Create app.py

app.py

@@ -1 +1,69 @@
 streamlit run app.py
+# app.py
+import os
+from huggingface_hub import login
+from transformers import pipeline
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+import gradio as gr
+
+# Step 1: Authenticate with Hugging Face using an environment variable
+api_key = os.getenv("HF_API_KEY")  # Retrieves the API key from environment variables
+login(api_key)
+
+# Initialize a free question-answering model from Hugging Face
+question_answerer = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
+
+# Load or create data on Pakistan's economic and population growth trends
+documents = [
+    {"id": 1, "text": "Pakistan's population growth rate is approximately 2%, making it one of the fastest-growing populations in South Asia."},
+    {"id": 2, "text": "The youth population in Pakistan is significant, with over 60% of the population under the age of 30."},
+    {"id": 3, "text": "Pakistan's economy relies heavily on agriculture, with about 20% of GDP coming from this sector."},
+    {"id": 4, "text": "In recent years, Pakistan has been investing in infrastructure projects, such as the China-Pakistan Economic Corridor (CPEC), to boost economic growth."},
+    {"id": 5, "text": "Urbanization is rapidly increasing in Pakistan, with cities like Karachi and Lahore seeing substantial population inflows."},
+    {"id": 6, "text": "Remittances from overseas Pakistanis play a critical role in supporting the country's economy."},
+    {"id": 7, "text": "Pakistan's literacy rate has improved over the years but remains lower than the regional average."},
+    {"id": 8, "text": "The government is focusing on initiatives for digital economy growth, particularly in the technology and freelancing sectors."},
+    {"id": 9, "text": "Pakistan’s unemployment rate is a concern, especially among young people entering the job market."},
+    {"id": 10, "text": "The fertility rate in Pakistan has been declining but remains above the replacement rate."},
+]
+
+# Step 2: Embed documents for retrieval using SentenceTransformer
+embedder = SentenceTransformer('all-MiniLM-L6-v2')  # A lightweight embedding model
+document_embeddings = [embedder.encode(doc['text']) for doc in documents]
+index = faiss.IndexFlatL2(384)  # Dimension of the embeddings
+index.add(np.array(document_embeddings))
+
+# Step 3: Define the RAG retrieval function
+def retrieve_documents(query, top_k=3):
+    query_embedding = embedder.encode(query).reshape(1, -1)
+    distances, indices = index.search(query_embedding, top_k)
+    return [documents[i]['text'] for i in indices[0]]
+
+# Step 4: Implement the question-answering function with retrieval
+def ask_question(question):
+    # Retrieve relevant documents
+    retrieved_docs = retrieve_documents(question)
+    # Combine retrieved documents into a single context
+    context = " ".join(retrieved_docs)
+    
+    # Use the model to generate an answer based on retrieved context
+    answer = question_answerer(question=question, context=context)
+    return answer['answer']
+
+# Step 5: Create Gradio Interface for the RAG app
+def rag_interface(question):
+    answer = ask_question(question)
+    return answer
+
+# Step 6: Launch the Gradio app
+interface = gr.Interface(
+    fn=rag_interface,
+    inputs="text",
+    outputs="text",
+    title="Pakistan Economic and Population Growth Advisor",
+    description="Ask questions related to Pakistan's economic and population growth. This app uses retrieval-augmented generation to provide answers based on relevant documents about Pakistan."
+)
+
+interface.launch()