Upload 2 files

app.py

@@ -0,0 +1,184 @@
+import os
+import gradio as gr
+from openai import OpenAI
+
+API_KEY = os.environ['API_KEY']
+# Initialize client
+client = OpenAI(
+    base_url="https://openrouter.ai/api/v1",
+    api_key=API_KEY
+)
+
+def classify_text(text, classification_type="sentiment", custom_labels=""):
+    """
+    Classify text using OpenRouter's GPT-OSS-20B model
+    """
+    if not text.strip():
+        return "Please enter some text to classify."
+    
+    # Define classification prompts based on type
+    if classification_type == "Sentiment":
+        prompt = f"Classify the sentiment of the following text as Positive, Negative, or Neutral. Only respond with one word: Positive, Negative, or Neutral.\n\nText: {text}"
+    # elif classification_type == "topic":
+    #     prompt = f"Classify the main topic/category of the following text. Choose the most appropriate category and respond with just the category name.\n\nText: {text}"
+    elif classification_type == "Spam":
+        prompt = f"Classify whether the following text is Spam or Not Spam. Only respond with: Spam or Not Spam.\n\nText: {text}"
+    # elif classification_type == "custom":
+    #     if not custom_labels.strip():
+    #         return "Please provide custom labels for classification."
+    #     prompt = f"Classify the following text into one of these categories: {custom_labels}. Only respond with one of the provided categories.\n\nText: {text}"
+    # else:
+    #     prompt = f"Classify the following text and provide a brief classification result.\n\nText: {text}"
+    
+    try:
+        response = client.chat.completions.create(
+            model="openai/gpt-oss-20b",
+            messages=[
+                {"role": "system", "content": "You are a text classification assistant. Provide concise, accurate classifications."},
+                {"role": "user", "content": prompt}
+            ],
+            max_tokens=50,
+            temperature=0.1,
+            extra_headers={
+                "Authorization": f"Bearer {API_KEY}",
+                "HTTP-Referer": "https://your-app-url.com",
+                "X-Title": ""
+            }
+        )
+        
+        classification_result = response.choices[0].message.content.strip()
+        return f"Classification Result: {classification_result}"
+        
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+def batch_classify(file, classification_type="sentiment", custom_labels=""):
+    """
+    Classify multiple texts from uploaded file
+    """
+    if file is None:
+        return "Please upload a text file."
+    
+    try:
+        # Read file content
+        with open(file.name, 'r', encoding='utf-8') as f:
+            lines = f.readlines()
+        
+        results = []
+        for i, line in enumerate(lines[:10], 1):  # Limit to first 10 lines
+            line = line.strip()
+            if line:
+                result = classify_text(line, classification_type, custom_labels)
+                results.append(f"{i}. **Text:** {line}\n   **Result:** {result}\n")
+        
+        return "\n".join(results) if results else "No text found in file."
+        
+    except Exception as e:
+        return f"Error processing file: {str(e)}"
+
+# Create Gradio interface
+with gr.Blocks(
+    title="",
+    #theme=gr.themes.Soft()
+    theme=gr.themes.Default(primary_hue="sky")
+
+) as demo:
+    with gr.Tabs():
+        # Single Text Classification Tab
+        with gr.Tab("Single Text"):
+            with gr.Row():
+                with gr.Column(scale=2):
+                    text_input = gr.Textbox(
+                        label="",
+                        placeholder="Enter text to classify...",
+                        lines=4
+                    )
+                    
+                    classification_type = gr.Radio(
+                        choices=["Sentiment", "Spam"],
+                        value="Sentiment",
+                        label="Classification Type:"
+                    )
+                    
+                    custom_labels = gr.Textbox(
+                        label="Custom Labels (for custom classification)",
+                        placeholder="e.g., business, technology, sports, entertainment",
+                        visible=False
+                    )
+                    
+                    classify_btn = gr.Button("Classify Text", variant="primary")
+                
+                with gr.Column(scale=2):
+                    single_output = gr.Markdown(
+                        value=""
+                    )
+            
+            # Show/hide custom labels based on selection
+            def toggle_custom_labels(choice):
+                return gr.update(visible=(choice == "custom"))
+            
+            classification_type.change(
+                toggle_custom_labels,
+                inputs=[classification_type],
+                outputs=[custom_labels]
+            )
+            
+            classify_btn.click(
+                classify_text,
+                inputs=[text_input, classification_type, custom_labels],
+                outputs=[single_output]
+            )
+        
+        # Batch Classification Tab
+        with gr.Tab("Batch Classification"):
+            with gr.Row():
+                with gr.Column(scale=2):
+                    gr.Markdown("Upload a text or csv file:")
+                    
+                    file_input = gr.File(
+                        label="Upload File",
+                        file_types=[".txt", ".csv"]
+                    )
+                    
+                    batch_classification_type = gr.Radio(
+                        choices=["Sentiment", "Spam"],
+                        value="Sentiment",
+                        label="Classification Type:"
+                    )
+                    
+                    batch_custom_labels = gr.Textbox(
+                        label="Custom Labels (for custom classification)",
+                        placeholder="e.g., business, technology, sports, entertainment",
+                        visible=False
+                    )
+                    
+                    batch_classify_btn = gr.Button("🔍 Classify Batch", variant="primary")
+                
+                with gr.Column(scale=2):
+                    batch_output = gr.Markdown(
+                        value=""
+                    )
+            
+            def toggle_batch_custom_labels(choice):
+                return gr.update(visible=(choice == "custom"))
+            
+            batch_classification_type.change(
+                toggle_batch_custom_labels,
+                inputs=[batch_classification_type],
+                outputs=[batch_custom_labels]
+            )
+            
+            batch_classify_btn.click(
+                batch_classify,
+                inputs=[file_input, batch_classification_type, batch_custom_labels],
+                outputs=[batch_output]
+            )
+
+# Launch the app
+if __name__ == "__main__":
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=True,
+        show_error=True
+    )

requirements.txt

@@ -0,0 +1 @@
+openai