Add file

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,28 @@
+from fastapi import Depends, FastAPI, Header, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from routers import tokenize
+import pythainlp
+
+
+DESC_TEXT = "PyThaiNLP API"
+
+app = FastAPI(
+    title='PyThaiNLP API',
+    description=DESC_TEXT,
+    version='0.1',
+)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.get("/")
+def index():
+    return {"Pythainlp Version": pythainlp.__version__}
+
+app.include_router(tokenize.router, prefix="/tokenize", tags=["Tokenize"])

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn[standard]
+pythainlp==5.0.5
+python-crfsuite

routers/tokenize.py

@@ -0,0 +1,41 @@
+# -*- coding: utf-8 -*-
+from fastapi import APIRouter
+from pythainlp.tokenize import word_tokenize as py_word_tokenize, subword_tokenize as py_subword_tokenize
+from enum import Enum
+from typing import List, Optional
+from pydantic import BaseModel
+
+router = APIRouter()
+
+
+class SentTokenizeEngine(str, Enum):
+    whitespace = "whitespace"
+    whitespace_newline = "whitespace+newline"
+
+
+class WordTokenizeEngine(str, Enum):
+    newmm = "newmm"
+    longest = "longest"
+    deepcut = "deepcut"
+    icu = "icu"
+    ulmfit = "ulmfit"
+
+
+class SubwordTokenizeEngine(str, Enum):
+    tcc = "tcc"
+    etcc = "etcc"
+
+class WordTokenizeResponse(BaseModel):
+    words: List[str] = []
+
+class SubwordTokenizeResponse(BaseModel):
+    subwords: List[str] = []
+
+@router.get('/word_tokenize', response_model=WordTokenizeResponse)
+def word_tokenize(text: str, engine: WordTokenizeEngine = "newmm"):
+    return {"words": py_word_tokenize(text=text, engine=engine)}
+
+
+@router.get('/subword_tokenize', response_model=SubwordTokenizeResponse)
+def subword_tokenize(text: str, engine: SubwordTokenizeEngine = "tcc"):
+    return {"subwords": py_subword_tokenize(text=text, engine=engine)}