Update app.py

app.py

@@ -1,156 +1,23 @@
 import gradio as gr
 from transformers import pipeline
-from datetime import datetime
-import json
-import numpy as np
 
-# Initialize models (with error handling)
-try:
-    sentiment_analyzer = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
-    text_generator = pipeline("text-generation", model="gpt2")
-except Exception as e:
-    print(f"Model loading error: {e}")
-    raise
-
-# Custom CSS for better UI
-custom_css = """
-footer {visibility: hidden}
-.important-text {
-    font-size: 14px;
-    color: #666;
-    font-style: italic;
-}
-"""
+# Load sentiment-analysis pipeline
+classifier = pipeline("sentiment-analysis")
 
 def analyze_sentiment(text):
-    start_time = datetime.now()
-    try:
-        result = sentiment_analyzer(text)[0]
-        return {
-            "analysis": {
-                "sentiment": result["label"],
-                "confidence": float(result["score"]),
-                "processing_time": str(datetime.now() - start_time)
-            },
-            "original_text": text
-        }
-    except Exception as e:
-        return {"error": str(e)}
-
-def generate_text(prompt, length=50, temperature=0.7):
-    start_time = datetime.now()
-    try:
-        generated = text_generator(
-            prompt,
-            max_length=length,
-            num_return_sequences=1,
-            temperature=temperature
-        )
-        return {
-            "generated_text": generated[0]["generated_text"],
-            "metadata": {
-                "model": "GPT-2",
-                "length": length,
-                "temperature": temperature,
-                "processing_time": str(datetime.now() - start_time)
-            }
-        }
-    except Exception as e:
-        return {"error": str(e)}
+    result = classifier(text)[0]
+    label = result['label']
+    score = result['score']
+    return f"Sentiment: {label} ({score:.2f})"
 
-with gr.Blocks(
-    title="NLP Production API",
-    theme=gr.themes.Soft(),
-    css=custom_css
-) as demo:
-    gr.Markdown("""
-    # 🏭 NLP Production Endpoint
-    **Enterprise-ready NLP services** with monitoring capabilities
-    """)
-    
-    with gr.Tab("Sentiment Analysis"):
-        with gr.Row():
-            with gr.Column(scale=2):
-                sentiment_input = gr.Textbox(
-                    label="Input Text",
-                    placeholder="Enter text to analyze...",
-                    lines=3
-                )
-                with gr.Accordion("Advanced Options", open=False):
-                    gr.Markdown("No additional options for sentiment analysis", elem_classes="important-text")
-                sentiment_button = gr.Button("Analyze", variant="primary")
-                
-            with gr.Column(scale=3):
-                sentiment_output = gr.JSON(
-                    label="Analysis Results",
-                    container=True
-                )
-        
-        gr.Examples(
-            examples=[
-                "This product revolutionized our workflow!",
-                "The service was unsatisfactory and slow.",
-                "It meets basic requirements but lacks innovation."
-            ],
-            inputs=sentiment_input,
-            label="Try these examples"
-        )
+with gr.Blocks() as demo:
+    gr.Markdown("# 🧠 Sentiment Analyzer")
+    gr.Markdown("Enter text and get the sentiment prediction!")
 
-    with gr.Tab("Text Generation"):
-        with gr.Row():
-            with gr.Column(scale=2):
-                gen_input = gr.Textbox(
-                    label="Prompt",
-                    placeholder="Start your creative writing here...",
-                    lines=3
-                )
-                with gr.Accordion("Generation Parameters", open=False):
-                    gen_length = gr.Slider(20, 200, value=50, label="Output Length")
-                    gen_temp = gr.Slider(0.1, 1.0, value=0.7, step=0.1, label="Creativity (Temperature)")
-                gen_button = gr.Button("Generate Text", variant="primary")
-                
-            with gr.Column(scale=3):
-                gen_output = gr.JSON(
-                    label="Generated Output",
-                    container=True
-                )
-    
-    # Monitoring section (hidden by default)
-    with gr.Accordion("API Monitoring", open=False):
-        gr.Markdown("""
-        ### Performance Metrics
-        - Last request time: `2025-04-29 15:36:26`
-        - Average processing time: `0.45s`
-        - System health: ✅ Operational
-        """)
-    
-    # Footer
-    gr.Markdown("---")
-    gr.HTML("""
-    <div style="text-align: center">
-        <p>Powered by Hugging Face Transformers | Gradio {version} | Python 3.10</p>
-        <p>Build SHA: 6615a41 | Queued at 2025-04-29 15:36:26</p>
-    </div>
-    """.format(version=gr.__version__))
+    text_input = gr.Textbox(label="Enter your text")
+    analyze_button = gr.Button("Analyze Sentiment")
+    output = gr.Textbox(label="Result")
 
-    # Event handlers
-    sentiment_button.click(
-        fn=analyze_sentiment,
-        inputs=sentiment_input,
-        outputs=sentiment_output,
-        api_name="analyze_sentiment"
-    )
-    
-    gen_button.click(
-        fn=generate_text,
-        inputs=[gen_input, gen_length, gen_temp],
-        outputs=gen_output,
-        api_name="generate_text"
-    )
+    analyze_button.click(fn=analyze_sentiment, inputs=text_input, outputs=output)
 
-if __name__ == "__main__":
-    demo.launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        show_api=True
-    )
+demo.launch()