chunked/nltk_chunking/_pipeline_webserver/chunk_10.txt

Create server.py:

from starlette.applications import Starlette
from starlette.responses import JSONResponse
from starlette.routing import Route
from transformers import pipeline
import asyncio
async def homepage(request):
    payload = await request.body()
    string = payload.decode("utf-8")
    response_q = asyncio.Queue()
    await request.app.model_queue.put((string, response_q))
    output = await response_q.get()
    return JSONResponse(output)
async def server_loop(q):
    pipe = pipeline(model="google-bert/bert-base-uncased")
    while True:
        (string, response_q) = await q.get()
        out = pipe(string)
        await response_q.put(out)
app = Starlette(
    routes=[
        Route("/", homepage, methods=["POST"]),
    ],
)
@app.on_event("startup")
async def startup_event():
    q = asyncio.Queue()
    app.model_queue = q
    asyncio.create_task(server_loop(q))

Now you can start it with:

uvicorn server:app
And you can query it:
```bash
curl -X POST -d "test [MASK]" http://localhost:8000/
[{"score":0.7742936015129089,"token":1012,"token_str":".","sequence":"test.