Create app.py

app.py

@@ -0,0 +1,63 @@
+from dotenv import load_dotenv, find_dotenv
+import os
+import io
+from io import BytesIO
+from PIL import Image
+import base64
+import requests
+import json
+import warnings
+import gradio as gr
+
+# Suppress specific warnings
+warnings.filterwarnings("ignore", message=".*Using the model-agnostic default `max_length`.*")
+
+# Load environment variables from .env file
+load_dotenv(find_dotenv())
+hf_api_key = os.getenv('HF_API_KEY')
+endpoint_url = os.getenv('HF_API_ITT_BASE')
+
+
+def generate_caption(image):
+    """
+    Sends an image to the Hugging Face Inference Endpoint for caption generation.
+    :param image: An image in PIL format.
+    :return: Generated caption or error message.
+    """
+    headers = {"Authorization": f"Bearer {hf_api_key}"}
+    files = {"inputs": image}
+    response = requests.post(endpoint_url, headers=headers, files=files)
+
+    if response.status_code == 200:
+        return response.json().get("generated_text", "No caption generated.")
+    else:
+        return f"Error: {response.status_code} - {response.text}"
+
+# Predefined sample images
+def get_sample_images():
+    """
+    Returns a list of predefined sample images in the assets directory.
+    """
+    sample_dir = "CreatureCaptures"
+    return [
+        os.path.join(sample_dir, file)
+        for file in os.listdir(sample_dir)
+        if file.lower().endswith((".png", ".jpg", ".jpeg"))
+    ]
+
+# Gradio interface
+sample_images = get_sample_images()  # Load predefined sample images
+demo = gr.Interface(
+    fn=generate_caption,
+    inputs=gr.inputs.Image(type="file", label="Upload Image"),
+    outputs=gr.outputs.Textbox(label="Generated Caption"),
+    examples=sample_images,
+    title="Image Captioning App",
+    description=(
+        "Upload an image or use one of the predefined samples to generate a caption. "
+        "This app uses a Hugging Face Inference Endpoint for the `Salesforce/blip-image-captioning-base` model."
+    ),
+)
+
+if __name__ == "__main__":
+    demo.launch()