GraphRAG 宣言：为 GenAI 添加知识

source: https://neo4j.com/blog/graphrag-manifesto/

Notes

---

Origin

We’re Entering the “Blue Links” Era of RAG

我们正在进入 RAG 的“蓝色链接”时代

We are on the verge of realizing that in order to do anything significantly useful with GenAI, you can’t depend only on autoregressive LLMs to make your decisions. I know what you’re thinking: “RAG is the answer.” Or fine-tuning, or GPT-5.

我们即将意识到，为了利用 GenAI 做任何非常有用的事情，你不能仅仅依靠自回归 LLMs 来做出决定。我知道你在想什么：“RAG 就是答案。”或者微调，或者GPT-5。

Yes. Techniques like vector-based RAG and fine-tuning can help. And they are good enough for some use cases. But there’s another whole class of use cases where these techniques all bump into a ceiling. Vector-based RAG – in the same way as fine-tuning – increases the probability of a correct answer for many kinds of questions. However neither technique provides the certainty of a correct answer. Oftentimes they also lack context, color, and a connection to what you know to be true. Further, these tools don’t leave you with many clues about why they made a particular decision.

是的。基于矢量的 RAG 和微调等技术可以提供帮助。它们对于某些用例来说已经足够好了。但还有另外一类用例，这些技术都遇到了天花板。基于向量的 RAG——与微调的方式相同——增加了多种问题的正确答案的概率。然而，这两种技术都不能提供正确答案的确定性。通常，它们也缺乏背景、色彩以及与你所知道的真实事物的联系。此外，这些工具并没有给你留下太多关于他们为什么做出特定决定的线索。

Back in 2012, Google introduced their second-generation search engine with an iconic blog post titled “Introducing the Knowledge Graph: things, not strings¹.” They discovered that a huge leap in capability is possible if you use a knowledge graph to organize the things represented by the strings in all these web pages, in addition to also doing all of the string processing. We are seeing this same pattern unfold in GenAI today. Many GenAI projects are bumping up against a ceiling, where the quality of results is gated by the fact that the solutions in use are dealing in strings, not things.

早在 2012 年，Google 就推出了他们的第二代搜索引擎，并发表了一篇标志性的博客文章，标题为“知识图简介：事物，而不是字符串 ¹ ”。他们发现，如果您使用知识图来组织所有这些网页中字符串表示的事物，并且除了执行所有字符串处理之外，还可以实现能力的巨大飞跃。今天，我们在 GenAI 中看到了同样的模式。许多 GenAI 项目都遇到了上限，结果的质量受到以下事实的限制：所使用的解决方案处理的是字符串，而不是事物。

Fast forward to today, AI engineers and academic researchers at the leading edge are discovering the same thing that Google did: that the secret to breaking through this ceiling is knowledge graphs. In other words, bring knowledge about things into the mix of statistically-based text techniques. This works just like any other type of RAG, except with a call to a knowledge graph in addition to a vector index. Or in other words, GraphRAG!

快进到今天，处于前沿的人工智能工程师和学术研究人员正在发现与谷歌相同的事情：突破这一天花板的秘诀是知识图谱。换句话说，将有关事物的知识融入基于统计的文本技术的组合中。它的工作原理与任何其他类型的 RAG 一样，除了向量索引之外还调用知识图。或者换句话说，GraphRAG！

This post is intended to be a comprehensive and easy-to-read treatment of GraphRAG. It turns out that building a knowledge graph of your data and using it in RAG gives you several powerful advantages. There’s a robust body of research proving that it gives you better answers to most if not ALL questions you might ask an LLM using normal vector-only RAG.

这篇文章旨在对 GraphRAG 进行全面且易于阅读的处理。事实证明，构建数据知识图并在 RAG 中使用它可以为您带来几个强大的优势。有大量的研究证明，它可以为您使用纯向量 RAG 时可能会问 LLM 的大多数（如果不是全部）问题提供更好的答案。

That alone will be a huge driver of GraphRAG adoption. In addition to that, you get easier development thanks to data being visible when building your app. A third major advantage is that graphs can be readily understood and reasoned upon by humans as well as machines. Building with GraphRAG is therefore easier, gives you better results, and – this is a killer in many industries – is explainable and auditable! I believe GraphRAG will subsume vector-only RAG and emerge as the default RAG architecture for most use cases. This post explains why.

仅此一点就将成为 GraphRAG 采用的巨大推动力。除此之外，由于构建应用程序时数据可见，您的开发变得更加容易。第三个主要优点是人类和机器都可以轻松理解和推理图表。因此，使用 GraphRAG 进行构建更容易，可以为您提供更好的结果，而且——这在许多行业都是杀手——是可解释和可审计的！我相信 GraphRAG 将包含纯矢量 RAG，并成为大多数用例的默认 RAG 架构。这篇文章解释了原因。

Wait, Graph? 等等，图？

Let’s be clear that when we say graph, we mean something like this:

让我们明确一点，当我们说图表时，我们的意思是这样的：

_While this image has been widely used to exemplify knowledge graphs, the original source and author remain unidentified. The earliest known usage appears to be this Medium post from Farahnaz Akrami. If you are the creator of this image, please contact us so we may provide proper attribution.

虽然该图像已被广泛用于举例说明知识图，但原始来源和作者仍未确定。已知最早的用法似乎是 Farahnaz Akrami 的这篇 Medium 帖子。如果您是该图像的创建者，请联系我们，以便我们提供正确的归属。_

Or this:

_The Graph of Thrones visualization by William Lyon.

威廉·里昂的《权力图谱》可视化。_

Or this:

_London Underground Map (Credit: Transport for London.) Fun fact, Transport for London recently deployed a graph-powered digital twin to improve incident response and reduce congestion.

伦敦地铁地图（图片来源：伦敦交通局）。有趣的是，伦敦交通局最近部署了图形驱动的数字孪生模型，以改善事件响应并减少拥堵。_

In other words, not a chart.

换句话说，不是图表。

If you want to delve more into graphs and knowledge graphs, I’d recommend a detour to Neo4j’s GraphAcademy or Andrew Ng’s Deeplearning.ai course on Knowledge Graphs for RAG. We won’t linger on definitions here and will continue forward assuming basic working knowledge of graphs.

如果您想深入研究图和知识图，我建议您绕道访问 Neo4j 的 GraphAcademy 或 Andrew Ng 的 Deeplearning.ai 关于 RAG 知识图的课程。我们不会在这里停留在定义上，并将继续假设图形的基本工作知识。

If you understand the pictures above, you can see how you might query the underlying knowledge graph data (stored in a graph database) as part of your RAG pipeline. This is what GraphRAG is about.

