ollama-rag

What problem does it solve?

This Skill simplifies the process of building Retrieval Augmented Generation (RAG) systems by leveraging Ollama for both local and cloud-based Large Language Models (LLMs) and embedding models.

Core Features & Use Cases

• Local & Cloud LLMs: Utilize powerful models like DeepSeek-V3.2 (GPT-5 level) or Qwen3-Coder (1M context) via Ollama, with or without local hardware.
• RAG Frameworks: Integrates seamlessly with LangChain and LlamaIndex for document Q&A, knowledge bases, and agentic RAG.
• Embedding Models: Supports various embedding models for accurate document retrieval.
• Use Case: Quickly set up a RAG system to answer questions from a large codebase or a collection of technical documents using a local Ollama model.

Quick Start

Use the ollama-rag skill to build a RAG system using LangChain and a local 'nemotron-3-nano' model.