add files

Dockerfile

@@ -0,0 +1,26 @@
+FROM ubuntu:jammy
+#FROM alpine:latest
+
+# Install dependencies
+RUN apt-get update && apt-get install -y \
+    tesseract-ocr \
+    tesseract-ocr-eng \
+    tesseract-ocr-tha \
+    python3 \            
+    python3-pip 
+
+# Install FastAPI and Uvicorn (an ASGI server)
+RUN pip3 install fastapi uvicorn pillow pytesseract python-multipart PyMuPDF
+
+# Set working directory
+WORKDIR /app
+
+# Copy your application code
+COPY . .
+
+
+# Expose port for the service
+EXPOSE 5000
+
+# Start your application with Uvicorn
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"] 

app.py

@@ -0,0 +1,39 @@
+from fastapi import FastAPI, File, UploadFile
+from PIL import Image
+import pytesseract
+import io
+import fitz
+
+app = FastAPI()
+
+@app.get("/test")
+async def test_api():
+    return {"message": "API is working ..."} 
+
+@app.post("/ocr_image")
+async def perform_ocr_image(image: UploadFile = File(...)):
+    image_data = await image.read()
+
+    image = Image.open(io.BytesIO(image_data))
+    text = pytesseract.image_to_string(image, lang='tha+eng')
+    return {"text": text}
+
+
+@app.post("/ocr_pdf")
+async def perform_ocr_pdf(image: UploadFile = File(...)):
+    image_data = await image.read()
+
+    doc = fitz.open(stream=image_data, filetype="pdf")
+
+    page = doc[0]  # Access the desired page (zero-indexed)
+
+    # Generate a high-quality image of the page
+    zoom = 2  # Adjust for better OCR resolution if needed
+    mat = fitz.Matrix(zoom, zoom)  # Zoom matrix
+    pix = page.get_pixmap(matrix=mat)
+    img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+
+    # Analyze text orientation with Pytesseract
+    #text_orientation = pytesseract.image_to_osd(img)  
+    text = pytesseract.image_to_string(img, lang='tha+eng')
+    return {"text": text}