Attempt 5 (ChatGPT revised)

app.py

@@ -1,7 +1,12 @@
 import gradio as gr
 
+# Define the theme with custom colors and styles
 theme = gr.themes.Default(
-    primary_hue=gr.themes.Color(c100="#ffedd5", c200="#fed7aa", c300="#ffe09e", c400="#c2814c", c50="#fff8f0", c500="#f97316", c600="#ea580c", c700="#c2410c", c800="#9a3412", c900="#7c2d12", c950="#611f00"),
+    primary_hue=gr.themes.Color(
+        c100="#ffedd5", c200="#fed7aa", c300="#ffe09e", c400="#c2814c",
+        c50="#fff8f0", c500="#f97316", c600="#ea580c", c700="#c2410c",
+        c800="#9a3412", c900="#7c2d12", c950="#611f00"
+    ),
     secondary_hue="red",
     neutral_hue="slate",
     font=[gr.themes.GoogleFont('jack armstrong'), 'ui-sans-serif', 'system-ui', 'sans-serif'],
@@ -64,25 +69,17 @@ theme = gr.themes.Default(
     button_cancel_text_color_dark='*button_secondary_text_color'
 )
 
-with gr.Blocks(theme=theme) as demo:
-    ...
-
 from sentence_transformers import SentenceTransformer, util
 import openai
 import os
 
-# potential color customization
-from transformers import pipeline
-
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
-# Initialize paths and model identifiers for easy configuration and maintenance
-filename = "output_chess_details.txt"  # Path to the file storing chess-specific details
+filename = "output_chess_details.txt"
 retrieval_model_name = 'output/sentence-transformer-finetuned/'
 
 openai.api_key = os.environ["OPENAI_API_KEY"]
 
-# Attempt to load the necessary models and provide feedback on success or failure
 try:
     retrieval_model = SentenceTransformer(retrieval_model_name)
     print("Models loaded successfully.")
@@ -90,9 +87,6 @@ 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()]
@@ -105,37 +99,21 @@ 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 information about St. Louis events.
-    """
     try:
         system_message = "You are a chatbot specialized in providing information on local events, pro-Palestine movements, and community outreach, pride movements/events and community resources."
-        user_message = f"Here's the information on St. Louis local events, outreach programs, community resources and local activism and movements.  : {relevant_segment}"
+        user_message = f"Here's the information on St. Louis local events, outreach programs, community resources and local activism and movements: {relevant_segment}"
         messages = [
             {"role": "system", "content": system_message},
             {"role": "user", "content": user_message}
@@ -155,9 +133,6 @@ def generate_response(user_query, relevant_segment):
         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 GloBot! Ask me anything about the St. Louis Community!"
     relevant_segment = find_relevant_segment(question, segments)
@@ -166,9 +141,7 @@ def query_model(question):
     response = generate_response(question, relevant_segment)
     return response
 
-# Define the welcome message and specific topics the chatbot can provide information about
 welcome_message = """
-
 ## Your AI-driven assistant for STL community outreach queries. Created by Honna, Davonne, and Maryam of the 2024 Kode With Klossy St.Louis Camp! 
 """
 
@@ -179,32 +152,27 @@ topics = """
 -  Social Justice Workshops
 -  Cultural Festivals
 -  Community Outreach Programs
--  Enviormental Activism
+-  Environmental Activism
 -  Health & Wellness Events
 - How to Support Local Businesses
 """
 
-
-# Display function
-
 def display_image():
     return "Globot_Logo3.jpg"
 
 # Setup the Gradio Blocks interface with custom layout components
-with gr.Blocks(theme='gstaff/xkcd') as demo:
-    gr.Image(display_image(), width = 2000, height=600)
-    gr.Markdown(welcome_message)  # Display the formatted welcome message
+with gr.Blocks(theme=theme) as demo:
+    gr.Image(display_image(), width=2000, height=600)
+    gr.Markdown(welcome_message)
     with gr.Row():
         with gr.Column():
-            gr.Markdown(topics)  # Show the topics on the left side
+            gr.Markdown(topics)
     with gr.Row():
         with gr.Column():
             question = gr.Textbox(label="Your question", placeholder="What do you want to ask about?")
             answer = gr.Textbox(label="GloBot Response", placeholder="GloBot will respond here...", interactive=False, lines=10)
             submit_button = gr.Button("Submit")
             submit_button.click(fn=query_model, inputs=question, outputs=answer)
-    
 
-    
 # Launch the Gradio app to allow user interaction
 demo.launch(share=True)