如果您理解上面的图片，您就可以了解如何查询底层知识图数据（存储在图数据库中）作为 RAG 管道的一部分。这就是 GraphRAG 的意义所在。

Two Types of Knowledge Representation: Vectors & Graphs

两种类型的知识表示：向量和图形

The core of typical RAG – vector search – takes in a chunk of text and returns conceptually similar text from a candidate body of written material. This is pleasantly automagical and is very useful for basic searches.

典型 RAG 的核心——向量搜索——接收一段文本并从候选书面材料中返回概念上相似的文本。这是令人愉快的自动魔法，对于基本搜索非常有用。

What you might not think about every time you do this is what a vector looks like, or what the similarity calculation is doing. Let’s look at an apple in human terms, vector terms, and graph terms:

每次执行此操作时，您可能不会想到向量是什么样子，或者相似性计算正在做什么。让我们用人类术语、矢量术语和图形术语来看看苹果：

The human representation is complex and multidimensional and not something we can fully capture on paper. Let’s grant some poetic license and imagine that this beautifully tempting picture represents an apple in all its perceptual & conceptual glory.

人类的表征是复杂的、多维的，我们无法在纸上完全捕捉到。让我们给予一些诗意的许可，想象这张美丽诱人的图片代表了一个苹果在其所有感知和概念上的荣耀。

The vector representation of the apple² is an array of numbers – a construct of the statistical realm. The magic of vectors is that they each capture the essence of their corresponding text in encoded form. In a RAG context however, they are only valuable when you need to identify how similar one handful of words is to another. Doing this is as simple as running a similarity calculation (aka vector math) and getting a match. However, if you want to make sense of what’s inside of a vector, understand what’s around it, get a handle on the things represented in your text, or understand how any of these fit into a larger context, then vectors as a representation just aren’t able to do that.

苹果 ² 的向量表示是一个数字数组 - 统计领域的构造。矢量的神奇之处在于它们每个都以编码形式捕获相应文本的本质。然而，在 RAG 上下文中，只有当您需要确定几个单词与另一个单词的相似程度时，它们才有价值。执行此操作就像运行相似性计算（又名向量数学）并获得匹配一样简单。但是，如果您想了解向量内部的内容，了解其周围的内容，掌握文本中表示的事物，或者了解其中任何一个如何适应更大的上下文，那么向量作为表示就可以了无法做到这一点。

Knowledge graphs, by contrast, are declarative – or in AI terms, symbolic – representations of the world. As a result, both humans and machines can understand and reason upon knowledge graphs. This is a BIG DEAL, which we’ll revisit later. Additionally, you can query, visualize, annotate, fix, and grow knowledge graphs. A knowledge graph represents your world model³ – the part of the world that represents the domain you are working with.

相比之下，知识图是世界的声明性（或者用人工智能术语来说，是符号性）表示。因此，人类和机器都可以根据知识图谱进行理解和推理。这是一件大事，我们稍后会再讨论。此外，您还可以查询、可视化、注释、修复和扩展知识图。知识图代表您的世界模型 ³ - 代表您正在使用的领域的世界部分。

GraphRAG “vs.” RAG GraphRAG“对比”抹布

It’s not a competition 🙂 Vector and graph queries each add value in RAG. As pointed out by founder of LlamaIndex Jerry Liu, it’s helpful to think about GraphRAG as inclusive of vectors. This is distinct from “vector-only RAG,” which is strictly based on similarity with embeddings based on words in text.

这不是一场竞赛 🙂 矢量和图形查询都在 RAG 中增加了价值。正如 LlamaIndex 创始人 Jerry Liu 所指出的，将 GraphRAG 视为包含向量是有帮助的。这与“纯向量 RAG”不同，后者严格基于与基于文本中单词的嵌入的相似性。

Fundamentally, GraphRAG is RAG, where the Retrieval path includes a knowledge graph. As you can see below, the core GraphRAG pattern is straightforward. It’s basically the same architecture as RAG with vectors⁴ but with a knowledge graph layered into the picture.

从根本上讲，GraphRAG 是 RAG，其中检索路径包括知识图。如下所示，核心 GraphRAG 模式非常简单。它的架构与带有向量 ⁴ 的 RAG 基本相同，但知识图分层到图片中。

GraphRAG Pattern GraphRAG 模式

Here, you see a graph query being triggered. It can optionally include a vector similarity component. You can choose to store your graphs and vectors either separately in two distinct databases, or use a graph database like Neo4j which also supports vector search.

在这里，您会看到正在触发的图形查询。它可以选择性地包括向量相似性组件。您可以选择将图形和向量分别存储在两个不同的数据库中，或者使用像 Neo4j 这样也支持向量搜索的图形数据库。

One of the common patterns for using GraphRAG is as follows:

使用 GraphRAG 的常见模式之一如下：

1. Do a vector or keyword search to find an initial set of nodes.

   进行向量或关键字搜索以查找初始节点集。

2. Traverse the graph to bring back information about related nodes.

   遍历图以带回相关节点的信息。

3. Optionally, re-rank documents using a graph-based ranking algorithm such as PageRank.

   或者，使用基于图形的排名算法（例如 PageRank）对文档重新排名。

Patterns vary by use case, and like everything else in AI today, GraphRAG is proving to be a rich space, with new discoveries emerging every week. We will dedicate a future blog post to the most common GraphRAG patterns we see today.

模式因用例而异，与当今人工智能中的其他事物一样，GraphRAG 被证明是一个丰富的空间，每周都会出现新的发现。我们将在未来的博客文章中专门介绍我们今天看到的最常见的 GraphRAG 模式。

GraphRAG Lifecycle GraphRAG 生命周期

A GenAI application that uses GraphRAG follows the same pattern as any RAG application, with an added “create graph” step at the start:

使用 GraphRAG 的 GenAI 应用程序遵循与任何 RAG 应用程序相同的模式，只是在开始时添加了“创建图形”步骤：

Creating a graph is analogous to chunking documents and loading them into a vector database. Advances in tooling have made graph creation literally that easy. The good news is threefold:

创建图表类似于对文档进行分块并将其加载到矢量数据库中。工具的进步使得图形创建变得如此简单。好消息有三个：

1. Graphs are highly iterative – you can start with a “minimum viable graph” and expand from there.

   图是高度迭代的——您可以从“最小可行图”开始，然后从那里扩展。

2. Once your data is in a knowledge graph, it becomes very easy to evolve. You can add more kinds of data, to reap the benefits of data network effects. You can also improve the quality of the data to up the value of your application results.

