# honeyandme/RAGQnASystem

<https://repo.masters-masters.com/en/repos/honeyandme/RAGQnASystem>

[Home](https://repo.masters-masters.com/en) › [honeyandme](https://repo.masters-masters.com/en/owners/honeyandme) › [RAGQnASystem](https://repo.masters-masters.com/en/repos/honeyandme/RAGQnASystem)

honeyandme/RAGQnASystem has 1,499 stars on GitHub. Its RepoMasters card: Beta tier. 本项目设计并实现了一个基于知识图谱 RAG 与大语言模型的医疗智能问答系统。系统以 DiseaseKG 医疗数据集为基础，依托 Neo4j 构建包含…

| Field | Value |
| --- | --- |
| Owner | [honeyandme](https://repo.masters-masters.com/en/owners/honeyandme) |
| Stars | 1,499 |
| Forks | 150 |
| Language | [Jupyter Notebook](https://repo.masters-masters.com/en/languages/jupyter-notebook) |
| License | None |
| Created | 2024 |
| Tier | [Beta (700 to 1,999 ★)](https://repo.masters-masters.com/en/ranks/box_office) |
| View on GitHub | [honeyandme/RAGQnASystem](https://github.com/honeyandme/RAGQnASystem) |

## Repository

本项目设计并实现了一个基于知识图谱 RAG 与大语言模型的医疗智能问答系统。系统以 DiseaseKG 医疗数据集为基础，依托 Neo4j 构建包含 4.4 万实体与 31 万关系的领域知识图谱；结合 BERT 命名实体识别与 32B 大模型意图识别，通过精确的图谱检索与受控的答案生成，有效缓解大模型在医疗场景中的幻觉问题，显著提升回答的准确性与可靠性。

The tier for repos with 700 to 1,999 ★. Published odds per card pulled: 6%. Rarity: Rare.

## Nearby in Jupyter Notebook

- [dvgodoy/PyTorchStepByStep · ★ 1,504 · Jupyter Notebook · Beta](https://repo.masters-masters.com/en/repos/dvgodoy/PyTorchStepByStep)
- [modelscope/modelscope-classroom · ★ 1,504 · Jupyter Notebook · Beta](https://repo.masters-masters.com/en/repos/modelscope/modelscope-classroom)
- [alicezheng/feature-engineering-book · ★ 1,499 · Jupyter Notebook · Beta](https://repo.masters-masters.com/en/repos/alicezheng/feature-engineering-book)
- [h2oai/h2o-tutorials · ★ 1,497 · Jupyter Notebook · Beta](https://repo.masters-masters.com/en/repos/h2oai/h2o-tutorials)
- [gengyanlei/fire-smoke-detect-yolov4 · ★ 1,497 · Jupyter Notebook · Beta](https://repo.masters-masters.com/en/repos/gengyanlei/fire-smoke-detect-yolov4)
- [google-deepmind/educational · ★ 1,497 · Jupyter Notebook · Beta](https://repo.masters-masters.com/en/repos/google-deepmind/educational)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.