Update app.py

app.py

@@ -1,9 +1,6 @@
 import gradio as gr
 import os
 from openai import OpenAI
-import base64
-from PIL import Image
-import io
 
 # OpenRouter API key
 OPENROUTER_API_KEY = "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"
@@ -11,28 +8,19 @@ OPENROUTER_API_KEY = "sk-or-v1-e2894f0aab5790d69078bd57090b6001bf34f80057bea8fba
 # Available models
 MODELS = {
     "Mistral Small": "mistralai/mistral-small-3.2-24b-instruct:free",
-    "Kimi Vision": "moonshotai/kimi-vl-a3b-thinking:free",
+    "Claude 3 Haiku": "anthropic/claude-3-haiku:free",
     "Gemini Pro": "google/gemini-2.5-pro-exp-03-25",
-    "Qwen VL": "qwen/qwen2.5-vl-32b-instruct:free",
+    "Qwen": "qwen/qwen2.5-32b-instruct:free",
     "Mistral 3.1": "mistralai/mistral-small-3.1-24b-instruct:free",
     "Gemma": "google/gemma-3-4b-it:free",
-    "Llama 3.2 Vision": "meta-llama/llama-3.2-11b-vision-instruct:free",
+    "Llama 3": "meta-llama/llama-3-70b-instruct:free",
 }
 
-def image_to_base64(image):
-    """Convert an image to base64 encoding"""
-    # If image is a file path
-    if isinstance(image, str):
-        with open(image, "rb") as img_file:
-            return base64.b64encode(img_file.read()).decode()
-    
-    # If image is already a PIL Image
-    buffered = io.BytesIO()
-    image.save(buffered, format="JPEG")
-    return base64.b64encode(buffered.getvalue()).decode()
+# Initialize chat history
+history = []
 
-def analyze_image(image, prompt, model_name):
-    """Analyze an image using the selected OpenRouter model"""
+def chat_with_ai(message, model_name, history):
+    """Chat with the selected OpenRouter model"""
     try:
         # Initialize OpenAI client with OpenRouter base URL
         client = OpenAI(
@@ -40,8 +28,14 @@ def analyze_image(image, prompt, model_name):
             api_key=OPENROUTER_API_KEY,
         )
         
-        # Convert image to base64
-        img_base64 = image_to_base64(image)
+        # Format the conversation history for the API
+        messages = []
+        for human, assistant in history:
+            messages.append({"role": "user", "content": human})
+            messages.append({"role": "assistant", "content": assistant})
+        
+        # Add the current message
+        messages.append({"role": "user", "content": message})
         
         # Create the completion request
         completion = client.chat.completions.create(
@@ -50,23 +44,7 @@ def analyze_image(image, prompt, model_name):
                 "X-Title": "Gradio OpenRouter Interface",
             },
             model=MODELS[model_name],
-            messages=[
-                {
-                    "role": "user",
-                    "content": [
-                        {
-                            "type": "text",
-                            "text": prompt
-                        },
-                        {
-                            "type": "image_url",
-                            "image_url": {
-                                "url": f"data:image/jpeg;base64,{img_base64}"
-                            }
-                        }
-                    ]
-                }
-            ]
+            messages=messages
         )
         
         # Return the model's response
@@ -76,92 +54,63 @@ def analyze_image(image, prompt, model_name):
         return f"Error: {str(e)}"
 
 # Create the Gradio interface
-with gr.Blocks(title="OpenRouter AI Vision Interface", css="style.css") as demo:
+with gr.Blocks(title="OpenRouter AI Chat Interface", css="style.css") as demo:
     gr.Markdown(
         """
-        # 🔍 OpenRouter AI Vision Interface
+        # 💬 OpenRouter AI Chat Interface
         
-        Upload an image and ask a question about it. The AI will analyze the image and respond.
+        Chat with multiple AI models powered by OpenRouter API.
         
