Create app.py

app.py

@@ -0,0 +1,171 @@
+import gradio as gr
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import time
+from gradio_client import Client
+
+blipper="Salesforce/blip-image-captioning-large"
+chatter="K00B404/transcript_image_generator"
+
+# Load BLIP model for image captioning
+processor = BlipProcessor.from_pretrained(blipper)
+model = BlipForConditionalGeneration.from_pretrained(blipper)
+
+# Initialize the API client for the chatbot
+chatbot_client = Client(chatter)
+
+def caption_to_persona(caption):
+    """Convert a basic image caption into a character persona prompt"""
+    persona = f"""You are {caption.replace('arafed image of ','a ')}
+
+Your personality, speech patterns, knowledge, and behavior should reflect this description.
+When responding to users:
+1. Stay in character at all times
+2. Use speech patterns and vocabulary that would be natural for your character
+3. Reference experiences, emotions, and perspectives that align with your character's background
+4. Maintain a consistent personality throughout the conversation
+
+Additional context: Your responses should vary in length based on what would be natural for your character. 
+Some characters might be terse while others might be more verbose."""
+
+    return persona
+
+def generate_persona(img, min_len, max_len, persona_detail_level):
+    # Process the image
+    raw_image = Image.open(img).convert('RGB')
+    inputs = processor(raw_image, return_tensors="pt")
+    
+    # Generate caption with specified length constraints
+    start = time.time()
+    out = model.generate(**inputs, min_length=min_len, max_length=max_len)
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    
+    # Enhance the caption based on detail level
+    if persona_detail_level == "Basic":
+        enhanced_caption = caption
+    elif persona_detail_level == "Detailed":
+        enhanced_caption = f"{caption} You have a distinct personality with unique mannerisms and speech patterns."
+    else:  # Comprehensive
+        enhanced_caption = f"{caption} You have a complex backstory, rich emotional depth, unique perspectives, and distinctive speech patterns that set you apart."
+    
+    # Generate persona from caption
+    persona = caption_to_persona(enhanced_caption)
+    
+    # Calculate processing time
+    end = time.time()
+    total_time = f"Processing time: {end - start:.2f} seconds"
+    
+    return caption, persona, total_time
+
+def chat_with_persona(message, history, system_message, max_tokens, temperature, top_p):
+    """Function to interact with the chatbot API using the generated persona"""
+    try:
+        # Call the API with the current message and system prompt (persona)
+        response = chatbot_client.predict(
+            message=message,
+            system_message=system_message,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            api_name="/chat"
+        )
+        return response
+    except Exception as e:
+        return f"Error communicating with the chatbot API: {str(e)}"
+
+# Create Gradio interface with tabs
+with gr.Blocks(title="Image Character Persona Generator") as iface:
+    # Store the generated persona in a state variable to share between tabs
+    persona_state = gr.State("")
+    
+    with gr.Tabs():
+        # First tab: Persona Generator
+        with gr.TabItem("Generate Persona"):
+            gr.Markdown("# Image Character Persona Generator")
+            gr.Markdown("Upload an image containing a character to generate an LLM persona based on that character.")
+            
+            with gr.Row():
+                with gr.Column():
+                    input_image = gr.Image(type='filepath', label='Character Image')
+                    min_length = gr.Slider(label='Minimum Description Length', minimum=10, maximum=500, value=50, step=5)
+                    max_length = gr.Slider(label='Maximum Description Length', minimum=50, maximum=1000, value=200, step=10)
+                    detail_level = gr.Radio(["Basic", "Detailed", "Comprehensive"], label="Persona Detail Level", value="Comprehensive")
+                    submit_btn = gr.Button("Generate Character Persona")
+                
+                with gr.Column():
+                    caption_output = gr.Textbox(label='Character Description (Base Caption)')
+                    persona_output = gr.Textbox(label='LLM Character Persona Prompt', lines=10)
+                    time_output = gr.Textbox(label='Processing Information')
+            
+            gr.Markdown("""
+            ## How to use this tool
+            1. Upload an image containing a character (real or fictional)
+            2. Adjust the sliders to control description length
+            3. Select detail level for the persona
+            4. Click "Generate Character Persona"
+            5. Switch to the "Test Persona" tab to chat with your character
+            """)
+        
+        # Second tab: Test Character Chat
+        with gr.TabItem("Test Persona"):
+            gr.Markdown("# Test Your Character Persona")
+            gr.Markdown("Chat with an AI using your generated character persona to see how it behaves.")
+            
+            with gr.Row():
+                with gr.Column():
+                    system_prompt = gr.Textbox(label="Character Persona (System Prompt)", lines=8)
+                    
+                    with gr.Accordion("Advanced Settings", open=False):
+                        max_tokens = gr.Slider(label="Max Tokens", minimum=50, maximum=2048, value=512, step=1)
+                        temperature = gr.Slider(label="Temperature", minimum=0.1, maximum=1.5, value=0.7, step=0.1)
+                        top_p = gr.Slider(label="Top P", minimum=0.1, maximum=1.0, value=0.95, step=0.05)
+                
+                with gr.Column():
+                    chatbot = gr.Chatbot(label="Conversation with Character")
+                    msg = gr.Textbox(label="Your message")
+                    clear_btn = gr.Button("Clear Conversation")
+            
+            # Handle sending messages in the chat
+            def respond(message, chat_history, system_message, max_tokens, temperature, top_p):
+                if not message.strip():
+                    return "", chat_history
+                
+                # Add user message to history
+                chat_history.append((message, ""))
+                
+                # Get response from API
+                bot_response = chat_with_persona(message, chat_history, system_message, max_tokens, temperature, top_p)
+                
+                # Update the last response in history
+                chat_history[-1] = (message, bot_response)
+                
+                return "", chat_history
+            
+            # Clear chat history
+            def clear_chat():
+                return []
+            
+            # Connect message input to chat response
+            msg.submit(respond, 
+                      [msg, chatbot, system_prompt, max_tokens, temperature, top_p], 
+                      [msg, chatbot])
+            
+            clear_btn.click(clear_chat, outputs=chatbot)
+    
+    # Function to update system prompt in Test tab when persona is generated
+    def update_persona_state(caption, persona, time_output):
+        return persona, persona
+    
+    # Connect the persona generator to update the system prompt
+    submit_btn.click(fn=generate_persona, 
+                    inputs=[input_image, min_length, max_length, detail_level],
+                    outputs=[caption_output, persona_output, time_output])
+    
+    # Update the system prompt in Test tab when persona is generated
+    submit_btn.click(fn=update_persona_state,
+                    inputs=[caption_output, persona_output, time_output],
+                    outputs=[persona_state, system_prompt])
+
+# Launch the interface
+iface.launch()