Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

stop encoder being read into memory on each call to /vectorize #113

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

stop encoder being read into memory on each call to /vectorize #113

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
100 changes: 53 additions & 47 deletions docker/app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,70 +9,76 @@
from LASER.source.lib.text_processing import Token, BPEfastApply
from LASER.source.embed import *

app = Flask(__name__)
app.config['JSON_AS_ASCII'] = False


@app.route("/")
def root():
print("/")
html = "<h3>Hello {name}!</h3>" \
"<b>Hostname:</b> {hostname}<br/>"
return html.format(name=os.getenv("LASER", "world"), hostname=socket.gethostname())


@app.route("/vectorize")
def vectorize():
content = request.args.get('q')
lang = request.args.get('lang')
embedding = ''
if lang is None or not lang:
lang = "en"
def create_app():
app = Flask(__name__)
app.config['JSON_AS_ASCII'] = False
# encoder
model_dir = Path(__file__).parent / "LASER" / "models"
encoder_path = model_dir / "bilstm.93langs.2018-12-26.pt"
bpe_codes_path = model_dir / "93langs.fcodes"
app.bpe_codes_path = model_dir / "93langs.fcodes"
print(f' - Encoder: loading {encoder_path}')
encoder = SentenceEncoder(encoder_path,
max_sentences=None,
max_tokens=12000,
sort_kind='mergesort',
cpu=True)
with tempfile.TemporaryDirectory() as tmp:
tmpdir = Path(tmp)
ifname = tmpdir / "content.txt"
bpe_fname = tmpdir / 'bpe'
bpe_oname = tmpdir / 'out.raw'
with ifname.open("w") as f:
f.write(content)
if lang != '--':
tok_fname = tmpdir / "tok"
Token(str(ifname),
str(tok_fname),
lang=lang,
romanize=True if lang == 'el' else False,
lower_case=True,
gzip=False,
verbose=True,
over_write=False)
ifname = tok_fname
BPEfastApply(str(ifname),
app.encoder = encoder

@app.route("/")
def root():
print("/")
html = "<h3>Hello {name}!</h3>" \
"<b>Hostname:</b> {hostname}<br/>"
return html.format(name=os.getenv("LASER", "world"), hostname=socket.gethostname())

@app.route("/vectorize")
def vectorize():
content = request.args.get('q')
lang = request.args.get('lang')
embedding = ''
if lang is None or not lang:
lang = "en"

with tempfile.TemporaryDirectory() as tmp:
tmpdir = Path(tmp)
ifname = tmpdir / "content.txt"
bpe_fname = tmpdir / 'bpe'
bpe_oname = tmpdir / 'out.raw'
with ifname.open("w") as f:
f.write(content)
if lang != '--':
tok_fname = tmpdir / "tok"
Token(str(ifname),
str(tok_fname),
lang=lang,
romanize=True if lang == 'el' else False,
lower_case=True,
gzip=False,
verbose=True,
over_write=False)
ifname = tok_fname
BPEfastApply(str(ifname),
str(bpe_fname),
str(bpe_codes_path),
str(app.bpe_codes_path),
verbose=True, over_write=False)
ifname = bpe_fname
EncodeFile(encoder,
ifname = bpe_fname
EncodeFile(app.encoder,
str(ifname),
str(bpe_oname),
verbose=True,
over_write=False,
buffer_size=10000)
dim = 1024
X = np.fromfile(str(bpe_oname), dtype=np.float32, count=-1)
X.resize(X.shape[0] // dim, dim)
embedding = X
body = {'content': content, 'embedding': embedding.tolist()}
return jsonify(body)
dim = 1024
X = np.fromfile(str(bpe_oname), dtype=np.float32, count=-1)
X.resize(X.shape[0] // dim, dim)
embedding = X
body = {'content': content, 'embedding': embedding.tolist()}
return jsonify(body)

return app


if __name__ == "__main__":
app = create_app()
app.run(debug=True, port=80, host='0.0.0.0')