LLM Use Cases from Scratch

This tutorial series provides hands-on approach to LLM applications using Ollama. Avoiding reliance on popular frameworks such as LangChain, LlamaIndex, or Chroma DB, this series offers a "from-scratch" methodology, enabling a nuanced understanding of each step involved in developing LLM-driven applications.

Series Outline:

• 0. Introduction to Ollama, LLMs, and Vision LLMs
• 1. Retrieval-Augmented Generation (RAG): Using Embedding Models and Creating Vector Stores from Scratch
• 2. Agentic RAG: Leveraging LLM Tool Capabilities to Optimize RAG Pipelines