   一旦你的数据进入知识图谱，它就变得非常容易发展。您可以添加更多种类的数据，以获得数据网络效应的好处。您还可以提高数据质量，以提高应用程序结果的价值。

3. This part of the stack is rapidly improving, which means graph creation will only get easier as tooling gets more sophisticated.

   堆栈的这一部分正在迅速改进，这意味着随着工具变得更加复杂，图形创建只会变得更加容易。

Adding the graph creation step to the earlier picture gives you a pipeline that looks like this:

将图形创建步骤添加到前面的图片中将为您提供一个如下所示的管道：

I will dive deeper into graph creation later. For now, let’s set that aside and talk about the benefits of GraphRAG.

稍后我将更深入地研究图形创建。现在，让我们先把这个放在一边，谈谈 GraphRAG 的好处。

Why GraphRAG? 为什么选择 GraphRAG？

The benefits we are seeing from GraphRAG relative to vector-only RAG fall into three main buckets:

我们从 GraphRAG 中看到的相对于纯向量 RAG 的优势主要分为三个方面：

1. Higher accuracy and more complete answers (runtime / production benefit)

   更高的准确性和更完整的答案（运行时/生产效益）

2. Once you’ve created your knowledge graph, then it’s easier to both build⁵ and subsequently maintain your RAG application (development time benefit)

   创建知识图后，构建 ⁵ 和随后维护 RAG 应用程序就会变得更加容易（开发时间优势）

3. Better explainability, traceability⁶, and access controls (governance benefit)

   更好的可解释性、可追溯性 ⁶ 和访问控制（治理效益）

Let’s drill into these:

让我们深入研究这些：

#1: Higher Accuracy & More Useful Answers

#1：更高的准确性和更有用的答案

The first (and most immediately tangible) benefit we see with GraphRAG is higher-quality responses. In addition to a growing number of examples we see from our customers, an increasing number of academic studies also support this. One such example is by data catalog company Data.world. At the end of 2023, they published a study that showed that GraphRAG, on average, improved accuracy of LLM responses by 3x across 43 business questions. The benchmark found evidence of a significant improvement in the accuracy of responses when backed by a knowledge graph.

我们通过 GraphRAG 看到的第一个（也是最直接的）好处是更高质量的响应。除了我们从客户那里看到的越来越多的例子之外，越来越多的学术研究也支持这一点。数据目录公司 Data.world 就是这样的一个例子。 2023 年底，他们发表的一项研究表明，GraphRAG 在 43 个业务问题中的 LLM 响应的准确性平均提高了 3 倍。该基准发现有证据表明，在知识图的支持下，响应的准确性显着提高。

More recently and perhaps better known is a series of posts by Microsoft starting in February 2024 with a research blog titled GraphRAG: Unlocking LLM discovery on narrative private data, along with an associated research paper, and software release. Here they observed that baseline RAG (i.e. with vectors) has the two following problems:

最近，也许更为人所知的是 Microsoft 从 2024 年 2 月开始发布的一系列帖子，其中包括题为 GraphRAG：解锁叙述性私人数据的 LLM 发现的研究博客，以及相关的研究论文和软件版本。在这里，他们观察到基线 RAG（即带有向量）存在以下两个问题：

• _Baseline RAG struggles to connect the dots. This happens when answering a question requires traversing disparate pieces of information through their shared attributes in order to provide new synthesized insights.

  Baseline RAG 很难将这些点联系起来。当回答问题需要通过共享属性遍历不同的信息以提供新的综合见解时，就会发生这种情况。_

• _Baseline RAG performs poorly when being asked to holistically understand summarized semantic concepts over large data collections or even singular large documents.

  当被要求全面理解大型数据集合甚至单个大型文档的概括语义概念时，基线 RAG 表现不佳。_

Microsoft found that “By using the LLM-generated knowledge graph, GraphRAG vastly improves the ‘retrieval’ portion of RAG, populating the context window with higher relevance content, resulting in better answers and capturing evidence provenance.” They also discovered that GraphRAG required between 26% and 97% fewer tokens than alternative approaches, making it not just better at providing answers, but also cheaper and more scalable⁷.

Microsoft 发现“通过使用 LLM 生成的知识图，GraphRAG 极大地改进了 RAG 的‘检索’部分，用更高相关性的内容填充上下文窗口，从而获得更好的答案并捕获证据来源。”他们还发现，与其他方法相比，GraphRAG 所需的令牌少了 26% 到 97%，这使得它不仅能够更好地提供答案，而且还更便宜且更具可扩展性 ⁷ 。

Digging deeper into the topic of accuracy, it’s not just whether an answer is correct that’s important; it’s also how useful the answers are. What people have been finding with GraphRAG is that not only are the answers more accurate, but they are also richer, more complete, and more useful. LinkedIn’s recent paper describing the impact of GraphRAG on their customer service application provides an excellent example of this. GraphRAG improves both correctness and richness (and therefore usefulness) for answering customer service questions, reducing median per-issue resolution time by 28.6% for their customer service team⁸.

深入探讨准确性这个话题，重要的不仅仅是答案是否正确，更重要的是答案是否正确。这也是答案的有用性。人们发现 GraphRAG 不仅答案更准确，而且更丰富、更完整、更有用。 LinkedIn 最近的一篇论文描述了 GraphRAG 对其客户服务应用程序的影响，这就是一个很好的例子。 GraphRAG 提高了回答客户服务问题的正确性和丰富性（从而提高了实用性），将客户服务团队的每个问题解决时间中值缩短了 28.6% ⁸ 。

A similar example comes from a GenAI workshop taught by Neo4j and with our partners at GCP, AWS, and Microsoft. The sample query below, which targets a collection of SEC filings, provides a good illustration of the kinds of answers that are possible when using vector + GraphRAG vs. those that one obtains when using vector-only RAG:

类似的例子来自 Neo4j 以及我们在 GCP、AWS 和 Microsoft 的合作伙伴教授的 GenAI 研讨会。下面的示例查询针对 SEC 文件的集合，很好地说明了使用向量 + GraphRAG 时可能得到的答案类型与使用纯向量 RAG 时获得的答案的类型：

Note the difference between describing the characteristics of companies likely to be impacted by a lithium shortage, and listing specific companies that are likely to be. If you are an investor looking to rebalance your portfolio in the face of a change in the market or a company looking to rebalance its supply chain in the face of a natural disaster, having access to the latter and not just the former can be game changing. Here, both answers are accurate. The second one is clearly more useful.

