import gradio as gr
from sentence_transformers import SentenceTransformer, util
import transformers
from transformers import pipeline
import webbrowser
import openai
import os
os.environ["TOKENIZERS_PARALLELISM"] = "false"
# Initialize paths and model identifiers for easy configuration and maintenance
filename = "output_composting_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"]
# 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_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 to provide information related to composting food.
"""
try:
system_message = "You are a chatbot specialized in providing information about food composting tips, tricks, and basics."
user_message = f"Here's the information on composting: {relevant_segment}"
messages = [
{"role": "system", "content": system_message},
{"role": "user", "content": user_message}
]
response = openai.ChatCompletion.create(
model="gpt-4o",
messages=messages,
max_tokens=200,
temperature=0.5,
top_p=1,
frequency_penalty=0.5,
presence_penalty=0.5
)
return response['choices'][0]['message']['content'].strip()
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 CompBot! Ask me anything about composting tips, tricks, and basics!"
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 = """
<span style="color:#836953; font-size:24px; font-family:Roboto;">🌱Welcome to CompBot!</span>
""""""
## Your AI-driven assistant for all composting-related queries.
"""
topics = """
### Feel free to ask me anything from the topics below!
- Components of composting
- Green and brown materials
- The composting process
- Common strategies
- Uses of compost
- Tips for successful composting
- Sustainability
"""
# Define the HTML iframe content
podcast_iframe = '''
<div style="height:10px;"></div>
<iframe style="border-radius:12px"
src="https://open.spotify.com/embed/episode/1Emjgqf8PfwD42kvyKvtfW?utm_source=generator&theme=0"
width="100%" height="152" frameBorder="0"
allow="autoplay; clipboard-write; encrypted-media; fullscreen; picture-in-picture" loading="lazy"></iframe>
<div style="height:20px;"></div>
<iframe style="border-radius:12px"
src="https://open.spotify.com/embed/episode/6m83iwiAwCOu5yaW8LOT1v?utm_source=generator&theme=0"
width="100%" height="152" frameBorder="0" allowfullscreen=""
allow="autoplay; clipboard-write; encrypted-media; fullscreen; picture-in-picture" loading="lazy"></iframe>
'''
youtube_iframe = '''
<iframe width="560" height="315" src="https://www.youtube.com/embed/MryNKPPvFbk" frameborder="0"
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
'''
def display_image():
return "https://huggingface.co/spaces/dogutcu/composting-how-tos/resolve/main/compbot.jpeg"
custom_css = """
<style>
.textbox-question {
background-color: #E8F0FE !important; /* Light blue background */
}
.textbox-answer {
background-color: #F1F8E9 !important; /* Light green background */
}
</style>
"""
theme = gr.themes.Base().set(
background_fill_primary='#AFC9AD', # Light cyan background
background_fill_primary_dark='#AFC9AD', # Dark teal background
background_fill_secondary='#ffccbc', # Light orange background
background_fill_secondary_dark='#d84315', # Dark orange background
border_color_accent='#ffab40', # Accent border color
border_color_accent_dark='#ff6d00', # Dark accent border color
border_color_accent_subdued='#ff8a65', # Subdued accent border color
border_color_primary='#2a2a2a', # Primary border color
block_border_color='#2a2a2a', # Block border color
button_primary_background_fill='#2a2a2a', # Primary button background color
button_primary_background_fill_dark='#2a2a2a' # Dark primary button background color
)
# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme=theme) as demo:
gr.HTML(custom_css)
gr.Image(display_image(), show_label = False, show_share_button = False, show_download_button = False, width=300, height=200)
gr.Markdown(welcome_message) # Display the formatted welcome message
with gr.Row():
with gr.Column():
gr.Markdown(topics) # Show the topics on the left side
gr.HTML(youtube_iframe) # Embed the iframe on the left side
with gr.Row():
with gr.Column():
question = gr.Textbox(label="Your question", placeholder="What would you like to know?")
answer = gr.Textbox(label="CompBot Response", placeholder="CompBot will respond here...", interactive=False, lines=16)
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)