Skip to content

Commit

Permalink
Readme optimize (#65)
Browse files Browse the repository at this point in the history 
* update readme for cn,en

* update readme for cn,en

* update readme for cn,en

* minor format tweak

---------

Co-authored-by: huaidong.xhd <[email protected]>
  • Loading branch information
@caszkgui @xionghuaidong
caszkgui and xionghuaidong authored Nov 21, 2024
1 parent 421090e commit 8c80cdc
Show file tree
Hide file tree
Showing 3 changed files with 129 additions and 85 deletions.
112 changes: 69 additions & 43 deletions README.md
View file
Original file line number Diff line number Diff line change
@@ -1,60 +1,85 @@
# KAG: Knowledge Augmented Generation

[中文版文档](./README_cn.md)
[日本語版ドキュメント](./README_ja.md)

## 1. What is KAG

Retrieval Augmentation Generation (RAG) technology promotes the integration of domain applications with large language models. However, RAG has problems such as a large gap between vector similarity and knowledge reasoning correlation, and insensitivity to knowledge logic (such as numerical values, time relationships, expert rules, etc.), which hinder the implementation of professional knowledge services.

On October 24, 2024, OpenSPG released v0.5, officially releasing the professional domain knowledge service framework of knowledge augmented generation (KAG). The goal of KAG is to build a knowledge-enhanced LLM service framework in professional domains, supporting logical reasoning, factual Q&A, etc. KAG fully integrates the logical and factual characteristics of the KGs. Meanwhile, it uses OpenIE to lower the threshold for knowledgeization of domain documents and alleviates the sparsity problem of the KG through hybrid reasoning. As far as we know, KAG is the only RAG framework that supports logical reasoning and multi-hop factual Q&A. Its core features include:

* Knowledge and Chunk Mutual Indexing structure to integrate more complete contextual text information
* Knowledge alignment using conceptual semantic reasoning to alleviate the noise problem caused by OpenIE
* Schema-constrained knowledge construction to support the representation and construction of domain expert knowledge
* Logical form-guided hybrid reasoning and retrieval to support logical reasoning and multi-hop reasoning Q&A

KAG is significantly better than NaiveRAG, HippoRAG and other methods in multi-hop Q&A tasks. The F1 score on hotpotQA is relatively increased by 19.6%, and the F1 score on 2wiki is relatively increased by 33.5%. We have successfully applied KAG to Ant Group's professional knowledge Q&A tasks, such as e-government Q&A and e-health Q&A, and the professionalism has been significantly improved compared to the traditional RAG method.
<div align="center">
<a href="https://spg.openkg.cn/en-US">
<img src="./_static/images/OpenSPG-1.png" width="520" alt="openspg logo">
</a>
</div>

<p align="center">
<a href="./README.md">English</a> |
<a href="./README_cn.md">简体中文</a> |
<a href="./README_ja.md">日本語版ドキュメント</a>
</p>

<p align="center">
<a href='https://arxiv.org/pdf/2409.13731'><img src='https://img.shields.io/badge/arXiv-2409.13731-b31b1b'></a>
<a href="https://github.com/OpenSPG/KAG/releases/latest">
<img src="https://img.shields.io/github/v/release/OpenSPG/KAG?color=blue&label=Latest%20Release" alt="Latest Release">
</a>
<a href="https://github.com/OpenSPG/KAG/blob/main/LICENSE">
<img height="21" src="https://img.shields.io/badge/License-Apache--2.0-ffffff?labelColor=d4eaf7&color=2e6cc4" alt="license">
</a>
</p>

# 1. What is KAG?

KAG is a logical reasoning and Q&A framework based on the [OpenSPG](https://github.com/OpenSPG/openspg) engine and large language models, which is used to build logical reasoning and Q&A solutions for vertical domain knowledge bases. KAG can effectively overcome the ambiguity of traditional RAG vector similarity calculation and the noise problem of GraphRAG introduced by OpenIE. KAG supports logical reasoning and multi-hop fact Q&A, etc., and is significantly better than the current SOTA method.

