Blazing-fast app review clustering: 100k reviews in <20s on GPU
Project description
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
pip install roast-fast # CPU
pip install "roast-fast[gpu]" # GPU (CUDA)
Usage
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 |
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file roast_fast-0.1.0-py3-none-any.whl.
File metadata
- Download URL: roast_fast-0.1.0-py3-none-any.whl
- Upload date:
- Size: 15.7 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
de43b9aa02a5d68f83f1e4a8c0c6699e4d9cafe69964107bc643f00edef3e33b
|
|
| MD5 |
e00f9314eed70c5925543c89b7696dc8
|
|
| BLAKE2b-256 |
319decfdd27fd19615b962a2a60372c9a93b5cac01f6bf9a76c192ede82bea2c
|
