Encoders
A library of neural encoders to convert any types of data into embeddings, dense or sparse.
Build a package
python setup.py bdist_wheel
twine upload dist/*
Use Locally
model = EncoderLoader.load_model('pretrain-models', <model_id>, use_gpu=True, region='cn')
model.encode(['I am a good man'], show_progress_bar=True, batch_size=batch_size,)
Use as RESTful API
Start a server
uvicorn soco_encoders.http.main:app --host 0.0.0.0 --port 8000 --workers 4
Start a client
res = requests.post(url='http://localhost:8000/encoder/v1/encode',
json={
"model_id": model_id,
"text": [x1] * batch_size,
'batch_size': batch_size,
"mode": "default",
"kwargs": {}
})
Use as GRPC API
Start a server
python -m soco_encoders.grpc.server --host 0.0.0.0 --port 8000 --workers 4
Start a client
check out example in bench_grpc.py
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
soco-encoders-0.2.9.2.tar.gz
(33.3 kB
view details)
File details
Details for the file soco-encoders-0.2.9.2.tar.gz.
File metadata
- Download URL: soco-encoders-0.2.9.2.tar.gz
- Upload date:
- Size: 33.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/3.3.0 pkginfo/1.6.1 requests/2.25.1 setuptools/51.1.2 requests-toolbelt/0.9.1 tqdm/4.55.1 CPython/3.8.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
29097f0d2f740116026f420da2270d4b2a9ce3835ac1a3ada56fa95d3f054e76
|
|
| MD5 |
0aed0504ad8ad32e098db0504567120d
|
|
| BLAKE2b-256 |
d19cc90fba422d9b7a6ed881ec70eea113aa96b2a7179fea3d3ca80e531039d0
|
