Spaces:
Sleeping
Sleeping
File size: 2,810 Bytes
d464752 3d77d1e d5efa20 3d77d1e d5efa20 3d77d1e d5efa20 3d77d1e d5efa20 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
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)
|