The goal of KAG is to build a knowledge-enhanced LLM service framework in professional domains, supporting logical reasoning, factual Q&A, etc. KAG fully integrates the logical and factual characteristics of the KGs. Its core features include:

- Knowledge and Chunk Mutual Indexing structure to integrate more complete contextual text information
- Knowledge alignment using conceptual semantic reasoning to alleviate the noise problem caused by OpenIE
- Schema-constrained knowledge construction to support the representation and construction of domain expert knowledge
- Logical form-guided hybrid reasoning and retrieval to support logical reasoning and multi-hop reasoning Q&A

⭐️ Star our repository to stay up-to-date with exciting new features and improvements! Get instant notifications for new releases! 🌟

![Star KAG](./_static/images/star-kag.gif)

## 2 Core Features
# 2. Core Features

### 2.1 Knowledge Representation
## 2.1 Knowledge Representation

In the context of private knowledge bases, unstructured data, structured information, and business expert experience often coexist. KAG references the DIKW hierarchy to upgrade SPG to a version that is friendly to LLMs. For unstructured data such as news, events, logs, and books, as well as structured data like transactions, statistics, and approvals, along with business experience and domain knowledge rules, KAG employs techniques such as layout analysis, knowledge extraction, property normalization, and semantic alignment to integrate raw business data and expert rules into a unified business knowledge graph.
In the context of private knowledge bases, unstructured data, structured information, and business expert experience often coexist. KAG references the DIKW hierarchy to upgrade SPG to a version that is friendly to LLMs.

For unstructured data such as news, events, logs, and books, as well as structured data like transactions, statistics, and approvals, along with business experience and domain knowledge rules, KAG employs techniques such as layout analysis, knowledge extraction, property normalization, and semantic alignment to integrate raw business data and expert rules into a unified business knowledge graph.

![KAG Diagram](./_static/images/kag-diag.jpg)

This makes it compatible with schema-free information extraction and schema-constrained expertise construction on the same knowledge type (e. G., entity type, event type), and supports the cross-index representation between the graph structure and the original text block. This mutual index representation is helpful to the construction of inverted index based on graph structure, and promotes the unified representation and reasoning of logical forms.
This makes it compatible with schema-free information extraction and schema-constrained expertise construction on the same knowledge type (e. G., entity type, event type), and supports the cross-index representation between the graph structure and the original text block.

This mutual index representation is helpful to the construction of inverted index based on graph structure, and promotes the unified representation and reasoning of logical forms.

### 2.2 Mixed Reasoning Guided by Logic Forms
## 2.2 Mixed Reasoning Guided by Logic Forms

![Logical Form Solver](./_static/images/kag-lf-solver.png)

KAG proposes a logically formal guided hybrid solution and inference engine. The engine includes three types of operators: planning, reasoning, and retrieval, which transform natural language problems into problem solving processes that combine language and notation. In this process, each step can use different operators, such as exact match retrieval, text retrieval, numerical calculation or semantic reasoning, so as to realize the integration of four different problem solving processes: Retrieval, Knowledge Graph reasoning, language reasoning and numerical calculation.
KAG proposes a logically formal guided hybrid solution and inference engine.

The engine includes three types of operators: planning, reasoning, and retrieval, which transform natural language problems into problem solving processes that combine language and notation.

In this process, each step can use different operators, such as exact match retrieval, text retrieval, numerical calculation or semantic reasoning, so as to realize the integration of four different problem solving processes: Retrieval, Knowledge Graph reasoning, language reasoning and numerical calculation.

## 3. Release Notes
# 3. Release Notes

### 3.1 Released Versions
* 2024.11.21 : Support docs upload, model invoke concurrency setting, User experience optimization, etc.
* 2024.10.25 : KAG release
## 3.1 Latest Updates

### 3.2 Future Plan
* 2024.12 : domain knowledge injection, domain schema customization, QFS tasks support, Visual query analysis, etc.
* 2025.01 : Logical reasoning optimization, conversational tasks support
* 2025.02 : kag-model release, kag solution for event reasoning knowledge graph and medical knowledge graph
* 2025.03 : Kag front-end open source, distributed build support, mathematical reasoning optimization
* 2024.11.21 : Support Word docs upload, model invoke concurrency setting, User experience optimization, etc.
* 2024.10.25 : KAG initial release

