Upload 3 files

Dockerfile

@@ -0,0 +1,18 @@
+FROM python:3.10-slim
+
+RUN apt-get update && apt-get install -y \
+    libglib2.0-0 libsm6 libxrender1 libxext6 libgl1 libgomp1 \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Download model saat build, bukan saat runtime
+RUN python -c "from paddleocr import PaddleOCR; PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False)"
+
+COPY . .
+
+EXPOSE 7860
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,27 @@
+from fastapi import FastAPI, UploadFile, File
+from paddleocr import PaddleOCR
+from PIL import Image
+import io, numpy as np
+
+app = FastAPI()
+ocr = PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False)
+
+@app.get("/")
+def health():
+    return {"status": "ok"}
+
+@app.post("/ocr")
+async def run_ocr(file: UploadFile = File(...)):
+    contents = await file.read()
+    image = Image.open(io.BytesIO(contents)).convert("RGB")
+    img_array = np.array(image)
+    result = ocr.ocr(img_array, cls=True)
+
+    texts = []
+    for line in result[0]:
+        texts.append({
+            "text": line[1][0],
+            "confidence": round(line[1][1], 4)
+        })
+
+    return {"filename": file.filename, "results": texts}

requirements.txt

@@ -0,0 +1,7 @@
+fastapi==0.111.0
+uvicorn==0.30.1
+paddlepaddle==2.6.1
+paddleocr==2.7.3
+python-multipart==0.0.9
+pillow==10.3.0
+numpy==1.26.4