Python Learning Path Generator-- A personalized roadmap for Python Learners
A Retrieval-Augmented Generation (RAG) based personalized Python learning path generator built with Streamlit. This application creates unique, explainable learning roadmaps tailored to each user's goals, skill level, and learning style.
๐ Features
Personalized Learning Paths
- Career-Focused: Choose from 6 career tracks (Web Dev, Data Science, ML, etc.)
- Skill-Adaptive: Adjusts to your current level (Absolute Beginner โ Advanced)
- Style-Matched: Project-Based, Theory-First, Balanced, or Challenge-Driven
- Objective-Oriented: Targets specific roles (Junior Dev, Data Scientist, ML Engineer, etc.)
Explainable AI
- Clear reasoning for every topic recommendation
- Transparent personalization factors
- Career outcome predictions
- Estimated timeline with study recommendations
Interactive UI
- Black/white theme for easy reading
- Dynamic weeks calculation based on your time commitment
- Expandable sections for each learning phase
- Project suggestions aligned with your goals
๐ Project Structure
python-learning-path/
โโโ app/
โ โโโ streamlit_app.py # Main Streamlit UI application
โโโ config/
โ โโโ settings.yaml # Configuration settings
โโโ knowledge_base/
โ โโโ python_topics.yaml # 51 Python topics with metadata
โโโ src/
โ โโโ retriever.py # Rule-based topic retrieval
โ โโโ generator.py # LLM integration (Groq API)
โ โโโ explainer.py # Explainable AI component
โโโ .gitignore # Git ignore rules
โโโ requirements.txt # Python dependencies
โโโ run_app.py # Launch script
โโโ README.md # This file
Prerequisites
- Python 3.12+
- pip or conda
Installation
- Clone the repository
git clone https://code.swecha.org/viswam/internships/icfai-ip-2-hackathon-17-jan/python_learning_path_generator.git
cd python_learning_path_generator/python-learning-path
- Create virtual environment
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies
pip install -r requirements.txt
- Set up Groq API Key (for LLM features)
# Option 1: Set as environment variable
export GROQ_API_KEY=your_api_key_here
# Option 2: Enter in the app's sidebar (API Configuration)
Get your free Groq API key at: https://console.groq.com/
- Run the application
# Using the run script (recommended)
python run_app.py
# OR using streamlit directly
PYTHONPATH=src streamlit run app/streamlit_app.py
# OR with custom port
python run_app.py --port 8501
- Open in browser
http://localhost:8501
๐ Knowledge Base
Topics Covered (51 total)
| Level |
Topics |
Description |
| Beginner |
10 |
Python basics, functions, data structures, Git, HTML/CSS |
| Intermediate |
34 |
OOP, Pandas, NumPy, Flask, APIs, Testing, Statistics |
| Advanced |
7 |
ML models, Deep Learning, Django, FastAPI, MLOps |
Career Tracks
- Web Development - Django, Flask, FastAPI, HTML/CSS
- Data Science & Analytics - Pandas, NumPy, Statistics, Visualization
- Machine Learning & AI - Scikit-learn, TensorFlow, Deep Learning
- Automation & Scripting - Web scraping, Task automation, APIs
- Backend API Development - REST APIs, Authentication, Databases
- Scientific Computing - NumPy, SciPy, Mathematical computation
Learning Styles
- Project-Based: Learn by building real projects immediately
- Theory-First: Understand concepts deeply before coding
- Balanced: Mix of theory and practice
- Challenge-Driven: Learn through coding challenges
๐ฏ Career Objectives
| Objective |
Target Role |
Time to Job Readiness |
| Junior Developer |
Entry-level developer |
6-9 months |
| Mid-Level Developer |
Experienced developer |
12-24 months |
| Data Analyst |
Data interpretation role |
6-12 months |
| Data Scientist |
Advanced analytics role |
12-18 months |
| ML Engineer |
ML systems engineer |
18-24 months |
๐ก How It Work
RAG Pipeline
User Profile โ Retriever โ Generator โ Explainer โ Learning Path
โ โ โ โ โ
(Input) (Find topics) (LLM) (Explain) (Output)
Retrieval: Rule-based filtering finds relevant topics based on:
- Career goal alignment
- Current skill level
- Learning style preference
- Prerequisites ordering
Generation: LLM (Groq Llama 3.3 70B) synthesizes:
- Coherent learning phases
- Personalized explanations
- Project suggestions
- Milestones
Explanation: Transparent reasoning shows:
- Why each topic was included
- How personalization was applied
- Career outcome predictions
- Timeline estimates
Example Output
Your Personalized Path for Data Science
Based on your Beginner level and goal to become a Data Scientist,
we've created a custom learning journey with 29 topics across 3 phases.
Career Outcome: Ready for data science roles
Phase 1: Beginner Level (4 weeks @ 10h/week)
1. Python Basics - Foundational topic - start here
2. Control Flow & Logic - Building on your foundations
...
Phase 2: Intermediate Level (5 weeks @ 10h/week)
1. NumPy Fundamentals - Core intermediate topic
2. Pandas Core - Core intermediate topic
...
๐งช Testing
# Test the retriever with different skill levels
cd python-learning-path
PYTHONPATH=src python3 -c "
from retriever import UserProfile, generate_retrieval
profile = UserProfile(
skill_level='beginner',
career_goal='data_science',
learning_style='project_based',
time_availability='10 hours/week',
)
topics, _ = generate_retrieval(profile)
print(f'Retrieved {len(topics)} topics')
"
๐ฆ Dependencies
- streamlit - Web UI framework
- pyyaml - YAML parsing
- groq - LLM API integration
- httpx - Async HTTP client
See requirements.txt for full list.
๐ค Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature)
- Commit your changes (
git commit -m 'Add some AmazingFeature')
- Push to the branch (
git push origin feature/AmazingFeature)
- Open a Pull Request
๐ License
This project is licensed under the MIT License - see the LICENSE file for details.
๐ Acknowledgments