This repository is a comprehensive, curated list of over 100 free resources aimed at data scientists looking to specialize in Generative AI and Large Language Models (LLMs). It provides a structured pathway to learning and building GenAI applications, covering everything from foundational concepts and Python libraries to deployment on cloud platforms.

How It Works

The resource list is organized into logical categories, mirroring the end-to-end workflow of a GenAI data scientist. It covers core components like LLM providers, open-source models, frameworks for building applications (e.g., LangChain, AutoGen), vector databases for RAG, fine-tuning techniques, and essential MLOps tools for testing and monitoring. The inclusion of both Python and R ecosystems offers broad accessibility.

Quick Start & Requirements

This is a curated list of resources, not a runnable software project. No installation or specific requirements are needed to browse the content. Links to official documentation, GitHub repositories, and tutorials are provided for each listed tool and framework.

Highlighted Details

• Extensive coverage of popular LLM frameworks like LangChain, LangGraph, and AutoGen.
• Detailed sections on RAG, vector databases (ChromaDB, FAISS, Qdrant), and LLMOps.
• Includes resources for both building AI applications and deploying them on major cloud providers (AWS, Azure, GCP).
• Features a dedicated section for R-based LLM tools and workflows.

Maintenance & Community

The repository is maintained by business-science and welcomes community contributions via pull requests or issues.

Licensing & Compatibility

As a curated list of links, the repository itself does not have a specific license. The licenses of the linked projects vary and should be checked individually.

Limitations & Caveats

This resource list is a compilation and does not provide direct functionality. The rapidly evolving nature of Generative AI means some linked resources may become outdated over time.