话题AIGC › RAG

AIGC:RAG

RAG敲响丧钟?大模型长上下文是否意味着向量检索不再重要

RAG已经被证明是一种解决大模型幻觉的有效方法。

Rerank——RAG中百尺竿头更进一步的神器,从原理到解决方案

本文主要内容: 为什么一般情况下RAG的检索相关性存在问题? Rerank为什么可以解决这个问题? 几种常用Rerank组合评测; 如何在自己的产品中使用Rerank?…

翻译:图文并茂讲解高级 RAG 技术

对高级检索增强生成技术(Retrieval Augmented Generation, RAG)及算法的全面讲解。

Using LlamaIndex with Elasticsearch for Enhanced Retrieval-Augmented Generation (RAG)

Retrieval-Augmented Generation (RAG) is a technique that combines retrieval and generation capabilities. It effectively addresses some issues of large language models (LLMs), such as hallucinations and knowledge limitations. With the evolution of RAG, vector technology involved in RAG has gained attention, and vector databases have become more widely recognized. Established database providers now support vector retrieval, including Elasticsearch, which recently added support for vector retrieval in its latest version. This article introduces the deployment of Elasticsearch and embedding models in RAG, as well as how to use Elasticsearch for document indexing and retrieval within the LLM framework LlamaIndex.

得物大模型平台接入最佳实践

大模型是未来业务创新的重要驱动力,可以帮助业务提升效率、质量和用户体验。业务可以通过渐进的方式接入大模型,从PROMPT开始,逐步尝试RAG和Fine-tuning,以达到最佳收益效果。期待与更多业务部门合作,共同探索大模型的更多可能性。

RAG实战案例:如何基于 LangChain 实现智能检索生成系统

在人工智能领域,如何有效结合大型语言模型(LLM)的常识性知识与特定的专有数据,一直是业界探索的热点。微调(Fine-tuning)与检索增强生成(RAG)两种方法各有千秋,且都对此问题有着不可忽视的贡献。

Advanced RAG Techniques: an Illustrated Overview

A comprehensive study of the advanced retrieval augmented generation techniques and algorithms, systemising various approaches. The article comes with a collection of links in my knowledge base referencing various implementations and studies mentioned.

Evaluating RAG Applications with RAGAs

A framework with metrics and LLM-generated data to evaluate the performance of your Retrieval-Augmented Generation pipeline.

  • «
  • 1
  • »

首页 - Wiki
Copyright © 2011-2024 iteam. Current version is 2.128.0. UTC+08:00, 2024-06-14 11:48
浙ICP备14020137号-1 $访客地图$