initial commit 🤖🤖🤖

Dockerfile

@@ -0,0 +1,26 @@
+# Use an official Python runtime as a parent image
+FROM python:3.10-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    tesseract-ocr \
+    libtesseract-dev \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Make port 7860 available to the world outside this container
+EXPOSE 7860
+
+# Run app.py when the container launches
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,30 @@
+import gradio as gr
+import pytesseract
+from PIL import Image
+import os
+
+def extract_text(image_path):
+    if not image_path:
+        return "No image uploaded. Please upload an image."
+    
+    if not os.path.exists(image_path):
+        return f"Error: File not found at {image_path}"
+    
+    try:
+        img = Image.open(image_path)
+        text = pytesseract.image_to_string(img)
+        return text if text.strip() else "No text detected in the image."
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+# Create the Gradio interface (same as before)
+iface = gr.Interface(
+    fn=extract_text,
+    inputs=gr.Image(type="filepath", label="Upload an image"),
+    outputs=gr.Textbox(label="Extracted Text"),
+    title="Image Text Extractor",
+    description="Upload an image and extract text from it using OCR."
+)
+
+# Launch the interface
+iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+pytesseract
+Pillow