Skip to content

Latest commit

 

History

History
 
 

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

README.md

🚀 100+ Open Source Libraries

A comprehensive collection of 90+ Jupyter notebooks covering essential AI/ML libraries and frameworks


📚 Overview

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.

🎯 Categories

🤖 AI Agents & Frameworks

  • 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

🔍 RAG & Vector Databases

  • 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

🧠 Language Models & NLP

  • 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

📊 Data Processing & Analysis

  • 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

🌐 Web Scraping & Data Extraction

  • FireCrawl - Advanced web scraping for AI applications
  • Crawl4AI - LLM-friendly web scraper
  • ScrapegraphAI - AI-powered web scraping
  • ExtractThinker - Intelligent document processing

🔧 Development & Deployment

  • 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

📈 Evaluation & Monitoring

  • 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

🎵 Multimodal & Specialized

  • Suno AI - Advanced speech synthesis platform
  • WhisperASR - Multilingual speech recognition
  • NeMo SpeechAI - Speech AI workbench
  • Mem0 - Intelligent memory for personalized AI

☁️ Cloud & Infrastructure

  • Supabase - Backend for GenAI applications
  • MongoDB - AI-powered applications database
  • Redis - High-speed data management for GenAI
  • Neon DB - Serverless PGVector database

🚀 Getting Started

  1. Choose a notebook based on your interest or project needs
  2. Open in Jupyter or your preferred notebook environment
  3. Install dependencies as specified in each notebook
  4. Follow along with the step-by-step examples
  5. Experiment with the provided code and adapt to your use case

📋 Prerequisites

  • Python 3.8+
  • Jupyter Notebook or JupyterLab
  • Basic understanding of Python programming
  • API keys for specific services (OpenAI, Anthropic, etc.) where required

🤝 Contributing

Found an issue or want to add a new library tutorial?

  1. Create an issue describing the problem or suggestion
  2. Fork the repository and create a new branch
  3. Add your notebook following the existing format
  4. Submit a pull request with a clear description

📄 License

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