Update app.py

app.py

@@ -8,7 +8,11 @@ os.environ["TOKENIZERS_PARALLELISM"] = "false"
 # Initialize paths and model identifiers for easy configuration and maintenance
 filename = "output_topic_details.txt"  # Path to the file storing chess-specific details
 retrieval_model_name = 'output/sentence-transformer-finetuned/'
-path_to_image = "images/san-francisco.jpg"  # Update this to the correct path
+
+# Define paths to images
+path_to_sf_image = "output/sf.png"
+path_to_sacramento_image = "output/sacramento.png"
+path_to_la_image = "output/la.png"
 
 openai.api_key = os.environ["OPENAI_API_KEY"]
 
@@ -24,6 +28,9 @@ except Exception as e:
     print(f"Failed to load models: {e}")
 
 def load_and_preprocess_text(filename):
+    """
+    Load and preprocess text from a file, removing empty lines and stripping whitespace.
+    """
     try:
         with open(filename, 'r', encoding='utf-8') as file:
             segments = [line.strip() for line in file if line.strip()]
@@ -36,50 +43,83 @@ def load_and_preprocess_text(filename):
 segments = load_and_preprocess_text(filename)
 
 def find_relevant_segment(user_query, segments):
+    """
+    Find the most relevant text segment for a user's query using cosine similarity among sentence embeddings.
+    This version finds the best match based on the content of the query.
+    """
     try:
+        # Lowercase the query for better matching
         lower_query = user_query.lower()
+        
+        # Encode the query and the segments
         query_embedding = retrieval_model.encode(lower_query)
         segment_embeddings = retrieval_model.encode(segments)
+        
+        # Compute cosine similarities between the query and the segments
         similarities = util.pytorch_cos_sim(query_embedding, segment_embeddings)[0]
+        
+        # Find the index of the most similar segment
         best_idx = similarities.argmax()
+        
+        # Return the most relevant segment
         return segments[best_idx]
     except Exception as e:
         print(f"Error in finding relevant segment: {e}")
         return ""
 
 def generate_response(user_query, relevant_segment):
+    """
+    Generate a response emphasizing the bot's capability in providing astronomical information.
+    """
     try:
         user_message = f"Here's the information on outer space: {relevant_segment}"
+
+        # Append user's message to messages list
         messages.append({"role": "user", "content": user_message})
         
         response = openai.ChatCompletion.create(
-            model="gpt-4o",
+            model="gpt-3.5-turbo",
             messages=messages,
-            max_tokens=500,
+            max_tokens=150,
             temperature=0.2,
             top_p=1,
             frequency_penalty=0,
             presence_penalty=0
         )
         
+        # Extract the response text
         output_text = response['choices'][0]['message']['content'].strip()
+        
+        # Append assistant's message to messages list for context
         messages.append({"role": "assistant", "content": output_text})
+        
         return output_text
+        
     except Exception as e:
         print(f"Error in generating response: {e}")
         return f"Error in generating response: {e}"
 
 def query_model(question):
+    """
+    Process a question, find relevant information, and generate a response.
+    """
     if question == "":
-        return "Welcome to Starfinder! Ask me anything about outer space, stargazing, and upcoming astronomical events."
+        return "Welcome to Starfinder! Ask me anything about outer space, stargazing, and upcoming astronomical events.", None
+    
     if "san francisco" in question.lower():
-        return path_to_image  # Return the image path when asked about San Francisco
+        return "Here is a picture of San Francisco!", path_to_sf_image
+    if "sacramento" in question.lower():
+        return "Here is a picture of Sacramento!", path_to_sacramento_image
+    if "los angeles" in question.lower() or "la" in question.lower():
+        return "Here is a picture of Los Angeles!", path_to_la_image
+    
     relevant_segment = find_relevant_segment(question, segments)
     if not relevant_segment:
-        return "Could not find specific information. Please refine your question."
+        return "Could not find specific information. Please refine your question.", None
     response = generate_response(question, relevant_segment)
-    return response
+    return response, None
 
+# Define the welcome message and specific topics the chatbot can provide information about
 welcome_message = """
 # ♟️ Welcome to Starfinder!
 ## Your AI-driven assistant for all astronomy-related queries. Created by Aarna, Aditi, and Anastasia of the 2024 Kode With Klossy SF Camp. 
@@ -95,21 +135,39 @@ topics = """
 - Astronomy tips
 """
 
-with gr.Blocks(theme='JohnSmith9982/small_and_pretty') as demo:
-    gr.Markdown(welcome_message)
+STARS = gr.themes.Base().set(
+    background_fill_primary='#2A628F',  # Light yellow background
+    background_fill_primary_dark='#FFD700',  # Darker yellow background
+    background_fill_secondary='#3E92CC',  # Light blue background
+    background_fill_secondary_dark='#2A628F',  # Darker blue background
+    border_color_accent='#16324F',  # Accent border color (dark blue)
+    border_color_accent_dark='#16324F',  # Dark accent border color (dark blue)
+    border_color_accent_subdued='#18435A',  # Subdued accent border color (slightly lighter blue)
+    border_color_primary='#2A628F',  # Primary border color (medium blue)
+    block_border_color='#2A628F',  # Block border color (medium blue)
+    button_primary_background_fill='#2A628F',  # Primary button background color (medium blue)
+)
+
+# Setup the Gradio Blocks interface with custom layout components
+with gr.Blocks(theme=STARS) as demo:
+    gr.Markdown(welcome_message)  # Display the formatted welcome message
     with gr.Row():
         with gr.Column():
-            gr.Markdown(topics)
+            gr.Markdown(topics)  # Show the topics on the left side
     with gr.Row():
         with gr.Column():
             question = gr.Textbox(label="Your question", placeholder="What do you want to ask about?")
             answer = gr.Textbox(label="StarFinder Response", placeholder="StarFinder will respond here...", interactive=False, lines=10)
+            image_output = gr.Image(label="Image Output")  # Add an Image component
             submit_button = gr.Button("Submit")
-            submit_button.click(fn=query_model, inputs=question, outputs=answer)
-            gr.Image(path_to_image).style(display=False)  # This will be toggled to display when needed
+            submit_button.click(fn=query_model, inputs=question, outputs=[answer, image_output])  # Update outputs to include the image component
 
+# Launch the Gradio app to allow user interaction
 demo.launch(share=True)
 
 
 
 
+
+
+