请注意描述可能受到锂短缺影响的公司的特征与列出可能受到锂短缺影响的具体公司之间的区别。如果您是一位投资者，希望在市场变化时重新平衡您的投资组合，或者是一家公司，希望在自然灾害面前重新平衡其供应链，那么获得后者而不仅仅是前者可能会改变游戏规则。在这里，两个答案都是准确的。第二个显然更有用。

Episode 23 of Going Meta by Jesus Barrasa provides another great example using a legal documents use case, starting with the lexical graph.

Jesus Barrasa 的 Going Meta 第 23 集提供了另一个使用法律文档用例的好例子，从词法图开始。

Those observing the X-sphere and who are active on LinkedIn will spot new examples coming out regularly from not just the lab but the field. Here, Charles Borderie at Lettria gives an example of vector-only RAG contrasted with GraphRAG, against an LLM-based text-to-graph pipeline that ingests 10,000 financial articles into a knowledge graph:

那些观察 X 球体和活跃在 LinkedIn 上的人会发现定期出现的新例子，不仅来自实验室，而且来自现场。这里，Lettria 的 Charles Borderie 给出了一个纯向量 RAG 与 GraphRAG 对比的示例，以及基于 LLM 的文本到图形管道，该管道将 10,000 篇金融文章提取到知识图中：

As you can see, not only did the quality of the answer improve markedly with GraphRAG vs. plain RAG, but the answer took one-third fewer tokens.

正如您所看到的，与普通 RAG 相比，GraphRAG 不仅答案的质量显着提高，而且答案所用的标记也减少了三分之一。

One last notable example I will include comes from Writer. They recently announced a RAG Benchmarking Report based on the RobustQA framework, comparing their GraphRAG-based approach⁹ to competitive best-in-class tools. GraphRAG resulted in a score of 86%, which is a significant improvement from the competition, whose scores ranged between 33% and 76%, with equivalent or better latency.

我要举的最后一个值得注意的例子来自 Writer。他们最近发布了一份基于 RobustQA 框架的 RAG 基准测试报告，将其基于 GraphRAG 的方法 ⁹ 与同类最佳工具进行比较。 GraphRAG 的得分为 86%，比竞争对手的得分在 33% 到 76% 之间有显着提高，且延迟时间相当或更好。

Every week I meet with customers across many industries who are experiencing similar positive effects with a wide variety of GenAI applications. Knowledge graphs are unblocking the path for GenAI by making the results more accurate and more useful.

每周我都会与许多行业的客户会面，他们在各种 GenAI 应用程序中都经历了类似的积极影响。知识图谱使结果更准确、更有用，从而为 GenAI 扫清了道路。

#2: Improved Data Understanding, Faster Iteration

#2：改进数据理解，加快迭代速度

Knowledge graphs are intuitive both conceptually and visually. Being able to explore them often reveals new insights. An unexpected side benefit that many users are reporting is that once they’ve invested in creating their knowledge graph, they find that it helps them build and debug their GenAI applications in unexpected ways. This has partly to do with how seeing one’s data as a graph paints a living picture of the data underlying the application. The graph also gives you hooks for tracing answers back to data, and tracing that data up the causal chain.

知识图在概念上和视觉上都很直观。能够探索它们通常会揭示新的见解。许多用户报告的一个意想不到的附带好处是，一旦他们投资创建知识图谱，他们就会发现它可以帮助他们以意想不到的方式构建和调试 GenAI 应用程序。这在一定程度上与如何将数据视为图表来描绘应用程序底层数据的生动图景有关。该图还为您提供了钩子，用于将答案追溯到数据，并沿着因果链追踪该数据。

Let’s look at an example using the lithium exposure question above. If you visualize the vectors, you will get something like this, except with far more rows and columns:

让我们看一个使用上述锂暴露问题的示例。如果你可视化向量，你会得到类似这样的东西，除了更多的行和列：

When you work with your data as a graph, you can apprehend it in a way that’s just not possible with a vector representation.

当您以图表形式处理数据时，您可以以矢量表示无法实现的方式理解它。

Here is an example from a recent webinar from LlamaIndex¹⁰, showing off their ability to extract the graph of vectorized chunks (the lexical graph) and LLM-extracted entities (the domain graph) and tie the two together with “MENTIONS” relationships:

以下是来自 LlamaIndex ¹⁰ 最近网络研讨会的一个示例，展示了他们提取矢量化块图（词法图）和 LLM 提取实体（域图）的能力并将两者通过“提及”关系联系在一起：

(You can find similar examples with Langchain, Haystack, SpringAI, and more.)

（您可以在 Langchain、Haystack、SpringAI 等中找到类似的示例。）

Looking at this diagram, you can probably start to see how having a rich structure where your data resides opens up a wide range of new development and debugging possibilities. The individual pieces of data retain their value, and the structure itself stores and conveys additional meaning, which you can use to add more intelligence to your application.

查看此图，您可能会开始了解数据所在的丰富结构如何开辟了广泛的新开发和调试可能性。各个数据片段保留其价值，结构本身存储并传达附加含义，您可以使用这些含义为应用程序添加更多智能。

It’s not just the visualization. It’s also the effect of having your data structured in a way that conveys and stores meaning. Here is the reaction of a developer from a well-known fintech a week into introducing knowledge graphs into their RAG workflow:

这不仅仅是可视化。这也是以传达和存储含义的方式构建数据的效果。以下是一位知名金融科技公司的开发人员在将知识图引入其 RAG 工作流程后一周的反应：

This developer’s reaction aligns well with the test-driven development assumption of verifying – not trusting – that answers are correct. Speaking for myself, I get the heebie-jeebies handing 100% of my autonomy over to SkyNet to make decisions that are entirely opaque! More concretely though, even AI non-doomers can appreciate the value of being able to see that a chunk or a document tied to “Apple, Inc.” should really not be mapped to “Apple Corps”. Since the data is ultimately what’s driving GenAI decisions, having facilities at hand to assess and assure correctness is all but paramount.

