Snippet Name: Install_Dependencies_with_Python

Tags:

Created Date: 2025-06-16 13:12:43
Last Modified Date: 2025-05-31 10:32:18

Dependencies:

DBA Notes:

Sample Output:

Title: Install Dependencies with Python
Author: user
I have an example python notebook named 01-semantic-kernel.ipynb.  it has a collection of imports, but for a brand new user, they would need to call pip to install them, most likely. can i use a python script to call pip to install missing dependencies? for example, these are part of the script: import os  
from typing import Annotated
from openai import AsyncOpenAI

from dotenv import load_dotenv

from semantic_kernel.agents import ChatCompletionAgent, ChatHistoryAgentThread
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion
from semantic_kernel.functions import kernel_function

Author: ChatGPT
Yes, you can definitely write a Python script that checks for and installs missing dependencies using `pip`. There are a few ways to do this, but here???s a clean and beginner-friendly approach:

---

### ??? **Approach: Write a bootstrap Python script to install dependencies**
You can include this at the top of your notebook or in a separate script like `install_requirements.py`.

#### ???? Sample script:
```python
import subprocess
import sys

# List your required packages here
required_packages = [
    "openai",
    "python-dotenv",
    "semantic-kernel"
]

# Install each package if not already installed
for package in required_packages:
    try:
        __import__(package.split("-")[0])  # crude but works in most simple cases
    except ImportError:
        subprocess.check_call([sys.executable, "-m", "pip", "install", package])
```

---

### ?????? Explanation:
- `__import__(...)` checks if the base module (like `openai` or `dotenv`) is available.
- If not, `subprocess.check_call` uses the Python interpreter to run `pip install`.
- You can put this script in a separate file, or prepend it to the notebook.

---

### ???? Alternative: Use `requirements.txt`
You could also generate a `requirements.txt` file:
```text
openai
python-dotenv
semantic-kernel
```
And install everything using:
```python
subprocess.check_call([sys.executable, "-m", "pip", "install", "-r", "requirements.txt"])
```

---

Would you like a version that **auto-generates** the `requirements.txt` from your notebook imports?

Author: user
i typically like to add a section at the top called prerequisites, that would load the dependancies. i think the first example you gave me is fine

Author: ChatGPT
Perfect ??? adding a **"Prerequisites"** section at the top of the notebook with that logic is a great practice. It helps new users get started without worrying about missing packages.

Here???s a polished version of your "Prerequisites" section that you can copy-paste directly into the top of your notebook:

---

### ???? **Prerequisites (Auto-install missing packages)**

```python
# Prerequisites: Ensure required packages are installed
import subprocess
import sys

required_packages = [
    "openai",           # For OpenAI API access
    "python-dotenv",    # For loading .env files
    "semantic-kernel"   # Microsoft Semantic Kernel
]

for package in required_packages:
    try:
        __import__(package.split("-")[0])
    except ImportError:
        print(f"Installing missing package: {package}")
        subprocess.check_call([sys.executable, "-m", "pip", "install", package])
```

---

This section:
- Checks if each base module is importable.
- Installs it with `pip` if not.
- Is notebook-friendly and gives output in the cell.

Let me know if you want a version that checks for version constraints too, like `openai==1.16.1`, or if you want to make it reusable across multiple notebooks.