How sachinchaurasia/python-ai-learning works
This repository is a week-by-week Python and AI learning collection, not one integrated application. Its independent lessons progress from programming and data handling through machine learning, deep learning, and LLM topics. The clearest runnable user-to-result flow in the sampled code is the Week 9 retrieval-augmented generation script: it loads text documents, chunks and embeds them, searches for context for a question, then requests and displays an LLM answer. Other scripts demonstrate separate prompt modes, JSON-oriented responses, and ML pipelines. The tree and samples do not establish shared runtime wiring between lessons.
Main entry points: rag2_app.py RAG Application · Functions_examples.py Python Lessons · Student_management.py Student Manager · MLPipelines.py ML Pipeline
Components 18
Python Foundations
- Python Lessons
Week1/Basics/Functions_examples.py - Student Manager
Week1/mini_projects/Student_management.py
Machine Learning
- ML Pipeline
Week5/MachineLearningPipeLinesD4/MLPipelines.py - Feature Engineering
Week5/Feature EngineeringD5/FeatureEngineering.py
LLM Applications
- Prompt Engineering
Week8/D7-Prompt_Engineering+LLM App.py - LLM Q&A
Week 9/Week9_Day3/week9_day3_llm.py - Multi-Mode LLM
Week 9/WEEK9_DAY4/week9_day4_MultiMode_LLM_Application.py - JSON Response
Week 9/Week9_Day5/week9_day5_LLM_JSON2.py
Retrieval
- RAG Application
Week 9/week9_Day7/rag2_app.py - Chunk Documents
Week 9/week9_Day7/rag2_app.py - Embed Text
Week 9/week9_Day7/rag2_app.py - Semantic Search
Week 9/week9_Day7/rag2_app.py - Build Context Prompt
Week 9/week9_Day7/rag2_app.py
Other components
- Learner
- Text Documents
- Question
- OpenAI API
- Displayed Answer
Connections 19
- Learner → Python Lessons: studies
- Learner → Student Manager: runs
- Learner → ML Pipeline: runs
- Learner → Feature Engineering: runs
- Learner → Prompt Engineering: studies
- Learner → LLM Q&A: asks
- Learner → Multi-Mode LLM: selects mode
- Learner → JSON Response: enters topic
- Text Documents → RAG Application: loads
- RAG Application → Chunk Documents: chunks
- Chunk Documents → Embed Text: encodes chunks
- Learner → RAG Application: runs
- Learner → Question: enters
- RAG Application → Embed Text: encodes question
- Embed Text → Semantic Search: compares vectors
- Semantic Search → Build Context Prompt: selects context
- RAG Application → Build Context Prompt: formats prompt
- RAG Application → OpenAI API: requests answer
- OpenAI API → Displayed Answer: returns response