Gradio と Hugging Face を使用して、線の下に Python コードを使用してテキスト抽出アプリを構築する

# Use an official Python runtime as a parent image
FROM python:3.12
ENV PIP_ROOT_USER_ACTION=ignore

# Set the working directory in the container
WORKDIR $HOME/app

# Install system dependencies
RUN apt-get update && apt-get install -y
RUN apt-get install -y tesseract-ocr
RUN apt-get install -y libtesseract-dev
RUN apt-get install -y libgl1-mesa-glx
RUN apt-get install -y libglib2.0-0
RUN pip install --upgrade pip

# Copy requirements and install dependencies
COPY requirements.txt requirements.txt
RUN pip install --no-cache-dir -r requirements.txt

# Copy the app code
COPY app.py ./

# Expose the port for Gradio
EXPOSE 7860

# Run the application
CMD ["python", "app.py"]

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)}"

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."
)

iface.launch(server_name="0.0.0.0", server_port=7860)

gradio
pytesseract
Pillow