Repository files navigation

A relation-free graph construction method for efficient GraphRAG. It eliminates LLM token costs during graph construction, making GraphRAG faster and more efficient than ever.

• ✅Context-Preserving: Relation-free graph construction, relying on lightweight entity recognition and semantic linking to achieve comprehensive contextual comprehension.
• ✅Complex Reasoning: Enables deep retrieval via semantic bridging, achieving multi-hop reasoning in a single retrieval pass without requiring explicit relational graphs.
• ✅High Scalability: Zero LLM token consumption, faster processing speed, and linear time/space complexity.

• [2025-10-27] We releaseLinearRAG, a relation-free graph construction method for efficient GraphRAG.
• [2025-06-06] We releaseGraphRAG-Bench, the benchmark for evaluating GraphRAG models.
• [2025-01-21] We release theGraphRAG survey.

Step 1: Install Python packages

pip install -r requirements.txt

Step 2: Download Spacy language model

python -m spacy download en_core_web_trf

Note: For themedical dataset, you need to install the scientific/biomedical Spacy model:

pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_scibert-0.5.3.tar.gz

Step 3: Set up your OpenAI API key

export OPENAI_API_KEY="your-api-key-here"export OPENAI_BASE_URL="your-base-url-here"

Step 4: Download Datasets

Download the datasets from HuggingFace and place them in thedataset/ folder:

git clone https://huggingface.co/datasets/Zly0523/linear-ragcp -r linear-rag/dataset/* dataset/

Step 5: Prepare Embedding Model

Make sure the embedding model is available at:

model/all-mpnet-base-v2/

SPACY_MODEL="en_core_web_trf"EMBEDDING_MODEL="model/all-mpnet-base-v2"DATASET_NAME="2wikimultihop"LLM_MODEL="gpt-4o-mini"MAX_WORKERS=16python run.py \    --spacy_model${SPACY_MODEL} \    --embedding_model${EMBEDDING_MODEL} \    --dataset_name${DATASET_NAME} \    --llm_model${LLM_MODEL} \    --max_workers${MAX_WORKERS}

Main results of end-to-end performance

Efficiency and performance comparison.

If you find this work helpful, please consider citing us:

@article{zhuang2025linearrag,title={LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora},author={Zhuang, Luyao and Chen, Shengyuan and Xiao, Yilin and Zhou, Huachi and Zhang, Yujing and Chen, Hao and Zhang, Qinggang and Huang, Xiao},journal={arXiv preprint arXiv:2510.10114},year={2025}}

This project is licensed under the GNU General Public License v3.0 (License).

✉️ Email:zhuangluyao523@gmail.com