app.py

import os
import gradio as gr
import faiss
import numpy as np
import pickle
from sentence_transformers import SentenceTransformer
from transformers import AutoTokenizer, AutoModelForCausalLM


HF_TOKEN = os.getenv("HF_TOKEN")
if not HF_TOKEN:
    raise ValueError("HF_TOKEN environment variable not set. Please configure it in Space settings.")


# Load precomputed chunks and FAISS index
with open("chunks.pkl", "rb") as f:
    chunks = pickle.load(f)
index = faiss.read_index("index.faiss")

# Load embedding model (same as used in preprocessing)
embedding_model = SentenceTransformer("sentence-transformers/paraphrase-multilingual-mpnet-base-v2")


# Load Jais model and tokenizer
model_name = "aubmindlab/aragpt2-base"
tokenizer = AutoTokenizer.from_pretrained(model_name, token=HF_TOKEN, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, token=HF_TOKEN, trust_remote_code=True)


# RAG function to retrieve and generate a response
def get_response(query, k=3):
    query_embedding = embedding_model.encode([query])
    distances, indices = index.search(np.array(query_embedding), k)
    retrieved_chunks = [chunks[i] for i in indices[0]]
    context = " ".join(retrieved_chunks)
    prompt = f"Based on the following documents: {context}, answer the question: {query}"
    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512)
    outputs = model.generate(
        **inputs,
        max_new_tokens=200,
        do_sample=True,
        temperature=0.7,
        top_p=0.9,
        return_full_text=False
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response.split(query)[-1].strip()

# Gradio interface
import gradio as gr

with gr.Blocks(title="المتحدث الآلي للتشريعات المحلية لإمارة دبي") as demo:
    gr.Markdown("# Dubai Legislation Chatbot\nاسأل أي سؤال حول تشريعات دبي- نسخة تجريبة (تصميم وتنفيذ م.أسامة الخطيب")
    chatbot = gr.Chatbot(elem_id="chatbot")  # Assign an ID for CSS targeting
    msg = gr.Textbox(placeholder="اكتب سؤالك هنا...", rtl=True)
    clear = gr.Button("مسح")

    def user(user_message, history):
        return "", history + [[user_message, None]]

    def bot(history):
        user_message = history[-1][0]
        bot_message = get_response(user_message)  # Your response function
        history[-1][1] = bot_message
        return history

    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
        bot, chatbot, chatbot
    )
    clear.click(lambda: None, None, chatbot, queue=False)

# Launch with custom CSS
demo.launch(css="""
    #chatbot {
        direction: rtl;
        text-align: right;
        width: 100%;
    }
""", share=True)