利用基于 RAG 的 LLM 在分析任务中的优势

Retrieval-Augmented Generation (RAG) is a powerful process that is designed to integrate direct function calling to answer queries more efficiently by retrieving relevant information from a broad database. In the rapidly evolving business landscape, Data Analysts (DAs) are struggling with the growing number of data queries from stakeholders. The conventional method of manually writing and running similar queries repeatedly is time-consuming and inefficient. This is where RAG-powered Large Language Models (LLMs) step in, offering a transformative solution to streamline the analytics process and empower DAs to focus on higher value tasks.

检索增强生成（RAG）是一个强大的过程，旨在通过从广泛的数据库中检索相关信息来更高效地集成直接函数调用以回答查询。在快速发展的商业环境中，数据分析师（DAs）正面临着来自利益相关者的日益增长的数据查询数量。手动编写和重复运行类似查询的传统方法耗时且效率低下。这就是RAG驱动的大型语言模型（LLMs）发挥作用的地方，它们提供了一种改进分析过程并使DAs能够专注于更高价值任务的变革性解决方案。

In this article, we will share how the Integrity Analytics team has built out a data solution using LLMs to help automate tedious analytical tasks like generating regular metric reports and performing fraud investigations.

在本文中，我们将分享Integrity Analytics团队如何使用LLMs构建数据解决方案，以帮助自动化繁琐的分析任务，如生成定期指标报告和进行欺诈调查。

While LLMs are known for their proficiency in data interpretation and insight generation, they represent just a fragment of the entire solution. For a comprehensive solution, LLMs must be integrated with other essential tools. The following is required in assembling a solution:

虽然LLM以其数据解释和洞察力而闻名，但它们只是整个解决方案的一小部分。要获得全面的解决方案，LLM必须与其他必要的工具集成。以下是组装解决方案所需的内容：

Internally facing LLM tool - Spellvault is a platform within Grab that stores, shares, and refines LLM prompts. It features low/no-code RAG capabilities that lower the barrier of entry for people to create LLM applications.
面向内部的LLM工具 - Spellvault是Grab内部的一个平台，用于存储、共享和完善LLM提示。它具有低/无代码的RAG功能，降低了人们创建LLM应用的门槛。
Data - with real time or close to real-time latency to ensure accuracy. It has to be in a standardised format to ensure that all LLM data inputs are accurate.
数据 - 具有实时或接近实时的延迟，以确保准确性。它必须采用标准化格式，以确保所有LLM数据输入的准确性。
Scheduler - runs LLM...