Update app.py

app.py

@@ -1,3 +1,52 @@
+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
+    )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response.split(query)[-1].strip()
+
+# Gradio interface
+
 import gradio as gr
 
 # Print current Gradio version