Update app.py

app.py

@@ -1,59 +1,88 @@
 import os
-import random
 import gradio as gr
 from langchain_google_genai.chat_models import ChatGoogleGenerativeAI
+from PIL import Image
+import torch
+from torchvision import models, transforms
 
-# Set the path to the service account key
+# Set up the environment for Google Generative AI
 os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "./firm-catalyst-437006-s4-407500537db5.json"
-
-# Initialize the language model with required parameters
 llm = ChatGoogleGenerativeAI(model='gemini-1.5-pro')  
 
+# Load a pre-trained ResNet50 model for image analysis
+model = models.resnet50(pretrained=True)
+model.eval()  # Set the model to evaluation mode
+
+# Define the transformation for the image
+transform = transforms.Compose([
+    transforms.Resize(256),
+    transforms.CenterCrop(224),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+])
+
+# Load the ImageNet labels
+LABELS_URL = "https://raw.githubusercontent.com/anishathalye/imagenet-simple-labels/master/imagenet-simple-labels.json"
+labels = None
+
+if not os.path.exists("imagenet_labels.json"):
+    import requests
+    response = requests.get(LABELS_URL)
+    with open("imagenet_labels.json", "wb") as f:
+        f.write(response.content)
+
+import json
+with open("imagenet_labels.json") as f:
+    labels = json.load(f)
+
 def chat_with_gemini(message, chat_history):
-    # Append the user message to the chat history
-    chat_history.append(("User", message))  # Append username and message
+    # Generate a response from the language model
+    bot_response = llm.predict(message)
+    chat_history.append((message, bot_response))
     
-    # Generate a response using the language model
-    bot_response = llm.predict(message)  # Get the bot's response from the model
-    chat_history.append(("Bot", bot_response))  # Append bot's username and response
     return chat_history, chat_history
 
-def analyze_image(image, chat_history):
-    # Append the user message for the image sent
-    chat_history.append(("User", "Image sent"))  # Display a placeholder message for the image
+def analyze_image(image_path, chat_history):
+    # Load and preprocess the image
+    image = Image.open(image_path).convert("RGB")
+    image_tensor = transform(image).unsqueeze(0)
+    
+    # Predict the image class
+    with torch.no_grad():
+        outputs = model(image_tensor)
+        _, predicted_idx = outputs.max(1)
+    
+    # Retrieve the label
+    label = labels[predicted_idx.item()]
+    
+    # Respond with the classification result
+    bot_response = f"The image seems to be: {label}."
+    chat_history.append(("Uploaded an image for analysis", bot_response))
     
-    # Provide a random response for image uploads
-    random_responses = [
-        "I can't analyze this image right now, but it looks interesting!",
-        "What a lovely image! But I can't quite figure it out.",
-        "This image seems unique, but I can't process it.",
-        "Interesting! Unfortunately, I can't analyze images yet."
-    ]
-    bot_response = random.choice(random_responses)  # Randomly choose a response
-    chat_history.append(("Bot", bot_response))  # Append bot's response
     return chat_history, chat_history
 
-# Create a Gradio interface
+# Create Gradio interface
 with gr.Blocks() as iface:
     gr.Markdown("# Ken Chatbot")
     gr.Markdown("Ask me anything or upload an image for analysis!")
 
-    chatbot = gr.Chatbot(elem_id="chatbot")  # Initialize the chatbot with an element ID for styling
+    # Chatbot component without usernames
+    chatbot = gr.Chatbot(elem_id="chatbot")
+    
+    # User input components
     msg = gr.Textbox(label="Type your message here...", placeholder="Enter your message...")
-    send_btn = gr.Button("Send")  # New Send button for submitting text messages
-    state = gr.State([])  # Store chat history
-
-    # Image upload component for image analysis
+    send_btn = gr.Button("Send")
     img_upload = gr.Image(type="filepath", label="Upload an image for analysis")
 
-    # Set up the interactions
-    send_btn.click(chat_with_gemini, [msg, state], [chatbot, state])  # Submit message on button click
-    send_btn.click(lambda: "", None, msg)  # Clear text box on submit
+    # State for chat history
+    state = gr.State([])
 
-    # Image submission event for analysis
-    img_upload.change(analyze_image, [img_upload, state], [chatbot, state])
+    # Define interactions
+    send_btn.click(chat_with_gemini, [msg, state], [chatbot, state])  # Handle text input
+    send_btn.click(lambda: "", None, msg)  # Clear textbox
+    img_upload.change(analyze_image, [img_upload, state], [chatbot, state])  # Handle image uploads
 
-    # Custom CSS for styling the chatbot messages
+    # Custom CSS for styling chat bubbles without usernames
     gr.HTML("""
     <style>
     #chatbot .message-container {
@@ -62,11 +91,6 @@ with gr.Blocks() as iface:
         margin-bottom: 10px;
         max-width: 70%;
     }
-    #chatbot .username {
-        font-weight: bold;
-        font-size: 12px;
-        margin-bottom: 2px;
-    }
     #chatbot .message {
         border-radius: 15px;
         padding: 10px;
@@ -83,24 +107,8 @@ with gr.Blocks() as iface:
         margin-right: auto;
         text-align: left;
     }
-    #chatbot .username.user {
-        color: #3C763D;
-        text-align: right;
-    }
-    #chatbot .username.bot {
-        color: #333;
-        text-align: left;
-    }
-    .username.user {
-        color: #3C763D;
-        text-align: right;
-    }
-    .username.bot {
-        color: #333;
-        text-align: left;
-    }
     </style>
     """)
 
-# Launch the interface with debugging enabled
+# Launch the Gradio interface
 iface.launch(debug=True)