该开发人员的反应与验证（而不是信任）答案是否正确的测试驱动开发假设非常吻合。就我自己而言，我让那些惊慌失措的人将我 100% 的自主权交给 SkyNet，让其做出完全不透明的决定！但更具体地说，即使是人工智能非失败者也能体会到能够看到与“Apple, Inc.”相关的块或文档的价值。确实不应该映射到“苹果公司”。由于数据最终是推动 GenAI 决策的因素，因此拥有可用于评估和确保正确性的设施几乎是至关重要的。

#3: Governance: Explainability, Security, and More

#3：治理：可解释性、安全性等

The higher the impact¹¹ of a GenAI decision, the more you need to be able to convince the person who will ultimately be accountable if it goes wrong to trust the decision. This typically involves being able to audit each decision. It also requires a solid and repeatable track record of good decisions. But that isn’t enough. You also need to be able to explain the underlying reasoning to that person when they call a decision to the mat.

GenAI 决策的影响力 ¹¹ 越高，您就越需要能够说服最终承担责任的人相信该决策。这通常涉及能够审核每个决策。它还需要可靠且可重复的良好决策记录。但这还不够。当他们做出决定时，你还需要能够向他们解释其根本原因。

LLMs don’t offer a good way of doing this on their own. Yes, you can get references to the documents used to make the decision. But those don’t explain the decision itself – not to mention the fact that LLMs are known to make up those references! Knowledge graphs operate at an entirely different level, making the reasoning logic inside of GenAI pipelines much clearer, and the inputs a lot more explainable.

LLMs 没有提供单独执行此操作的好方法。是的，您可以参考用于做出决定的文件。但这些并不能解释决定本身 - 更不用说众所周知 LLMs 是构成这些参考文献的事实！知识图在完全不同的层面上运行，使得 GenAI 管道内部的推理逻辑更加清晰，输入也更容易解释。

Let’s continue with one of the examples above, where Charles from Lettria loads up a knowledge graph with extracted entities from 10,000 financial articles and uses this with an LLM to carry out GraphRAG. We saw how this provides better answers. Let’s get a look at the data:

让我们继续上面的一个示例，来自 Lettria 的 Charles 加载了一个知识图，其中包含从 10,000 篇金融文章中提取的实体，并将其与 LLM 一起使用来执行 GraphRAG。我们看到了这如何提供更好的答案。我们来看一下数据：

Seeing the data as a graph is the first part. The data is also navigable and queryable and can be corrected and updated as time goes on. The governance advantage is that it becomes far easier to view and audit the “world model” of the data. Using a graph makes it more likely that the responsible human who is ultimately accountable for the decision will understand it, relative to being served up the vector version of the same data. On the quality assurance side, having the data in a knowledge graph makes it a lot easier to pick out errors and surprises in the data (pleasant or otherwise), and trace them back to their source. You can also capture provenance and confidence information in the graph and use this not just in your calculation but your explanation. This just isn’t possible when you’re looking at the vector-only version of the same data, which as we discussed earlier is pretty inscrutable to the average – and even above-average!–human.

将数据视为图表是第一部分。数据还可以导航和查询，并且可以随着时间的推移进行更正和更新。治理优势在于查看和审核数据的“世界模型”变得更加容易。相对于提供相同数据的矢量版本，使用图表使得最终对决策负责的负责人更有可能理解它。在质量保证方面，将数据放在知识图中可以更容易地找出数据中的错误和意外（令人愉快的或其他的），并追溯到它们的来源。您还可以在图表中捕获出处和置信度信息，并将其不仅用于计算，还用于解释。当您查看相同数据的纯矢量版本时，这是不可能的，正如我们之前讨论的那样，这对于普通人（甚至高于平均水平！）的人类来说是非常难以理解的。

Knowledge graphs can also significantly enhance security and privacy. This tends to be less top of mind when building a prototype, but it’s a critical part of the path to production. If you’re in a regulated business such as banking or healthcare, the access any given employee has to information probably depends on that person’s role. Neither LLMs nor vector databases have a good way of limiting the scope of information to match up with the role. You can readily handle this with permissions inside a knowledge graph, where any given actor’s ability to access data is governed by the database, and exclude results that they aren’t allowed to see. Here is a mock-up of a simple security policy that you can implement in a knowledge graph with fine-grained access controls:

知识图还可以显着增强安全性和隐私性。在构建原型时，这往往不是最重要的，但它是生产过程中的关键部分。如果您从事银行或医疗保健等受监管企业，则任何特定员工对信息的访问权限可能取决于该人的角色。 LLMs 和向量数据库都没有很好的方法来限制信息范围以匹配角色。您可以使用知识图中的权限轻松处理此问题，其中任何给定参与者访问数据的能力均由数据库控制，并排除他们不允许看到的结果。以下是一个简单安全策略的模型，您可以在具有细粒度访问控制的知识图中实现该策略：

Knowledge Graph Creation

知识图谱创建

People often ask me what it takes to build a knowledge graph. The first step in understanding the answer is to know the two kinds of graphs most relevant to GenAI applications:

人们经常问我构建知识图谱需要什么。理解答案的第一步是了解与 GenAI 应用程序最相关的两种图：

1. The Domain graph is a graph representation of the world model relevant to your application. Here is a simple example:

   域图是与您的应用程序相关的世界模型的图形表示。这是一个简单的例子：

   

2. The Lexical graph¹² is a graph of document structure. The most basic lexical graph has a node for each chunk of text:

   词法图 ¹² 是文档结构图。最基本的词汇图对于每个文本块都有一个节点：

   

People often expand this to include relationships between chunks and document objects (such as tables), chapters, sections, page numbers, document name/ID, collections, sources, and so on. You can also combine domain and lexical graphs like so:

人们经常将其扩展为包括块和文档对象（例如表）、章节、页码、文档名称/ID、集合、源等之间的关系。您还可以组合域图和词法图，如下所示：

Creating a lexical graph is easy and largely a matter of simple parsing and chunking strategies¹³. As for the domain graph, there are a few different paths depending on whether the data you’re bringing in comes from a structured source, from unstructured text, or both. Luckily, tooling for creating knowledge graphs from unstructured data sources is rapidly improving. For example, the new Neo4j Knowledge Graph Builder takes PDF documents, web pages, YouTube clips, or Wikipedia articles, and automatically creates a knowledge graph from them. It’s as easy as clicking a few buttons, and lets you visualize (and of course query) both domain and lexical graphs of your input text. It’s powerful and fun, and significantly reduces the barrier to creating a knowledge graph.

