Update app.py

Add feature to switch between running locally and running in the cloud (cloud is sometimes faster)

app.py

@@ -1,21 +1,42 @@
+import os
 import gradio as gr
 from transformers import pipeline
+from huggingface_hub.inference_api import InferenceApi
 
-# Initialize the image-to-text pipeline
-extractor = pipeline("image-to-text", model="microsoft/git-base-textcaps")
+# Get the token from environment variable
+hf_token = os.environ.get("HF_TOKEN")
+if not hf_token:
+    raise ValueError("HF_TOKEN environment variable is not set. Please set it with your Hugging Face API token.")
 
-def extract_text(image):
-    result = extractor(image)
+# Initialize both local pipeline and Inference API
+local_extractor = pipeline("image-to-text", model="microsoft/git-base-textcaps")
+api_extractor = InferenceApi("microsoft/git-base-textcaps", token=hf_token)
+
+# Flag to track which mode is active
+use_api = False
+
+def switch_mode():
+    global use_api
+    use_api = not use_api
+    return "Using API" if use_api else "Using Local Model"
+
+def extract_text(image, mode_indicator):
+    if "API" in mode_indicator:
+        result = api_extractor(inputs=image)
+    else:
+        result = local_extractor(image)
     return result[0]['generated_text']
 
 # Create the Gradio interface
-iface = gr.Interface(
-    fn=extract_text,
-    inputs=gr.Image(type="pil"),
-    outputs="text",
-    title="Image Text Extractor",
-    description="Upload an image to extract text using Hugging Face's image-to-text model."
-)
+with gr.Blocks() as iface:
+    gr.Markdown("# Image Text Extractor")
+    with gr.Row():
+        image_input = gr.Image(type="pil")
+        text_output = gr.Textbox()
+    mode_button = gr.Button("Switch to API")
+    mode_indicator = gr.Textbox(value="Using Local Model", label="Current Mode")
+    
+    mode_button.click(switch_mode, outputs=mode_indicator)
+    image_input.change(extract_text, inputs=[image_input, mode_indicator], outputs=text_output)
 
-# Launch the app
 iface.launch()