Metadata-Version: 2.4
Name: roast-fast
Version: 0.1.0
Summary: Blazing-fast app review clustering: 100k reviews in <20s on GPU
Author-email: Kushal <kushal@example.com>
License: MIT
Keywords: clustering,embeddings,faiss,nlp,onnx,reviews
Requires-Python: >=3.9
Requires-Dist: faiss-cpu>=1.7
Requires-Dist: numpy<2.0,>=1.24
Requires-Dist: onnxruntime>=1.16
Requires-Dist: pandas>=1.5
Requires-Dist: transformers>=4.30
Provides-Extra: gpu
Requires-Dist: onnxruntime-gpu>=1.16; extra == 'gpu'
Description-Content-Type: text/markdown

# roast-fast

**Blazing-fast app review clustering. 1 lakh reviews in under 20 seconds.**

Built on ONNX + FAISS. Auto-detects GPU. Falls back to CPU.

## Install

```bash
pip install roast-fast          # CPU
pip install "roast-fast[gpu]"   # GPU (CUDA)
```

## Usage

```python
from roast_fast import process_reviews

result = process_reviews("reviews.csv")

print(result["stats"])
# {total_reviews: 100000, total_time_s: 17.9, throughput_rps: 5580, ...}

for cluster in result["clusters"][:5]:
    print(cluster["size"], cluster["sample_reviews"][0])
```

## Benchmark (A100-SXM4 MIG)

| Reviews | Time   | Throughput    |
|---------|--------|---------------|
| 1,000   | 0.8s   | 1,250 rev/s   |
| 10,000  | 2.1s   | 4,762 rev/s   |
| 100,000 | 17.9s  | 5,580 rev/s   |