创建词法图很容易，主要是简单的解析和分块策略 ¹³ 。至于域图，有几种不同的路径，具体取决于您引入的数据是来自结构化源、非结构化文本还是两者。幸运的是，用于从非结构化数据源创建知识图的工具正在迅速改进。例如，新的 Neo4j 知识图生成器采用 PDF 文档、网页、YouTube 剪辑或维基百科文章，并自动从中创建知识图。只需单击几个按钮即可轻松实现，并且可以让您可视化（当然还有查询）输入文本的域图和词法图。它功能强大且有趣，并且显着降低了创建知识图谱的障碍。

Data about customers, products, geographies, etc. probably lives somewhere in your enterprise in a structured form, and can be sourced directly from wherever it lives. Taking the most common case where it’s in a relational database, you can use standard tools¹⁴ that follow tried-and-true rules for relational-to-graph mapping.

有关客户、产品、地理位置等的数据可能以结构化形式存在于您的企业中的某个位置，并且可以直接从其所在的位置获取。以关系数据库中最常见的情况为例，您可以使用遵循经过验证的关系到图映射规则的标准工具 ¹⁴ 。

Working with Knowledge Graphs

使用知识图

Once you have a knowledge graph, there is a growing abundance of frameworks for doing GraphRAG, including LlamaIndex Property Graph Index, Langchain’s Neo4j integration as well as Haystack’s and others. This space is moving fast, but we’re now at the point where programmatic methods are becoming straightforward.

一旦你有了知识图谱，就会有越来越多的框架用于 GraphRAG，包括 LlamaIndex Property Graph Index、Langchain 的 Neo4j 集成以及 Haystack 等。这个领域正在快速发展，但我们现在正处于程序化方法变得简单的阶段。

The same is true on the graph construction front, with tools such as the Neo4j Importer, which has a graphical UI for mapping & importing tabular data into a graph, and Neo4j’s new v1 LLM Knowledge Graph Builder mentioned above. The picture below summarizes the steps for building a knowledge graph.

在图形构建方面也是如此，使用诸如 Neo4j Importer 之类的工具，它具有用于将表格数据映射和导入到图形中的图形 UI，以及上面提到的 Neo4j 的新 v1 LLM 知识图生成器。下图总结了构建知识图谱的步骤。

The other thing you’ll find yourself doing with knowledge graphs is mapping human-language questions to graph database queries. A new open source tool from Neo4j, NeoConverse, is designed to help with natural language querying of graphs. It’s a first solid step forward toward generalizing this¹⁵.

您会发现自己使用知识图做的另一件事是将人类语言问题映射到图数据库查询。 Neo4j 的一个新开源工具 NeoConverse 旨在帮助进行图形的自然语言查询。这是朝着泛化这个 ¹⁵ 迈出的坚实的第一步。

While it’s certainly the case that graphs require some work and learning to get started with, there is also good news in that it’s getting easier & easier as the tools improve.

虽然图表确实需要一些工作和学习才能开始，但也有好消息，随着工具的改进，它变得越来越容易。

Conclusion: GraphRAG is the Next Natural Step for RAG

结论：GraphRAG 是 RAG 的下一个自然步骤

The word-based computations and language skills inherent in LLMs and vector-based RAG offer good results. To get a consistently great result, one needs to go beyond strings and capture the world model in addition to the word model. In the same way that Google discovered that to master search, they needed to go beyond mere textual analysis and map out the underlying things underneath the strings, we are beginning to see the same pattern emerge in the world of AI. This pattern is GraphRAG.

LLMs 和基于向量的 RAG 固有的基于单词的计算和语言技能提供了良好的结果。为了获得始终如一的出色结果，我们需要超越字符串并捕获除了单词模型之外的世界模型。就像谷歌发现，要掌握搜索，他们需要超越单纯的文本分析，并找出字符串背后的底层事物，我们开始看到人工智能世界中出现同样的模式。这种模式就是 GraphRAG。

Progress happens in S-curves: as one technology tops out, another spurs progress and leapfrogs this prior. As GenAI progresses, for uses where answer quality is essential; or where an internal, external, or regulatory stakeholder requires explainability; or where fine-grained controls over access to data for privacy and security is needed, then there’s a good chance your next GenAI application will be using a knowledge graph.

进步发生在 S 曲线上：当一种技术达到顶峰时，另一种技术就会刺激进步并超越之前的技术。随着 GenAI 的进步，对于答案质量至关重要的用途；或者内部、外部或监管利益相关者需要解释性的情况；或者，如果需要对数据访问进行细粒度控制以保护隐私和安全，那么您的下一个 GenAI 应用程序很可能会使用知识图谱。

You Can Experience GraphRAG Firsthand!

您可以亲身体验 GraphRAG！

If you’re ready to take the next step with GraphRAG, I invite you to try the Neo4j LLM Knowledge Graph Builder. This simple web app lets you create a knowledge graph in just a few clicks, from unstructured text sources like PDFs, web pages, and YouTube videos. It’s the perfect playground for experiencing the power of GraphRAG firsthand.

如果您准备好使用 GraphRAG 进行下一步，我邀请您尝试 Neo4j LLM 知识图生成器。这个简单的 Web 应用程序让您只需点击几下即可从 PDF、网页和 YouTube 视频等非结构化文本源创建知识图。这是亲身体验 GraphRAG 强大功能的完美场所。

With the LLM Knowledge Graph Builder, you can:

使用LLM知识图生成器，您可以：

• Connect to your free cloud-based Neo4j instance and build a graph from your favorite text sources.

  连接到您基于云的免费 Neo4j 实例，并从您最喜欢的文本源构建图表。

• Explore your newly created knowledge graph with interactive visualizations.

  通过交互式可视化探索新创建的知识图。

• Chat with your data and put GraphRAG to the test.

  与您的数据交流并测试 GraphRAG。

• Integrate your knowledge graph into applications and unlock new insights.

  将您的知识图谱集成到应用程序中并释放新的见解。

To get started, spin up a free AuraDB instance and build your knowledge graph. You can learn more about the Neo4j LLM Knowledge Graph Builder and get a guided tour here!

首先，启动一个免费的 AuraDB 实例并构建您的知识图。您可以在此处了解有关 Neo4j LLM 知识图生成器的更多信息并获得指导！

Acknowledgments 致谢

A great many people contributed to this post. I’d like to acknowledge all of you who share your learnings, writings, and code—many examples of which are cited here—and encourage you to keep doing so. It is by sharing as a community that we all learn.

很多人都为这篇文章做出了贡献。我要感谢所有分享您的学习、著作和代码的人（这里引用了其中的许多示例），并鼓励您继续这样做。我们通过社区分享来学习。

I would also like to thank the many people who see the importance of GraphRAG and who generously offered their time to review and comment on the post itself. In many cases, this was informed by examples showing up in their world.

