Retrieval Augmented Generation

Retrieval Augmented Generation (RAG) improves large language models (LLMs) and AI-generated text by combining data retrieval with text generation.

Additional Reference Materials

• Retrieval Augmented Generation (RAG): All You Need To Know | Voiceflow
• Mistral - Basic RAG | Mistral AI Large Language Models
• Augmenting a Large Language Model with Retrieval-Augmented Generation and Fine-tuning | Microsoft Learn
• Open AI - Embeddings - OpenAI Platform
• Building Intelligent Applications with Local RAG in .NET and Phi-3: A Hands-On Guide

Text Embeddings

• Semantic Kernel Planner: Improvements with Embeddings and Semantic Memory | Semantic Kernel
• Systenics Solutions AI | Using Semantic Kernel with local embeddings
• Embedding models · Ollama Blog

Local Memory

• Local Memory: C# Semantic Kernel, Ollama and SQLite to manage Chat Memories locally | by John Kane | Medium
• A completely local RAG: .NET Langchain, SQLite and Ollama with no API keys required. | by John Kane | Medium

Libraries

• GitHub - microsoft/graphrag: A modular graph-based Retrieval-Augmented Generation (RAG) system

---

📇 Additional Metadata

• 🗂 Type:: note
• 🏷️ Tags::
• 📡 Status:: #status/🌱