Upload 3 files

Dockerfile

@@ -0,0 +1,20 @@
+# Use the official Python image
+FROM python:3.9.7
+
+# Set the working directory in the container
+WORKDIR /code
+
+# Copy the requirements file into the container
+COPY ./requirements.txt /code/requirements.txt
+
+# Install the dependencies
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Install Tesseract OCR via the package manager
+RUN apt-get update && apt-get install -y tesseract-ocr
+
+# Copy the entire project directory into the container
+COPY . /code
+
+# Command to run the FastAPI server
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,46 @@
+from PIL import Image
+import pytesseract
+from fastapi import FastAPI, UploadFile, File
+from fastapi.middleware.cors import CORSMiddleware
+from io import BytesIO
+
+
+app = FastAPI()
+
+
+origins = ["*"]
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.get('/')
+def welcome():
+    return {
+        'success': True,
+        'message': 'server of "image text extractor" is up and running successfully.'
+    }
+
+@app.post('/extract-text-from-image')
+async def extract_text_from_img(imageUploadedByUser: UploadFile = File(...)):
+    
+    img = await imageUploadedByUser.read()  
+
+    img_bytes_io = Image.open(BytesIO(img))
+
+    gray_scale_img = img_bytes_io.convert('L')
+
+    text = pytesseract.image_to_string(gray_scale_img)
+
+    text_cleaned = ' '.join(text.split())
+
+    return {
+        'success': True,
+        'message': 'Text has been successfully extracted from the uploaded image',
+        'extracted_text': text_cleaned
+    }

requirements.txt

@@ -0,0 +1,5 @@
+fastapi==0.109.2
+uvicorn==0.27.1
+python-multipart==0.0.9
+Pillow==10.2.0
+pytesseract==0.3.10