## 3.2 Future Plans

## 4. How to use it
* domain knowledge injection, domain schema customization, QFS tasks support, Visual query analysis, etc.
* Logical reasoning optimization, conversational tasks support
* kag-model release, kag solution for event reasoning knowledge graph and medical knowledge graph
* kag front-end open source, distributed build support, mathematical reasoning optimization

### 4.1 product-based (for ordinary users)
# 4. Quick Start

#### 4.1.1 Engine & Dependent Image Installation
## 4.1 product-based (for ordinary users)

### 4.1.1 Engine & Dependent Image Installation

* **Recommend System Version:**

Expand All @@ -81,19 +106,20 @@ curl -sSL https://raw.githubusercontent.com/OpenSPG/openspg/refs/heads/master/de
docker compose -f docker-compose.yml up -d
```

#### 4.1.2 Use the product
### 4.1.2 Use the product

Navigate to the default url of the KAG product with your browser: <http://127.0.0.1:8887>

See the [Product](https://openspg.yuque.com/ndx6g9/wc9oyq/rgd8ecefccwd1ga5) guide for detailed introduction.

### 4.2 toolkit-based (for developers)
## 4.2 toolkit-based (for developers)

#### 4.2.1 Engine & Dependent Image Installation
### 4.2.1 Engine & Dependent Image Installation

Refer to the 3.1 section to complete the installation of the engine & dependent image.

#### 4.2.2 Installation of KAG
### 4.2.2 Installation of KAG


**macOS / Linux developers**

Expand All @@ -117,33 +143,33 @@ Refer to the 3.1 section to complete the installation of the engine & dependent
# Install KAG: cd KAG && pip install -e .
```

#### 4.2.3 Use the toolkit
### 4.2.3 Use the toolkit

Please refer to the [Quick Start](https://openspg.yuque.com/ndx6g9/wc9oyq/owp4sxbdip2u7uvv) guide for detailed introduction of the toolkit. Then you can use the built-in components to reproduce the performance results of the built-in datasets, and apply those components to new busineness scenarios.

## 5. Technical Architecture
# 5. Technical Architecture

![Figure 1 KAG technical architecture](./_static/images/kag-arch.png)
![KAG technical architecture](./_static/images/kag-arch.png)

The KAG framework includes three parts: kg-builder, kg-solver, and kag-model. This release only involves the first two parts, kag-model will be gradually open source release in the future.

kg-builder implements a knowledge representation that is friendly to large-scale language models (LLM). Based on the hierarchical structure of DIKW (data, information, knowledge and wisdom), IT upgrades SPG knowledge representation ability, and is compatible with information extraction without schema constraints and professional knowledge construction with schema constraints on the same knowledge type (such as entity type and event type), it also supports the mutual index representation between the graph structure and the original text block, which supports the efficient retrieval of the reasoning question and answer stage.

kg-solver uses a logical symbol-guided hybrid solving and reasoning engine that includes three types of operators: planning, reasoning, and retrieval, to transform natural language problems into a problem-solving process that combines language and symbols. In this process, each step can use different operators, such as exact match retrieval, text retrieval, numerical calculation or semantic reasoning, so as to realize the integration of four different problem solving processes: Retrieval, Knowledge Graph reasoning, language reasoning and numerical calculation.

## 6. Contact us
# 6. Contact us

**GitHub**: <https://github.com/OpenSPG/KAG>

**OpenSPG**: <https://spg.openkg.cn/>

<img src="./_static/images/openspg-qr.png" alt="Contact Us: OpenSPG QR-code" width="200">

# Differences between KAG, RAG, and GraphRAG
# 7. Differences between KAG, RAG, and GraphRAG

**KAG introduction and applications**: <https://github.com/orgs/OpenSPG/discussions/52>

# Cite
# 8. Citation

If you use this software, please cite it as below:

Expand Down
Loading

0 comments on commit 8c80cdc

Please sign in to comment.