# vector-graph-rag **Repository Path**: cangmj/vector-graph-rag ## Basic Information - **Project Name**: vector-graph-rag - **Description**: mirror: https://github.com/zilliztech/vector-graph-rag.git - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2026-04-23 - **Last Updated**: 2026-04-23 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README


Vector Graph RAG

Graph RAG with pure vector search β€” no graph database needed.

PyPI Python License Docs Stars Discord

> πŸ’‘ Encode entities and relations as vectors in [Milvus](https://milvus.io/), replace iterative LLM agents with a single reranking pass β€” achieve state-of-the-art multi-hop retrieval at a fraction of the operational and computational cost.

Vector Graph RAG Demo

## ✨ Features - **No Graph Database Required** β€” Pure vector search with Milvus, no Neo4j or other graph databases needed - **Single-Pass LLM Reranking** β€” One LLM call to rerank, no iterative agent loops (unlike IRCoT or multi-step reflection) - **Knowledge-Intensive Friendly** β€” Optimized for domains with dense factual content: legal, finance, medical, literature, etc. - **Zero Configuration** β€” Uses Milvus Lite by default, works out of the box with a single file - **Multi-hop Reasoning** β€” Subgraph expansion enables complex multi-hop question answering - **State-of-the-Art Performance** β€” 87.8% avg Recall@5 on multi-hop QA benchmarks, outperforming HippoRAG ## πŸ“¦ Installation ```bash pip install vector-graph-rag # or uv add vector-graph-rag ```
With document loaders (PDF, DOCX, web pages) ```bash pip install "vector-graph-rag[loaders]" # or uv add "vector-graph-rag[loaders]" ```
## πŸš€ Quick Start ```python from vector_graph_rag import VectorGraphRAG rag = VectorGraphRAG() # reads OPENAI_API_KEY from environment rag.add_texts([ "Albert Einstein developed the theory of relativity.", "The theory of relativity revolutionized our understanding of space and time.", ]) result = rag.query("What did Einstein develop?") print(result.answer) ``` > **Note:** Set `OPENAI_API_KEY` environment variable before running.
πŸ“„ With pre-extracted triplets β€” click to expand Skip LLM extraction if you already have knowledge graph triplets: ```python rag.add_documents_with_triplets([ { "passage": "Einstein developed relativity at Princeton.", "triplets": [ ["Einstein", "developed", "relativity"], ["Einstein", "worked at", "Princeton"], ], }, ]) ```
🌐 Import from URLs and files β€” click to expand ```python from vector_graph_rag import VectorGraphRAG from vector_graph_rag.loaders import DocumentImporter # Import from URLs, PDFs, DOCX, etc. (with automatic chunking) importer = DocumentImporter(chunk_size=1000, chunk_overlap=200) result = importer.import_sources([ "https://en.wikipedia.org/wiki/Albert_Einstein", "/path/to/document.pdf", "/path/to/report.docx", ]) rag = VectorGraphRAG(milvus_uri="./my_graph.db") rag.add_documents(result.documents, extract_triplets=True) result = rag.query("What did Einstein discover?") print(result.answer) ```
βš™οΈ Custom configuration β€” click to expand ```python rag = VectorGraphRAG( milvus_uri="./my_data.db", # or remote Milvus / Zilliz Cloud llm_model="gpt-4o", embedding_model="text-embedding-3-large", collection_prefix="my_project", # isolate multiple datasets ) ``` All settings can also be configured via environment variables with `VGRAG_` prefix or a `.env` file: ```bash VGRAG_LLM_MODEL=gpt-4o VGRAG_EMBEDDING_MODEL=text-embedding-3-large VGRAG_MILVUS_URI=http://localhost:19530 ```
> πŸ“– Full Python API reference β†’ [Python API docs](https://zilliztech.github.io/vector-graph-rag/python-api/) ## πŸ”¬ How It Works **Indexing:** ``` Documents β†’ Triplet Extraction (LLM) β†’ Entities + Relations β†’ Embedding β†’ Milvus ``` **Query:** ``` Question β†’ Entity Extraction β†’ Vector Search β†’ Subgraph Expansion β†’ LLM Reranking β†’ Answer ``` **Example:** *"What did Einstein develop?"* 1. Extract entity: `Einstein` 2. Vector search finds similar entities and relations in Milvus 3. Subgraph expansion collects neighboring relations 4. **Single-pass LLM reranking** selects the most relevant passages 5. Generate answer from selected passages > πŸ“– Detailed pipeline walkthrough with diagrams β†’ [How It Works](https://zilliztech.github.io/vector-graph-rag/how-it-works/) Β· [Design Philosophy](https://zilliztech.github.io/vector-graph-rag/design-philosophy/) ## πŸ“Š Evaluation Results Evaluated on three multi-hop QA benchmarks (Recall@5):

