import gradio as gr
from sentence_transformers import SentenceTransformer, util
import openai
import os
import random # Import the random library
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/'
openai.api_key = os.environ["OPENAI_API_KEY"]
system_message = "You put together outfits by taking keywords such as modest or not modest,comfort level (1=comfortable, 2=everyday wear, 3=formal), color, and occasion inputted by users and outputting a list of simple clothing pieces (consisting of a top, bottom, and possibly accessories and outerwear) and a Pinterest link to the outfit created, resulting in a cohesive outfit."
# Initial system message to set the behavior of the assistant
messages = [{"role": "system", "content": system_message}]
# 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:
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 text: {e}")
return []
segments = load_and_preprocess_text(filename)
def find_relevant_segments(user_query, segments):
"""
Find the most relevant text segments for a user's query using cosine similarity among sentence embeddings.
"""
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]
# Get indices of the most similar segments
best_indices = similarities.topk(5).indices.tolist()
# Return the most relevant segments
return [segments[idx] for idx in best_indices]
except Exception as e:
print(f"Error in finding relevant segments: {e}")
return []
def generate_response(user_query, relevant_segments):
"""
Generate a response emphasizing the bot's capability in providing fashion information.
"""
try:
# Randomly select an outfit from the relevant segments
random_segment = random.choice(relevant_segments)
user_message = f"Of course! Here are your outfit suggestions and some sustainable brands you can buy from: {random_segment}"
# Append user's message to messages list
messages.append({"role": "user", "content": user_message})
response = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=messages,
max_tokens=150,
temperature=0.4,
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 Savvy! Use the word bank to describe the outfit you would like generated."
relevant_segments = find_relevant_segments(question, segments)
if not relevant_segments:
return "I'm sorry. Could you be more specific? Check your spelling and make sure to use words from the bank."
response = generate_response(question, relevant_segments)
return response
# Define the welcome message and specific topics the chatbot can provide information about
welcome_message = """
"""
topics = """
"""
pinterest = """