KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#developer-tools #dsh #dsh-plugin #ai-agent #claude-code #codex #typescript #ai-agents #mcp #cli #rust #deepseek-harness

AI-Builders-Bootcamp-2

★ 48 Open GitHub ↗

Code repository for AI Builders Bootcamp #2

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# AI-Builders-Bootcamp-2
Code repository for AI Builders Bootcamp #2.

See Cohort 1 examples [here](https://github.com/ShawhinT/AI-Builders-Bootcamp-1).

Course homepage on Maven: https://maven.com/shaw-talebi/ai-builders-bootcamp

## Lightning Lesson: How to Build a Resume Optimizer with AI
Building a resume optimization tool using Python, OpenAI's API, and Gradio.

Examples:
- [Notebook version](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/lightning-lesson/resume_optimizer_example.ipynb)
- [Gradio UI version](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/lightning-lesson/resume_optimizer_UI.ipynb)

## Session 1: Introduction, Software 1.0
Getting started with AI and building basic automation scripts with Python.

Examples:
- [Scraping AI job board](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-1/example_1-scrape_job_board.ipynb)
- [Building Dashboard with Plotly Dash](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-1/example_2-ai_job_dashboard.ipynb)

## Session 2: Software 2.0, Data Engineering, Machine Learning
Building ETL pipelines for machine learning projects.

Examples:
- [Scraping AI Job Board (1000 jobs)](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-2/example_0-extract_job_data.py)
- [ETL of AI Job Data](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-2/example_1-ai_job_etl.ipynb)
- [Training AI Job Classifier](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-2/example_2-train_job_classifier.ipynb)

## Session 3: Software 3.0, Foundation Models, Prompt Engineering
Here, we begin building AI systems with LLMs. Unlike machine learning, we don't need datasets to get started.

Examples:
- [Research paper summarizer](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-3/example_1-paper_summarizer.ipynb)
- [Text classifier](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-3/example_2-text-classifier.ipynb)
- [Local visual QA with LLaMA 3.2 Vision](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-3/example_3-local_visual_QA.ipynb)

## Session 4: Software 3.0, RAG, Text Embeddings
Prompting LLMs ChatGPT-style only scratches the surface of what we can use modern language models for. We can also leverage RAG to improve model performance and text embeddings to make text computable.

Examples:
- [Analyzing Unstructured Survey Data](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-4/example_1-unstructured_survey_analysis.ipynb)
- [Semantic Search Over Blogs](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-4/example_2-blog_semantic_search.ipynb)
- [Blog Series QA Assistant (with RAG)](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-4/example_3-blog_QA_RAG.ipynb)

## Session 5: Software 3.0, Fine-tuning
Although LLMs can solve a wide range of problems out-of-the-box, there are situations where more model customization is required. This can be achieved through model fine-tuning, which involves adapting a model to a particular use case through additional training.

Examples
- [Fine-tuning a LinkedIn Post Writer](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-5/example_1-linkedin_post_writer.ipynb)
- [Fine-tuning BERT for Text Classification](https://github.com/ShawhinT/AI-Builders-Bootcamp-2/blob/main/session-5/example_2-finetune_bert_classifier.ipynb)

AI-Builders-Bootcamp-2

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README