Spaces:
Sleeping
Sleeping
File size: 6,007 Bytes
3a8a968 ddfc072 3a8a968 ddfc072 3a8a968 ecf4549 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 ecf4549 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 02424b5 ff04da1 65a107c ff04da1 02424b5 ff04da1 02424b5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 |
---
title: RAGnosis
emoji: π§
colorFrom: red
colorTo: indigo
sdk: gradio
sdk_version: 5.36.2
app_file: app.py
pinned: false
license: mit
short_description: Clinical Query Answering with RAG + MIMIC-IV Notes.
---
# π§ RAGnosis β Clinical Reasoning via Retrieval-Augmented Generation
[](LICENSE)
[](https://www.python.org/)
[](https://huggingface.co/spaces/asadsandhu/RAGnosis)
[](https://github.com/asadsandhu/RAG-Diagnostic-Assistant)
> βοΈ A CPU-friendly RAG assistant for explainable clinical diagnosis, built using annotated notes from the [MIMIC-IV-Ext-DiReCT](https://github.com/asadsandhu/RAG-Diagnostic-Assistant/blob/main/mimic-iv-ext-direct-1.0.0.zip) dataset.
---
## πΌοΈ Live Demo
Try it on **Hugging Face Spaces** (CPU-based, ~500s latency) π :
π https://huggingface.co/spaces/asadsandhu/RAGnosis
<p align="center">
<img src="assets/demo.png" alt="Demo" width="750">
</p>
---
## βοΈ Technical Stack
| Component | Details |
|----------------|-------------------------------------------------------------------------|
| π§ Model | [`BioMistral/BioMistral-7B`](https://huggingface.co/BioMistral/BioMistral-7B) |
| π₯ Dataset | [`MIMIC-IV-Ext-DiReCT`](https://github.com/asadsandhu/RAG-Diagnostic-Assistant/blob/main/mimic-iv-ext-direct-1.0.0.zip) |
| π Retrieval | FAISS + SentenceTransformers (`all-MiniLM-L6-v2`) |
| π¬ Interface | Gradio (Runs on Hugging Face Spaces) |
| βοΈ Backend | PyTorch + Transformers (CPU inference) |
---
## π©Ί Key Features
- π Top-k clinical note retrieval from structured diagnostic chains
- π§ Diagnosis generation using `BioMistral-7B` without GPU
- ποΈ MIMIC-IV-Ext-DiReCT backed medical reasoning
- π¬ Natural query input and interpretable LLM output
- β
Optimized for Hugging Face's free CPU tier (16GB RAM)
---
## π§ͺ Example Prompt
> *patient is experiencing shortness of breath*
π¬ **Model response:**
> Shortness of breath is a common symptom that can be caused by a variety of respiratory conditions. The differential diagnosis for shortness of breath includes asthma, chronic obstructive pulmonary disease (COPD), congestive heart failure, pneumonia, and pneumothorax. In order to determine the cause of the shortness of breath, it is important to consider the patient's medical history, physical examination findings, and diagnostic testing results. For example, if the patient has a history of asthma and is experiencing wheezing and a prolonged expiratory phase on examination, this would suggest asthma as the cause of the shortness of breath. On the other hand, if the patient has a history of congestive heart failure and is experiencing orthopnea, crackles on auscultation, and a history of edema, this would suggest congestive heart failure as the cause of the shortness of breath.
---
## π§ Under the Hood
### π§ Step 1: Retrieval
- Sentence embeddings (`MiniLM-L6-v2`)
- FAISS indexing β [`faiss_index.bin`](https://github.com/asadsandhu/RAG-Diagnostic-Assistant/blob/main/faiss_index.bin)
- Source: [`retrieval_corpus.csv`](https://github.com/asadsandhu/RAG-Diagnostic-Assistant/blob/main/retrieval_corpus.csv)
### π§± Step 2: Prompt Construction
- Clinical query + retrieved chunks form an instruction prompt
### 𧬠Step 3: Generation
- Uses `BioMistral/BioMistral-7B`
- Generated on CPU (expect ~500 seconds)
---
## β οΈ Note on Performance
| Feature | Hugging Face (CPU) | Colab / Local (GPU) |
|--------------|----------------------------|--------------------------------------|
| Model Used | `BioMistral-7B` | `Nous-Hermes-2-Mistral-7B-DPO` |
| Speed | ~500 seconds/query π’ | ~10 seconds/query β‘ |
| Accuracy | β
Good | β
Great |
| Requirements | 1 CPU (free tier) | CUDA GPU (Colab/Kaggle/local) |
> Want faster responses? Use the [GPU version on GitHub](https://github.com/asadsandhu/RAG-Diagnostic-Assistant) with `app.py`.
---
## βοΈ Run It Locally (GPU Recommended)
```bash
# 1. Clone the repository
git clone https://github.com/asadsandhu/RAG-Diagnostic-Assistant.git
cd RAG-Diagnostic-Assistant
# 2. Install dependencies
pip install -r requirements.txt
# 3. Run the app (auto-detects GPU)
python app.py
````
Required files (already in repo):
* β
[`retrieval_corpus.csv`](https://github.com/asadsandhu/RAG-Diagnostic-Assistant/blob/main/retrieval_corpus.csv)
* β
[`faiss_index.bin`](https://github.com/asadsandhu/RAG-Diagnostic-Assistant/blob/main/faiss_index.bin)
---
## π Project Structure
```
RAG-Diagnostic-Assistant/
βββ app.py
βββ faiss_index.bin
βββ retrieval_corpus.csv
βββ requirements.txt
βββ assets/
β βββ demo.png
βββ README.md
```
---
## π€ Author
Built with β€οΈ by [Asad Ali](https://www.linkedin.com/in/asadsandhu0/)
* π§ Medium: [@asadsandhu](https://medium.com/@asadsandhu)
* π» GitHub: [@asadsandhu](https://github.com/asadsandhu)
* π€ Hugging Face: [@asadsandhu](https://huggingface.co/asadsandhu)
---
## π License
MIT License β see [LICENSE](https://opensource.org/license/mit)
---
## π Acknowledgments
* MIMIC-IV-Ext-DiReCT β Annotated diagnostic dataset
* Hugging Face Transformers + Gradio
* SentenceTransformers + FAISS
* BioMistral + NousResearch
---
> β οΈ **Disclaimer**: This is a research prototype and not intended for clinical decision-making. |