我还要感谢许多看到 GraphRAG 重要性并慷慨地花时间对帖子本身进行审查和评论的人们。在许多情况下，这是通过他们的世界中出现的例子得知的。

Rather than attempting to name everyone, I’d like to call out some of the people outside of what you would normally think about as the “graph world.” We are together seeing GraphRAG as not only an important trend but as a convergence between two worlds.

我不想尝试说出每个人的名字，而是想指出一些你通常认为的“图形世界”之外的人。我们共同认为 GraphRAG 不仅是一个重要趋势，而且是两个世界之间的融合。

Having said all of this, my deepest thanks to all of you, including (alphabetically by last name):

说了这么多，我向你们所有人表示最深切的感谢，包括（按姓氏字母顺序排列）：

• Harrison Chase, CEO of Langchain

  哈里森·蔡斯 (Harrison Chase)，Langchain 首席执行官

• Ali Ghodsi, CEO of Databricks

  Ali Ghodsi，Databricks 首席执行官

• Rod Johnson, Investor and Founder of SpringSource

  Rod Johnson，SpringSource 投资者兼创始人

• Douwe Kiela, CEO of ContextualAI and Co-inventor of RAG

  Douwe Kiela，ContextualAI 首席执行官兼 RAG 联合发明人

• Christina Li, FPV Ventures

  克里斯蒂娜·李，FPV Ventures

• Jerry Liu, CEO of LlamaIndex

  刘杰瑞，LlamaIndex首席执行官

• Owen Robertson, Principal, DTS

  欧文·罗伯逊 (Owen Robertson)，DTS 负责人

• Milos Rusic, CEO of deepset / Haystack

  Milos Rusic，deepset / Haystack 首席执行官

Supplement: Further Reading

补充：进一步阅读

There’s been a lot written about this topic, with new insights and examples appearing every day. While I can’t hope to provide a comprehensive list, here are a few particularly good pieces you can check out if you’re interested in learning more:

关于这个主题的文章有很多，每天都有新的见解和例子出现。虽然我不希望提供完整的列表，但如果您有兴趣了解更多信息，可以查看以下一些特别好的文章：

• The DeepLearning.AI short course on Knowledge Graphs for RAG is a great 60-minute way to get started.

  DeepLearning.AI RAG 知识图短期课程是一个很好的 60 分钟入门方式。

• The GraphRAG Ecosystem Tools. Start by spending a few minutes creating a knowledge graph of the data and concepts in a video from YouTube or your favorite PDF or Wikipedia page using the LLM Knowledge Graph Builder. If you don’t already have an Aura Free instance, you can create your own one here for us with the Knowledge Graph Builder.

  GraphRAG 生态系统工具。首先，花几分钟时间使用LLM知识图生成器创建 YouTube 视频或您最喜欢的 PDF 或维基百科页面中的数据和概念的知识图。如果您还没有 Aura Free 实例，您可以使用知识图生成器在此处为我们创建您自己的实例。

• Join the GraphRAG Discord.

  加入 GraphRAG Discord。

• Tomaz Bratanic’s post called Implementing ‘From Local to Global’ GraphRAG with Neo4j and LangChain: Constructing the Graph, which integrates Microsoft’s GraphRAG work into a Neo4j + Langchain pipeline.

  Tomaz Bratanic 的帖子名为《使用 Neo4j 和 LangChain 实现“从本地到全局”GraphRAG：构建图》，其中将 Microsoft 的 GraphRAG 工作集成到 Neo4j + Langchain 管道中。

• Any of Tomaz Bratanic’s many other blog posts. Seriously, they’re all awesome.

  Tomaz Bratanic 的许多其他博客文章中的任何一篇。说真的，他们都很棒。

• Ben Lorica’s two posts: Charting the Graphical Roadmap to Smarter AI and GraphRAG: Design Patterns, Challenges, Recommendations.

  Ben Lorica 的两篇文章：绘制智能 AI 的图形路线图和 GraphRAG：设计模式、挑战、建议。

• A couple of audio references:

  一些音频参考：

  • • The Data Exchange podcast episode, Supercharging AI with Graphs (June 27, 2024) where Ben and I both discuss the material in this post, and more.

      在数据交换播客节目《用图表增强人工智能》（2024 年 6 月 27 日）中，Ben 和我都讨论了本文中的内容以及更多内容。

    • The July 4, 2024 ThursdAI podcast 1-year anniversary episode, which includes a dedicated segment on GraphRAG, led by Emil Eifrem.

      2024 年 7 月 4 日的 ThursdAI 播客一周年纪念日节目，其中包括由 Emil Eifrem 领导的 GraphRAG 专题片段。

• Deloitte’s paper titled Responsible Enterprise Decisions with Knowledge-Enriched Generative AI, with the subtitle Why is it essential for enterprise-level generative AI to incorporate knowledge graphs?

  德勤的论文题为“利用知识丰富的生成式人工智能进行负责任的企业决策”，副标题是“为什么企业级生成式人工智能必须整合知识图谱？”

• Jesus Barrasa’s Going Meta series. It’s 27 videos and counting, each covering a different aspect or example of GraphRAG.

  Jesus Barrasa 的 Going Meta 系列。该视频共有 27 个视频，并且还在不断增加，每个视频都涵盖 GraphRAG 的不同方面或示例。

• Any of Leann Chen’s learning videos, including You Need Better Knowledge Graphs for Your RAG and Build an Advanced RAG Chatbot with Neo4j Knowledge Graph.

  Leann Chen 的任何学习视频，包括 You Need Better Knowledge Graphs for Your RAG 和 Build an Advanced RAG Chatbot with Neo4j Knowledge Graph。

• LlamaIndex’s six-part lightning Introduction to Property Graphs.

  LlamaIndex 的六部分闪电属性图简介。

• The GraphStuff.fm podcast, hosted by Jennifer Reif, Andreas Kollegger, Alison Cossette, Jason Koo.

  GraphStuff.fm 播客，由 Jennifer Reif、Andreas Kollegger、Alison Cossette、Jason Koo 主持。

• Last but not least, if you find yourself needing to justify GraphRAG to your boss and want to throw around some extra weight, look no further than Gartner’s 2024 Impact Radar for Generative AI, which puts knowledge graphs at the center of the bullseye for GenAI technologies most relevant right now!

  最后但并非最不重要的一点是，如果您发现自己需要向老板证明 GraphRAG 的合理性，并希望增加一些额外的权重，那么 Gartner 的 2024 年生成式 AI 影响雷达就是您的最佳选择，它将知识图谱置于 GenAI 技术的靶心中心现在最相关！

---

¹ Read this blog post to see just how great an analogy Google’s journey in web search is for what’s happening now in GenAI.