Recall@5: Naive RAG vs Vector Graph RAG

| Method | MuSiQue | HotpotQA | 2WikiMultiHopQA | Average | |--------|---------|----------|-----------------|---------| | Naive RAG | 55.6% | 90.8% | 73.7% | 73.4% | | IRCoT + HippoRAGΒΉ | 57.6% | 83.0% | 93.9% | 78.2% | | HippoRAG 2Β² | **74.7%** | **96.3%** | 90.4% | 87.1% | | **Vector Graph RAG** | 73.0% | **96.3%** | **94.1%** | **87.8%** | ΒΉ [HippoRAG (NeurIPS 2024)](https://arxiv.org/abs/2405.14831) Β² [HippoRAG 2 (2025)](https://arxiv.org/abs/2502.14802) > πŸ“– Detailed analysis and reproduction steps β†’ [Evaluation](https://zilliztech.github.io/vector-graph-rag/evaluation/) ## πŸ—„οΈ Milvus Backend Just change `milvus_uri` to switch between deployment modes: **Milvus Lite** (default) β€” zero config, single-process, data stored in a local file. Great for prototyping and small datasets: ```python rag = VectorGraphRAG(milvus_uri="./my_graph.db") # just works ``` ⭐ **Zilliz Cloud** β€” fully managed, [free tier available](https://cloud.zilliz.com/signup?utm_source=github&utm_medium=referral&utm_campaign=vector-graph-rag-readme) β€” [sign up](https://cloud.zilliz.com/signup?utm_source=github&utm_medium=referral&utm_campaign=vector-graph-rag-readme) πŸ‘‡: ```python rag = VectorGraphRAG( milvus_uri="https://in03-xxx.api.gcp-us-west1.zillizcloud.com", milvus_token="your-api-key", ) ```
⭐ Sign up for a free Zilliz Cloud cluster You can [sign up](https://cloud.zilliz.com/signup?utm_source=github&utm_medium=referral&utm_campaign=vector-graph-rag-readme) on Zilliz Cloud to get a free cluster and API key. ![Sign up and get API key](https://raw.githubusercontent.com/zilliztech/CodeIndexer/master/assets/signup_and_get_apikey.png)
Self-hosted Milvus Server (Docker) β€” for advanced users If you need a dedicated Milvus instance for multi-user or team environments, you can deploy Milvus standalone with Docker Compose. This requires Docker and some infrastructure knowledge. See the [official installation guide](https://milvus.io/docs/install_standalone-docker-compose.md) for detailed steps. ```python rag = VectorGraphRAG(milvus_uri="http://localhost:19530") ```
## πŸ–₯️ Frontend & REST API Vector Graph RAG includes a React-based frontend for interactive graph visualization and a FastAPI backend. ```bash # Backend uv sync --extra api uv run uvicorn vector_graph_rag.api.app:app --host 0.0.0.0 --port 8000 # Frontend cd frontend && npm install && npm run dev ```

Frontend β€” interactive graph visualization with 4-step retrieval

| Endpoint | Method | Description | |----------|--------|-------------| | `/api/health` | GET | Health check | | `/api/graphs` | GET | List available graphs | | `/api/graph/{name}/stats` | GET | Get graph statistics | | `/api/query` | POST | Query the knowledge graph | | `/api/documents` | POST | Add documents | | `/api/import` | POST | Import from URLs/paths | | `/api/upload` | POST | Upload files | See API docs at `http://localhost:8000/docs` after starting the server. > πŸ“– Full endpoint reference β†’ [REST API docs](https://zilliztech.github.io/vector-graph-rag/rest-api/) Β· [Frontend guide](https://zilliztech.github.io/vector-graph-rag/frontend/) ## πŸ“š Links - [Documentation](https://zilliztech.github.io/vector-graph-rag/) β€” full guides, API reference, and architecture details - [How It Works](https://zilliztech.github.io/vector-graph-rag/how-it-works/) β€” pipeline walkthrough with diagrams - [Design Philosophy](https://zilliztech.github.io/vector-graph-rag/design-philosophy/) β€” why pure vector search, no graph DB - [Milvus](https://milvus.io/) β€” the vector database powering Vector Graph RAG - [FAQ](https://zilliztech.github.io/vector-graph-rag/faq/) β€” common questions and troubleshooting ## Contributing Bug reports, feature requests, and pull requests are welcome! For questions and discussions, join us on [Discord](https://discord.com/invite/FG6hMJStWu). ## πŸ“„ License [MIT](LICENSE)