app.py

# app.py
import gradio as gr
from src.agent import Agent
from src.create_database import load_and_process_dataset  # Import from create_database.py
import os
import uuid
import requests
import logging
import subprocess
from llama_cpp import Llama  # Import Llama from llama_cpp
import spacy

# Configure logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Function to install requirements
def install_requirements():
    try:
        subprocess.check_call([os.sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
        logging.info("Requirements installed successfully.")
    except subprocess.CalledProcessError as e:
        logging.error(f"Failed to install requirements: {e}")

# Function to download the spaCy model
def download_spacy_model(model_name):
    try:
        subprocess.check_call([os.sys.executable, '-m', 'spacy', 'download', model_name])
        logging.info(f"SpaCy model {model_name} downloaded successfully.")
    except subprocess.CalledProcessError as e:
        logging.error(f"Failed to download SpaCy model {model_name}: {e}")

# Install requirements
install_requirements()

# Download the spaCy model if it doesn't exist
if not spacy.util.is_package('en_core_web_lg'):
    download_spacy_model('en_core_web_lg')

# Create the directory if it doesn't exist
local_dir = "models"
os.makedirs(local_dir, exist_ok=True)

# Specify the filename for the model
filename = "unsloth.Q4_K_M.gguf"
model_path = os.path.join(local_dir, filename)

# Function to download the model file
def download_model(repo_id, filename, save_path):
    # Construct the URL for the model file
    url = f"https://huggingface.co/{repo_id}/resolve/main/{filename}"

    # Download the model file
    response = requests.get(url)
    if response.status_code == 200:
        with open(save_path, 'wb') as f:
            f.write(response.content)
        print(f"Model downloaded to {save_path}")
    else:
        print(f"Failed to download model: {response.status_code}")

# Download the model if it doesn't exist
if not os.path.exists(model_path):
    download_model("PurpleAILAB/Llama3.2-3B-uncensored-SQLi-Q4_K_M-GGUF", filename, model_path)

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
):
    model_path = "models/unsloth.Q4_K_M.gguf"  # Path to the downloaded model
    db_path = "agent.db"
    system_prompt = system_message

    # Check if the database exists, if not, initialize it
    if not os.path.exists(db_path):
        data_update_path = "data-update.txt"
        keyword_dir = "keyword"  # Updated keyword directory
        load_and_process_dataset(data_update_path, keyword_dir, db_path)

    # Load the model with the maximum context length and control the maximum tokens in the response
    llm = Llama(
        model_path=model_path,
        n_ctx=500,  # Set the maximum context length
        max_tokens=500  # Control the maximum number of tokens generated in the response
    )

    agent = Agent(llm, db_path, system_prompt)
    user_id = str(uuid.uuid4())  # Generate a unique user ID for each session

    response = agent.process_query(user_id, message)
    return response

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="Vous êtes l'assistant intelligent de Les Chronique MTC. Votre rôle est d'aider les visiteurs en expliquant le contenu des Chroniques, Flash Infos et Chronique-FAQ de Michel Thomas. Utilisez le contexte fourni pour améliorer vos réponses et veillez à ce qu'elles soient précises et pertinentes.", label="System message"),
    ],
)

if __name__ == "__main__":
    demo.launch()