Best of RAG — May 2024

1. 1
   Article

   KDnuggets·2y

   Free AI Courses from NVIDIA: For All Levels

   Free AI courses from NVIDIA are available to help you learn and build AI applications. Topics include Generative AI, building a neural network, augmenting LLMs using Retrieval Augmented Generation (RAG), and building RAG Agents with LLMs.

   1.5K

   50
2. 2
   Article

   Community Picks·2y

   How We Saved 10s of Thousands of Dollars Deploying Low Cost Open Source AI Technologies At Scale with Kubernetes

   Learn how to deploy low-cost open source AI technologies at scale with Kubernetes for generative AI applications, using alternatives to OpenAI and running vLLM locally and on Kubernetes.

   36

   4
3. 3
   Article

   GoPenAI·2y

   From Text to Action: Building LLM Applications

   Explore the key issues hindering LLM applications and techniques to overcome them, including RAG and chain-of-thought prompting.

   20
4. 4
   Article

   Towards AI·2y

   Build Rag With Llamaindex To Make LLM Answer About Yourself, Like in an Interview or About General Information

   Learn how to build a chatbot using RAG (Retrieved Augmentation Generation) and Llamaindex. The article discusses the steps involved in building a chat engine and provides code examples.

   16

   1
5. 5
   Article

   Weaviate·2y

   Building a Local RAG System for Privacy Preservation with Ollama and Weaviate

   Learn how to implement a local RAG-based chatbot in Python using Ollama and Weaviate. Set up local language models with Ollama and a local vector database instance with Docker to build a local RAG pipeline for privacy preservation.

   14
6. 6
   Article

   GoPenAI·2y

   Implementing A Local RAG with LangChain and Llama3: A Quick Guide

   This post explores the implementation of a local RAG using LangChain and Llama3. It discusses the advantages of Llama3 and the process of extracting metadata from a user query for vector store filtering.

   14

   1
7. 7
   Article

   Google Cloud·2y

   RAG vs. Fine-tuning and more

   Learn about the different methods to leverage data with LLMs, including prompt engineering, retrieval augmented generation (RAG), supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), and distillation.

   12
8. 8
   Article

   Community Picks·2y

   RAG quickstart with Ray, LangChain, and HuggingFace

   Learn how to deploy a complete RAG application on Google Kubernetes Engine (GKE), and Cloud SQL for PostgreSQL and pgvector using Ray, LangChain, and Hugging Face.

   12
9. 9
   Article

   Substack·2y

   GraphRAG: Design Patterns, Challenges, Recommendations

   GraphRAG enhances traditional RAG method by integrating knowledge graphs with large language models, providing more accurate and relevant answers to user queries. It offers various architectures and presents challenges in implementing and maintaining a knowledge graph.

   11

   1