在使用Neo4j和LangChain的RAG应用程序中构建和检索知识图信息的实用指南

编者按：以下是Tomaz Bratanic的客座博客文章，他专注于Neo4j的Graph ML和GenAI研究。Neo4j是一家图形数据库和分析公司，它帮助组织深入、轻松、快速地发现数十亿数据连接中隐藏的关系和模式。

图检索增强生成（Graph RAG）作为传统矢量搜索检索方法的强大补充，正在获得发展势头。这种方法利用了图数据库的结构化特性，将数据组织为节点和关系，以增强检索信息的深度和上下文性。

使用postgres作为后端并利用pgvector扩展的LangChain向量库抽象的实现。

The code lives in an integration package called: langchain_postgres.

您可以运行以下命令来启动具有pgvector扩展名的postgres容器：

Before diving into InfluxDB, it’s good to get acquainted with some key concepts of the database. This document introduces key InfluxDB concepts and elements. To introduce the key concepts, we’ll cover how the following elements work together in InfluxDB:

Cohesion metrics measure how well the methods of a class are related to each other. A cohesive class performs one function while a non-cohesive class performs two or more unrelated functions. A non-cohesive class may need to be restructured into two or more smaller classes.

High cohesion is desirable since it promotes encapsulation. As a drawback, a highly cohesive class has high coupling between the methods of the class, which in turn indicates high testing effort for that class.

What is MySQL?

MySQL is a relational database management system, used by customers across the world from small home-grown applications up to some of the largest data centers. It is developed, distributed and supported by Oracle, who acquired the product from Sun Microsystems in 2010 when Oracle bought Sun.

In the current software development era, multiple teams work on numerous projects. We need to store the codebase in some version control system like GitHub or TFS. Many organizations add different projects to a single repository, which is known as a monorepo. Many big organizations like Google, Microsoft, and Uber use a monorepo in their application development.

In this blog post, you will learn how to:

Introduction: What is LLM?

Large Language Models (LLMs) serve as foundational elements in the development of artificial intelligence applications. They process and generate text that mimics human communication, thus making digital interactions feel more natural. Nowadays, these models play an essentail role across numerous sectors. They improve operational processes and enrich the customer journey. By analyzing vast amounts of data, LLMs offer insights previously beyond reach.

LLM engineering involves much more than just prompt design or prompt engineering. In this article, we share a set of engineering practices that helped us deliver a prototype LLM application rapidly and reliably in a recent project. We'll share techniques for automated testing and adversarial testing of LLM applications, refactoring, as well as considerations for architecting LLM applications and responsible AI.