阅读这篇博文，了解 Google 在网络搜索领域的历程与 GenAI 目前正在发生的事情有多么精彩的类比。

² NB: These particular numbers may or may not actually represent an apple. It’s hard to know, which illustrates one of the key differences between vectors and graphs.

² 注意：这些特定数字实际上可能代表也可能不代表苹果。这很难知道，这说明了向量和图之间的主要区别之一。

³ As is discussed later in the “Knowledge Graph Creation” section, another kind of knowledge graph distinct from the “domain graph” is emerging and proving to be useful. This is the “lexical graph”, which instead of a world model is a graph of the vector chunks and how they relate to one another and to the document structures around them: tables/ figures/ pages/ documents/ collections/ authors and so on.

³ 正如稍后在“知识图谱创建”部分中所讨论的，另一种与“领域图谱”不同的知识图谱正在出现并被证明是有用的。这就是“词汇图”，它不是世界模型，而是向量块的图，以及它们彼此之间以及它们周围的文档结构的关系：表格/数字/页面/文档/集合/作者等等。

⁴ Naturally this often shows up in the real world not just as a single all-encompassing step, but increasingly as a part of an agentic pipeline that follows its own set of steps and logic. This by the way is also a graph. As these get more complex one could potentially see capturing these workflows and rules in a graph database rather than in code. But we’re not there yet and it’s a different topic from the one at hand.

⁴ 自然地，这在现实世界中经常出现，不仅仅是作为一个包罗万象的单一步骤，而且越来越多地作为遵循其自己的一组步骤和逻辑的代理管道的一部分。顺便说一句，这也是一个图表。随着这些变得越来越复杂，人们可能会看到在图形数据库而不是代码中捕获这些工作流程和规则。但我们还没有到那一步，这与当前的话题不同。

⁵ This kicks in once you already have a knowledge graph in place. This doesn’t happen for free, but you may be surprised at how accessible this is becoming with the latest advances. Because this is such a foundational topic, we’ve dedicated a section after this one on the science and art of building a knowledge graph.

⁵ 一旦您已经有了知识图谱，这就开始了。这并不是免费的，但您可能会惊讶地发现，随着最新的进步，这变得如此容易。因为这是一个非常基础的主题，所以我们在这一节之后专门专门介绍了构建知识图谱的科学和艺术。

⁶ Knowledge graphs can also help with other forms of traceability, such as capturing how data flows between systems with systems-of-systems / provenance / data lineage graphs. They can also offer other AI benefits, such as keeping track of resolved entities. Since the focus here is GraphRAG, we’ll leave all of that aside.

⁶ 知识图还可以帮助实现其他形式的可追溯性，例如使用系统间/来源/数据沿袭图来捕获数据在系统之间的流动方式。它们还可以提供其他人工智能优势，例如跟踪已解析的实体。由于这里的重点是 GraphRAG，所以我们将把所有这些都放在一边。

⁷ If you’re looking to dive more deeply into this and get your hands into some working code, I highly recommend my colleague Tomaz Bratanic’s post: Implementing ‘From Local to Global’ GraphRAG with Neo4j and LangChain: Constructing the Graph. This takes Microsoft’s work a step further, integrating it into a Neo4j + Langchain pipeline.

⁷ 如果您想更深入地了解这一点并尝试一些工作代码，我强烈推荐我的同事 Tomaz Bratanic 的帖子：使用 Neo4j 和 LangChain 实现“从本地到全球”GraphRAG ：构建图表。这使微软的工作更进一步，将其集成到 Neo4j + Langchain 管道中。

⁸ The paper itself includes a more detailed comparison of the GraphRAG and vector-only RAG approaches, finding that GraphRAG improved answers by 77.6% in MRR and by 0.32 in BLEU over the baseline.

⁸ 论文本身对 GraphRAG 和纯向量 RAG 方法进行了更详细的比较，发现 GraphRAG 在 MRR 中的答案比基线提高了 77.6%，在 BLEU 中的答案比基线提高了 0.32。

⁹ Powered by Neo4j, as it happens.

⁹ 碰巧由 Neo4j 提供支持。

¹⁰ Which is a great webinar showing off using their new (circa May ‘24) Property Graph Index, which includes built-in methods for converting text into a graph.

¹⁰ 这是一个很棒的网络研讨会，展示了他们新的（大约 24 年 5 月）Property Graph Index 的使用，其中包括将文本转换为图表的内置方法。

¹¹ I think we all know what “impact” means, but just to break it down: this includes any decision where a wrong answer can have health & human safety impacts, social & fairness impacts, reputational impacts, or high dollar impacts. It obviously also includes any decision that might fall under government regulation or where there is otherwise a compliance impact.

¹¹ 我想我们都知道“影响”的含义，但只是将其分解：这包括任何错误答案可能产生健康和人类安全影响、社会和公平影响、声誉影响或高美元影响。显然，它还包括任何可能受到政府监管或存在合规影响的决定。

¹² Note that the term word “lexical” here refers not just to individual words, but more broadly (as the following dictionary definition suggests) “of or relating to words or the vocabulary of a language”. This encompasses everything that lies in the domain of a body of words and their relationships.

¹² 请注意，术语“词汇”在这里不仅指单个单词，而且更广泛地（如以下词典定义所示）“属于或与某种语言的单词或词汇相关”。这涵盖了单词及其关系领域中的所有内容。

¹³ A few libraries that do this are, in no particular order: Docs2KG, Diffbot, GLiNER, spaCy, NuMind, NetOwl®, and (particularly for its strength in entity resolution) Senzing.

¹³ 执行此操作的一些库（排名不分先后）是：Docs2KG、Diffbot、GLiNER、spaCy、NuMind、NetOwl® 和（特别是其在实体解析方面的优势）Senzing。

¹⁴ Stay tuned for a new version of this tool in H2 2024 that will support direct connectivity to your relational database of choice.

¹⁴ 请继续关注该工具在 2024 年下半年推出的新版本，该版本将支持直接连接到您选择的关系数据库。

¹⁵ NeoConverse and the LLM GraphBUilder are both part of a growing body of GraphRAG Ecosystem Tools built by Neo4j.

¹⁵ NeoConverse 和 LLM GraphBUilder 都是由 Neo4j 构建的不断壮大的 GraphRAG 生态系统工具的一部分。