A comprehensive collection of 90+ Jupyter notebooks covering essential AI/ML libraries and frameworks
This directory contains hands-on tutorials and practical examples for over 90 open-source AI/ML libraries. Each notebook provides step-by-step guidance, code examples, and real-world applications to help you master the most important tools in the AI ecosystem.
- AutoGen - Building collaborative AI agents in Python
- CrewAI - Multi-agent orchestration framework
- LangGraph - Multi-agent swarm systems
- Phidata - Production-ready AI agents
- Swarm Agents - OpenAI's experimental multi-agent framework
- Agency Swarm - Advanced AI agent framework
- Agno - Lightweight multi-modal agents
- Atomic Agents - Modular AI framework
- Browser Use - Web automation agents
- Composio - AI integration platform
- ChromaDB - Efficient vector database for embeddings
- Pinecone - Scalable vector database for AI applications
- Weaviate - AI-native vector database
- Qdrant - Vector search and semantic matching
- FAISS - Efficient document search and retrieval
- Milvus - Large-scale vector database
- AutoRAG - Automated RAG system optimization
- RAGatouille - Advanced RAG retrieval
- RAGLite - Efficient RAG framework
- LangChain - Building intelligent workflows
- LlamaIndex - Data integration for language models
- Hugging Face Transformers - Foundation for generative AI and NLP
- OpenAI - GPT models and API integration
- LiteLLM - Simplified LLM integration
- vLLM - Fast LLM inference
- Instructor - Structured outputs from LLMs
- DSPy - Language model prompting with Python
- Guidance - Structured LLM generation
- PandasAI - AI-powered data analysis
- Unstructured - Text processing for LLMs
- TextBlob - Simplified NLP for everyone
- SentenceTransformers - Semantic similarity and clustering
- Gensim - Topic modeling and document similarity
- PyTesseract - OCR tool for text extraction
- Tiktoken - High-performance tokenizer
- Chonkie AI - Advanced text chunking for RAG
- FireCrawl - Advanced web scraping for AI applications
- Crawl4AI - LLM-friendly web scraper
- ScrapegraphAI - AI-powered web scraping
- ExtractThinker - Intelligent document processing
- Streamlit - Interactive web apps development
- FastAPI - High-performance web framework for AI
- Gradio - Build interactive AI applications
- E2B - Execution environments with language models
- MLflow - Streamlining the ML lifecycle
- DeepEval - LLM evaluation framework
- Ragas - Evaluation framework for RAG systems
- LangSmith - Building and optimizing LLM applications
- Langfuse - Open-source LLM engineering platform
- Giskard - Evaluation & testing framework for AI systems
- OpenLLMetry - Observability for LLM apps
- Opik - LLM evaluation and monitoring
- Suno AI - Advanced speech synthesis platform
- WhisperASR - Multilingual speech recognition
- NeMo SpeechAI - Speech AI workbench
- Mem0 - Intelligent memory for personalized AI
- Supabase - Backend for GenAI applications
- MongoDB - AI-powered applications database
- Redis - High-speed data management for GenAI
- Neon DB - Serverless PGVector database
- Choose a notebook based on your interest or project needs
- Open in Jupyter or your preferred notebook environment
- Install dependencies as specified in each notebook
- Follow along with the step-by-step examples
- Experiment with the provided code and adapt to your use case
- Python 3.8+
- Jupyter Notebook or JupyterLab
- Basic understanding of Python programming
- API keys for specific services (OpenAI, Anthropic, etc.) where required
Found an issue or want to add a new library tutorial?
- Create an issue describing the problem or suggestion
- Fork the repository and create a new branch
- Add your notebook following the existing format
- Submit a pull request with a clear description
This collection is part of the Gen-AI-Experiments repository. Please refer to the main repository license.
Happy Learning! 🎉
Master AI/ML libraries one notebook at a time
Master AI/ML libraries one notebook at a time