-        *Powered by OpenRouter API with multiple vision-language models*
+        *Select from various large language models and start chatting!*
         """
     )
     
     with gr.Row():
-        with gr.Column():
-            # Input components with custom styling
+        with gr.Column(scale=4):
+            # Chat interface
+            chatbot = gr.Chatbot(height=500, label="Conversation")
+            msg = gr.Textbox(label="Your message", placeholder="Type your message here...")
+            
+            with gr.Row():
+                submit_btn = gr.Button("Send", variant="primary")
+                clear_btn = gr.Button("Clear Chat")
+        
+        with gr.Column(scale=1):
+            # Model selection
             with gr.Group():
-                image_input = gr.Image(type="pil", label="Upload Image")
-                prompt_input = gr.Textbox(label="Your Question", placeholder="What is in this image?", value="What is in this image?")
                 model_dropdown = gr.Dropdown(
                     choices=list(MODELS.keys()), 
                     value="Mistral Small", 
                     label="Select AI Model",
-                    info="Choose from different vision-language models"
+                    info="Choose from different language models"
                 )
-                submit_button = gr.Button("Analyze Image", variant="primary")
-        
-        with gr.Column():
-            # Output component with custom styling
-            with gr.Group():
-                output_text = gr.Textbox(label="AI Response", lines=12)
                 
-    gr.Markdown(
-        """
-        ### Available Models
-        - **Mistral Small**: Powerful vision-language model from Mistral AI
-        - **Kimi Vision**: Specialized vision model from Moonshot AI
-        - **Gemini Pro**: Google's advanced multimodal model
-        - **Qwen VL**: Alibaba's vision-language model
-        - **Mistral 3.1**: Earlier version of Mistral's vision model
-        - **Gemma**: Google's lightweight vision model
-        - **Llama 3.2 Vision**: Meta's vision-enabled large language model
-        """
-    )
+                gr.Markdown(
+                    """
+                    ### Available Models
+                    - **Mistral Small**: Powerful language model from Mistral AI
+                    - **Claude 3 Haiku**: Fast and efficient model from Anthropic
+                    - **Gemini Pro**: Google's advanced language model
+                    - **Qwen**: Alibaba's large language model
+                    - **Mistral 3.1**: Earlier version of Mistral's model
+                    - **Gemma**: Google's lightweight language model
+                    - **Llama 3**: Meta's large language model
+                    """
+                )
     
     # Set up the submit action
-    submit_button.click(
-        fn=analyze_image,
-        inputs=[image_input, prompt_input, model_dropdown],
-        outputs=output_text
-    )
-    
-    # Add example
-    gr.Examples(
-        examples=[
-            ["examples/nature.jpg", "What is in this image?", "Mistral Small"],
-            ["examples/nature.jpg", "Describe this scene in detail", "Kimi Vision"],
-        ],
-        inputs=[image_input, prompt_input, model_dropdown],
-    )
-
-# Create examples directory if it doesn't exist
-os.makedirs("examples", exist_ok=True)
-
-# Download example image if it doesn't exist
-def download_example_image():
-    if not os.path.exists("examples/nature.jpg"):
-        import requests
-        from PIL import Image
-        from io import BytesIO
-        
-        # URL of the example image
-        image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
+    def respond(message, chat_history, model):
+        if not message.strip():
+            return "", chat_history
         
-        # Download and save the image
-        response = requests.get(image_url)
-        if response.status_code == 200:
-            # Open the image from the response content
-            img = Image.open(BytesIO(response.content))
-            
-            # Save the image to the examples directory
-            img.save("examples/nature.jpg")
-            print("Example image downloaded successfully!")
-        else:
-            print(f"Failed to download image. Status code: {response.status_code}")
-
-# Download example image before launching the app
-download_example_image()
+        bot_message = chat_with_ai(message, model, chat_history)
+        chat_history.append((message, bot_message))
+        return "", chat_history
+    
+    # Connect the components
+    submit_btn.click(respond, [msg, chatbot, model_dropdown], [msg, chatbot])
+    msg.submit(respond, [msg, chatbot, model_dropdown], [msg, chatbot])
+    clear_btn.click(lambda: None, None, chatbot, queue=False)
 
 # For Hugging Face Spaces compatibility
 if __name__ == "__main__":