Update app.py

app.py

@@ -2,115 +2,94 @@ import gradio as gr
 from sentence_transformers import SentenceTransformer, util
 import openai
 import os
-import pandas as pd
-
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
-
-# Initialize paths and model identifiers
-filename = "output_topic_details.txt"
+# 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/'
-
 openai.api_key = os.environ["OPENAI_API_KEY"]
-
-system_message = (
-    "You are a restaurant recommending chatbot that takes details about a restaurant including type of restaurant, "
-    "dietary restrictions, and budget and chooses a restaurant in Seattle which best fits the user's criteria. "
-    "Then you output the restaurant name and website link."
-)
+system_message = "You are a restaurant recommending chatbot that suggests one restaurant based on the criteria the user provides."
+# Initial system message to set the behavior of the assistant
 messages = [{"role": "system", "content": system_message}]
-
-# Load the data into a DataFrame for easier querying
-def load_and_preprocess_data(filename):
+# Attempt to load the necessary models and provide feedback on success or failure
+try:
+    retrieval_model = SentenceTransformer(retrieval_model_name)
+    print("Models loaded successfully.")
+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:
-            data = file.read()
-        # Split into sections based on "Topic:" and then split into lines
-        sections = data.split("Topic: ")
-        restaurant_data = []
-        
-        for section in sections[1:]:
-            lines = section.strip().split("\n")
-            topic = lines[0]
-            description = "\n".join(lines[1:])
-            if topic == "Details about Restaurants":
-                lines = description.split("\n")
-                # Convert to a DataFrame
-                df = pd.DataFrame([line.split(",") for line in lines[1:]], columns=lines[0].split(","))
-                restaurant_data.append(df)
-        
-        # Concatenate all DataFrames into one
-        full_df = pd.concat(restaurant_data, ignore_index=True)
-        full_df.columns = full_df.columns.str.strip()  # Strip any extra whitespace from column names
-        print("Data loaded and preprocessed successfully.")
-        return full_df
+            segments = [line.strip() for line in file if line.strip()]
+        print("Text loaded and preprocessed successfully.")
+        return segments
     except Exception as e:
-        print(f"Failed to load or preprocess data: {e}")
-        return pd.DataFrame()
-
-data_df = load_and_preprocess_data(filename)
-
-def filter_restaurants(cuisine=None, dietary_restrictions=None, budget=None):
-    df_filtered = data_df
-    
-    if cuisine:
-        df_filtered = df_filtered[df_filtered['Type of Restaurant'].str.contains(cuisine, case=False, na=False)]
-    if dietary_restrictions:
-        for restriction in dietary_restrictions:
-            df_filtered = df_filtered[df_filtered[restriction].str.contains('Yes', case=False, na=False)]
-    if budget:
-        df_filtered = df_filtered[df_filtered['Price'].str.contains(budget, case=False, na=False)]
-    
-    if df_filtered.empty:
-        return "No matching restaurants found."
-
-    # Convert DataFrame to a list of dictionaries for easier handling
-    restaurants = df_filtered[['Restaurant', 'Website']].to_dict(orient='records')
-    return restaurants
-
-def generate_response(user_query):
-    # Example of parsing the query for simplicity
-    # You might want to use more sophisticated parsing and NLP for better results
-    # Dummy parsing based on example query format
-    cuisine = None
-    dietary_restrictions = []
-    budget = None
-
-    if 'gluten-free' in user_query.lower():
-        dietary_restrictions.append('Gluten-free Options?')
-    if 'vegan' in user_query.lower():
-        dietary_restrictions.append('Vegan Options?')
-    if 'lactose-intolerant' in user_query.lower():
-        dietary_restrictions.append('Lactose-Intolerant Options?')
-    if 'pescatarian' in user_query.lower():
-        dietary_restrictions.append('Pescatarian Options?')
-    
-    if 'low' in user_query.lower():
-        budget = 'Low'
-    elif 'moderate' in user_query.lower():
-        budget = 'Moderate'
-    elif 'high' in user_query.lower():
-        budget = 'High'
-    
-    # Handle cuisine extraction if needed
-
-    results = filter_restaurants(cuisine=cuisine, dietary_restrictions=dietary_restrictions, budget=budget)
-    if isinstance(results, str):  # If no restaurants found
-        return results
-    
-    response = "\n".join([f"{r['Restaurant']}: {r['Website']}" for r in results])
-    return response
-
+        print(f"Failed to load or preprocess text: {e}")
+        return []
+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 suggesting a restaurant.
+    """
+    try:
+        user_message = f"Here is a local restaurant based on your information: {relevant_segment}"
+        # Append user's message to messages list
+        messages.append({"role": "user", "content": user_message})
+        response = openai.ChatCompletion.create(
+            model="gpt-4o",
+            messages=messages,
+            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 "Please provide your restaurant preferences."
-    response = generate_response(question)
+        return "Give me your preferences..."
+    relevant_segment = find_relevant_segment(question, segments)
+    if not relevant_segment:
+        return "Could not find specific information. Please refine your question."
+    response = generate_response(question, relevant_segment)
     return response
-
+# Define the welcome message and specific topics the chatbot can provide information about
 welcome_message = """
 # Welcome to Ethical Eats Explorer!
-## Your AI-driven assistant for restaurant recs in Seattle. Created by Saranya, Cindy, and Liana of the 2024 Kode With Klossy Seattle Camp. 
+## Your AI-driven assistant for restaurant recs in Seattle. Created by Saranya, Cindy, and Liana of the 2024 Kode With Klossy Seattle Camp.
 """
-
 topics = """
 ### Please give me your restaurant preferences:
 - Dietary Restrictions
@@ -119,17 +98,17 @@ topics = """
 - Budget Preferences (Low: $0 - $20, Moderate: $20 - $30, High: $30+ - per person)
 Please send your message in the format: "Could you give me a (cuisine) restaurant with (dietary restriction) options that is (budget) budget?"
 """
-
+# Setup the Gradio Blocks interface with custom layout components
 with gr.Blocks(theme='JohnSmith9982/small_and_pretty') as demo:
-    gr.Markdown(welcome_message)
+    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="Give me your information...")
             answer = gr.Textbox(label="Explorer's Response", placeholder="Explorer 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)