Update README.md
Browse files
README.md
CHANGED
|
@@ -28,6 +28,8 @@ license: apache-2.0
|
|
| 28 |
|
| 29 |
The GFM-RAG is the first graph foundation model-powered RAG pipeline that combines the power of graph neural networks to reason over knowledge graphs and retrieve relevant documents for question answering.
|
| 30 |
|
|
|
|
|
|
|
| 31 |
We first build a knowledge graph index (KG-index) from the documents to capture the relationships between knowledge. Then, we feed the query and constructed KG-index into the pre-trained graph foundation model (GFM) retriever to obtain relevant documents for LLM generation. The GFM retriever experiences large-scale training and can be directly applied to unseen datasets without fine-tuning.
|
| 32 |
|
| 33 |
For more details, please refer to our [project page](https://rmanluo.github.io/gfm-rag/) and [paper](https://www.arxiv.org/abs/2502.01113).
|
|
|
|
| 28 |
|
| 29 |
The GFM-RAG is the first graph foundation model-powered RAG pipeline that combines the power of graph neural networks to reason over knowledge graphs and retrieve relevant documents for question answering.
|
| 30 |
|
| 31 |
+
<img src="https://github.com/RManLuo/gfm-rag/blob/main/docs/images/intro.png?raw=true" width = "800" />
|
| 32 |
+
|
| 33 |
We first build a knowledge graph index (KG-index) from the documents to capture the relationships between knowledge. Then, we feed the query and constructed KG-index into the pre-trained graph foundation model (GFM) retriever to obtain relevant documents for LLM generation. The GFM retriever experiences large-scale training and can be directly applied to unseen datasets without fine-tuning.
|
| 34 |
|
| 35 |
For more details, please refer to our [project page](https://rmanluo.github.io/gfm-rag/) and [paper](https://www.arxiv.org/abs/2502.01113).
|