# GraphRAG
**Repository Path**: DY88ZJH/GraphRAG
## Basic Information
- **Project Name**: GraphRAG
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-11-15
- **Last Updated**: 2025-11-15
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
## πΎ DIGIMON: Deep Analysis of Graph-Based Retrieval-Augmented Generation (RAG) Systems
> **GraphRAG** is a popular π₯π₯π₯ and powerful πͺπͺπͺ RAG system! ππ‘ Inspired by systems like Microsoft's, graph-based RAG is unlocking endless possibilities in AI.
> Our project focuses on **modularizing and decoupling** these methods 𧩠to **unveil the mystery** π΅οΈββοΈπβ¨ behind them and share fun and valuable insights! π€©π« Our projectπ¨ is included in [Awesome Graph-based RAG](https://github.com/DEEP-PolyU/Awesome-GraphRAG).
---
[](https://www.arxiv.org/abs/2503.04338)
[](https://pypi.org/project/agentscope/)
[](https://modelscope.github.io/agentscope/tutorial/contribute.html)
- If you find our work helpful, please kindly cite [our paper](https://www.arxiv.org/abs/2503.04338).
- Download the datasets [GraphRAG-dataset](https://drive.google.com/file/d/14nYYw-3FutumQnSRwKavIbG3LRSmIzDX/view?usp=sharing)
---
## Quick Start π
### From Source
```bash
# Clone the repository from GitHub
git clone https://github.com/JayLZhou/GraphRAG.git
cd GraphRAG
```
### Run a Method
You can run different GraphRAG methods by specifying the corresponding configuration file (`.yaml`).
#### Example: Running RAPTOR
```bash
python main.py -opt Option/Method/RAPTOR.yaml -dataset_name your_dataset
```
#### Available Methods:
The following methods are available, and each can be run using the same command format:
```bash
python main.py -opt Option/Method/.yaml -dataset_name your_dataset
```
Replace `` with one of the following:
- `Dalk`
- `GR`
- `LGraphRAG` (Local search in GraphRAG)
- `GGraphRAG` (Global search in GraphRAG)
- `HippoRAG`
- `KGP`
- `LightRAG`
- `RAPTOR`
- `ToG`
For example, to run `GraphRAG`:
```bash
python main.py -opt Option/Method/GraphRAG.yaml -dataset_name your_dataset
```
### Dependencies
Ensure you have the required dependencies installed (The default experiment name is digimon):
```bash
conda env create -f experiment.yml -n your_experiment_name
```
#### Supported LLM Backends
GraphRAG supports both cloud-based and local deployment of LLMs:
- **Cloud-based models:** OpenAI (e.g., `gpt-4`, `gpt-3.5-turbo`)
- **Locally deployed models:** `Ollama` and `LlamaFactory`
To use a local model, set `api_type` to `open_llm` in the configuration file.
##### Example Configuration (`config.yaml`):
```yaml
llm:
api_type: "openai/open_llm" # Options: "openai" or "open_llm" (For Ollama and LlamaFactory)
model: "YOUR_LOCAL_MODEL_NAME"
base_url: "YOUR_LOCAL_URL" # Change this for local models
api_key: "YOUR_API_KEY" # Not required for local models
```
##### For `LlamaFactory` or `Ollama`, ensure the model is correctly installed and running in your local environment.
You can refer to the Readme of [`LlamaFactory`](https://github.com/hiyouga/LLaMA-Factory)
```yaml
llm:
api_type: "open_llm" # Options: "openai" or "open_llm" (For Ollama and LlamaFactory)
model: "YOUR_LOCAL_MODEL_NAME"
base_url: "YOUR_LOCAL_URL" # Change this for local models
api_key: "ANY_THING_IS_OKAY" # Not required for local models
```
---
## Representative Methods
We select the following Graph RAG methods:
| Method | Description| Link | Graph Type|
| --- |--- |--- | :---: |
| RAPTOR | ICLR 2024 | [](https://arxiv.org/abs/2401.18059) [](https://github.com/parthsarthi03/raptor)| Tree |
| KGP | AAAI 2024 | [](https://arxiv.org/abs/2308.11730) [](https://github.com/YuWVandy/KG-LLM-MDQA)| Passage Graph |
| DALK | EMNLP 2024 | [](https://arxiv.org/abs/2405.04819) [](https://github.com/David-Li0406/DALK)| KG |
| HippoRAG | NIPS 2024 | [](https://arxiv.org/abs/2405.14831) [](https://github.com/OSU-NLP-Group/HippoRAG) | KG |
| G-retriever | NIPS 2024 | [](https://arxiv.org/abs/2402.07630) [](https://github.com/XiaoxinHe/G-Retriever)| KG |
| ToG | ICLR 2024 | [](https://arxiv.org/abs/2307.07697) [](https://github.com/IDEA-FinAI/ToG)| KG |
| MS GraphRAG | Microsoft Project | [](https://arxiv.org/abs/2404.16130) [](https://github.com/microsoft/graphrag)| TKG |
| FastGraphRAG | CircleMind Project | [](https://github.com/circlemind-ai/fast-graphrag)| TKG |
| LightRAG | High Star Project | [](https://arxiv.org/abs/2410.05779) [](https://github.com/HKUDS/LightRAG)| RKG |
## Graph Types
Based on the entity and relation, we categorize the graph into the following types:
+ **Chunk Tree**: A tree structure formed by document content and summary.
