\"
}

```

Remember just output the final result, output in JSON format containing \"agentid\",\"tool_name\" , \"input\" and \"output\"  key-value pairs .:

```json

[


{
    \"agentid\": \"step1\",
    \"tool_name\": \"Blog\",
    \"input\": \"Build Muliti Agents with MOE models\",
    \"output\": \".........\"
},

{
    \"agentid\": \"step2\",
    \"tool_name\": \"Search\",
    \"input\": \"can you introduce yourself in Chinese\",
    \"output\": \".........\"
},
{
    \"agentid\": \"final\"
    \"tool_name\": \"Result\",
    \"output\": \".........\"
}
]

```

The users answer is as follows.
"""
        }          ]    },    {      
```

```python
def instruction_format(sys_message: str, query: str):
    # note, don't "</s>" to the end
    return f'<|system|> {sys_message} <|end|>
<|user|> {query} <|end|>
<|assistant|>'
```

```python
query ='Write something about Generative AI with MOE , translate it to Chinese'
```

```python
input_prompt = instruction_format(sys_msg, query)
```

```python
input_prompt
```

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

### Initialize Azure OpenAI Client and Load Environment Variables

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/08-building-search-applications/python/aoai-solution.ipynb

Sets up the Azure OpenAI client using API key and deployment details from environment variables. Ensure your .env file contains AZURE_OPENAI_API_KEY and AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT.

```python
import os
import pandas as pd
import numpy as np
from openai import AzureOpenAI
from dotenv import load_dotenv

load_dotenv()

client = AzureOpenAI(
  api_key=os.environ['AZURE_OPENAI_API_KEY'],  # this is also the default, it can be omitted
  api_version = "2023-05-15"
  )

model = os.environ['AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT']

SIMILARITIES_RESULTS_THRESHOLD = 0.75
DATASET_NAME = "../embedding_index_3m.json"

```

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

### Build and Run TypeScript Application

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/AGENTS.md

Navigate to the TypeScript application directory, build the project, and then start the application.

```bash
# Navigate to TypeScript app directory
cd 06-text-generation-apps/typescript/recipe-app

# Build the TypeScript code
npm run build

# Run the application
npm start
```

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

### Install OpenAI Package

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/06-text-generation-apps/python/aoai-assignment.ipynb

Use these commands to create a virtual environment and install the OpenAI Python package. Ensure you activate the environment before installation. Note the Windows-specific activation command.

```python
# Create virtual environment
! python -m venv venv
# Activate virtual environment
! source venv/bin/activate
# Install openai package
! pip install openai
```

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

### Set and Run a Simple Prompt

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/04-prompt-engineering-fundamentals/python/oai-assignment.ipynb

Construct a prompt for summarization and execute it using the get_completion function. Ensure the text to be summarized is properly formatted within the prompt.

```python
prompt = f"
Summarize content you are provided with for a second-grade student.
```{text}```
"

## Run the prompt
response = get_completion(prompt)
print(response)
```

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

### Verify Conda Installation

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/00-course-setup/02-setup-local.md

Check if Conda is installed and accessible from the command line.

```bash
conda --version
```

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

### Initialize Azure OpenAI Client

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/11-integrating-with-function-calling/python/aoai-assignment.ipynb

Set up the Azure OpenAI client using API key, endpoint, and deployment name. Ensure environment variables are loaded.

```python
import os
import json
from openai import AzureOpenAI
from dotenv import load_dotenv
load_dotenv()

client = AzureOpenAI(
  api_key=os.environ['AZURE_OPENAI_API_KEY'],  # this is also the default, it can be omitted
  api_version = "2023-07-01-preview"
  )

deployment=os.environ['AZURE_OPENAI_DEPLOYMENT']
```

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

### Verify Docker Installation

Source: https://github.com/microsoft/generative-ai-for-beginners/blob/main/00-course-setup/02-setup-local.md

Check if Docker is installed and accessible from the command line.

```bash
docker --version
```