TesseractをAPIとして実行
またはセルフホストサービスとして。

pip install fastapi uvicorn python-multipart pytesseract pillow
# 先にエンジン + 言語パックをインストール（インストールガイド参照）
uvicorn app:app --host 0.0.0.0 --port 8000

import asyncio, io
from concurrent.futures import ProcessPoolExecutor
from fastapi import FastAPI, File, UploadFile, HTTPException, Query
from PIL import Image
import pytesseract

app = FastAPI(title="Tesseract OCR API")
pool = ProcessPoolExecutor(max_workers=4)
MAX_BYTES = 10 * 1024 * 1024  # 10 MB
LANGS = {"eng", "jpn"}

def _ocr(data: bytes, lang: str) -> str:
    image = Image.open(io.BytesIO(data))
    return pytesseract.image_to_string(image, lang=lang)

@app.get("/health")
def health():
    return {"status": "ok"}

@app.post("/ocr")
async def ocr(file: UploadFile = File(...), lang: str = Query("jpn")):
    if lang not in LANGS:
        raise HTTPException(400, "未対応の言語")
    data = await file.read()
    if len(data) > MAX_BYTES:
        raise HTTPException(413, "ファイルが大きすぎます")
    loop = asyncio.get_running_loop()
    try:
        text = await asyncio.wait_for(loop.run_in_executor(pool, _ocr, data, lang), timeout=30)
    except asyncio.TimeoutError:
        raise HTTPException(504, "OCRタイムアウト")
    return {"text": text, "lang": lang}

FROM python:3.12-slim
RUN apt-get update && apt-get install -y --no-install-recommends \
      tesseract-ocr tesseract-ocr-eng tesseract-ocr-jpn \
      libgl1 libglib2.0-0 && rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY app.py .
EXPOSE 8000
HEALTHCHECK CMD python -c "import urllib.request;urllib.request.urlopen('http://localhost:8000/health')"
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "2"]