+ **Passage Graph**: A relational network composed of passages, tables, and other elements within documents.
+ **KG**: knowledge graph (KG) is constructed by extracting entities and relationships from each chunk, which contains only entities and relations, is commonly represented as triples.
+ **TKG**: A textual knowledge graph (TKG) is a specialized KG (following the same construction step as KG), which enriches entities with detailed descriptions and type information.
+ **RKG**: A rich knowledge graph (RKG), which further incorporates keywords associated with relations.
The criteria for the classification of graph types are as follows:
|Graph Attributes | Chunk Tree |Passage Graph | KG | TKG | RKG |
| --- |--- |--- |--- | --- | --- |
|Original Content| β
|β
| β|β|β|
|Entity Name| β|β|β
|β
|β
|
|Entity Type| β| β| β|β
|β
|
|Entity Description|β| β| β|β
|β
|
|Relation Name| β|β|β
|β|β
|
|Relation keyword|β| β| β|β|β
|
|Relation Description|β| β| β|β
|β
|
|Edge Weight| β|β|β
|β
|β
|
## Operators in the Retrieve Stage
> The retrieval stage lies the **key role** βΌοΈ in the entire GraphRAG process. β¨ The goal is to identify query-relevant content that supports the generation phase, enabling the LLM to provide more **accurate** responses.
π‘π‘π‘ After thoroughly reviewing all implementations, we've distilled them into a set of **16** operators π§©π§©. Each method then constructs its retrieval module by combining one or more of these operators π§©.
### Five Types of Operators
> We classify the operators into five categories, each offering a different way to retrieve and structure relevant information from graph-based data.
#### βοΈ Entity Operators
> Retrieve entities (e.g., people, places, organizations) that are most relevant to the given query.
| Name | Description | Example Methods |
|---|---|---|
| **VDB** | Select top-k nodes from the vector database | G-retriever, RAPTOR, KGP |
| **RelNode** | Extract nodes from given relationships | LightRAG |
| **PPR** | Run PPR on the graph, return top-k nodes with PPR scores | FastGraphRAG |
| **Agent** | Utilizes LLM to find the useful entities| ToG |
| **Onehop** | Selects the one-hop neighbor entities of the given entities| LightRAG |
| **Link** | Return top-1 similar entity for each given entity| HippoRAG |
| **TF-IDF** | Rank entities based on the TF-IFG matrix| KGP |
#### β‘οΈ Relationship Operators
> Extracting useful relationships for the given query.
| Name | Description | Example Methods |
|---|---|---|
| **VDB** | Retrieve relationships by vector-database| LightRAGγG-retriever |
| **Onehop** | Selects relationships linked by one-hop neighbors of the given selected entities | Local Search for MS GraphRAG |
| **Aggregator** | Compute relationship scores from entity PPR matrix, return top-k | FastGraphRAG |
| **Agent**| Utilizes LLM to find the useful entities| ToG|
#### π Chunk Operators
> Retrieve the most relevant text segments (chunks) related to the query.
| Name | Description | Example Methods |
|---|---|---|
| **Aggregator** | Use the relationship scores and the relationship-chunk interactions to select the top-k chunks | HippoRAG |
| **FromRel** | Return chunks containing given relationships | LightRAG |
| **Occurrence** | Rank top-k chunks based on occurrence of both entities in relationships | Local Search for MS GraphRAG |
#### π Subgraph Operators
> Extract a relevant subgraph for the given query
| Name | Description | Example Methods |
|---|---|---|
| **KhopPath** | Find k-hop paths with start and endpoints in the given entity set | DALK |
| **Steiner** | Compute Steiner tree based on given entities and relationships | G-retriever |
| **AgentPath** | Identify the most relevant π-hop paths to a given question, by using LLM to filter out the irrelevant paths | TOG |
#### π Community Operators
> Identify high-level information, which is only used for MS GraphRAG.
| **Name** | **Description** | **Example Methods** |
|---|---|---|
| **Entity** | Detects communities containing specified entities | Local Search for MS GraphRAG |
| **Layer** | Returns all communities below a required layer | Global Search for MS GraphRAG |
You can freely πͺ½ combine those operators 𧩠to create more and more GraphRAG methods.
#### π° Examples
> Below, we present some examples illustrating how existing algorithms leverage these operators.
| Name | Operators|
|---|---|
| **HippoRAG** | Chunk (Aggregator) |
| **LightRAG** | Chunk (FromRel) + Entity (RelNode) + Relationship (VDB) |
| **FastGraphRAG** | Chunk (Aggregator) + Entity (PPR) + Relationship (Aggregator) |
## πΉ Our future plans
- [ ] Detailed readme
- [ ] Support RoG, PathRAG, etc.
- [ ] Provide a docker image for easy deployment.
- [ ] Support more LLMs, such as AZURE.
## π§ Cite Our Paper
If you find this work useful, please consider citing our papers:
### In-depth Analysis of Graph-based RAG in a Unified Framework
```
@article{zhou2025depth,
title={In-depth Analysis of Graph-based RAG in a Unified Framework},
author={Zhou, Yingli and Su, Yaodong and Sun, Youran and Wang, Shu and Wang, Taotao and He, Runyuan and Zhang, Yongwei and Liang, Sicong and Liu, Xilin and Ma, Yuchi and others},
journal={arXiv preprint arXiv:2503.04338},
year={2025}
}
```
