Update app.py

app.py

@@ -70,5 +70,48 @@ def create_vector_store(text):
 st.title("RAG-based Application with Focused Context")
 
 # Predefined Google Drive link
-drive_url = "h
+drive_url = "https://drive.google.com/file/d/1XvqA1OIssRs2gbmOtKFKj-02yQ5X2yg0/view?usp=sharing"
+
+# Extract document content
+st.write("Extracting content from the document...")
+text = extract_pdf_content(drive_url)
+if text:
+    st.write("Document extracted successfully!")
+
+    st.write("Creating vector store...")
+    vector_store, sentences = create_vector_store(text)
+
+    st.write("Vector store created successfully!")
+
+    query = st.text_input("Enter your query:")
+    if query:
+        st.write("Retrieving relevant context from the document...")
+        retriever = vector_store.as_retriever()
+        retriever.search_kwargs["k"] = 3  # Retrieve top 3 matches
+
+        # Define a prompt template to guide LLM response generation
+        prompt_template = PromptTemplate(
+            template="""
+            Use the following context to answer the question:
+            
+            {context}
+            
+            Question: {question}
+            Answer:""",
+            input_variables=["context", "question"]
+        )
+
+        # Create a RetrievalQA chain
+        qa_chain = RetrievalQA.from_chain_type(
+            retriever=retriever,
+            llm=llm,
+            chain_type="stuff",  # Use the default chain type
+            return_source_documents=True  # Optional
+        )
+
+        # Run the query through the QA chain
+        result = qa_chain.run(query)
+        st.write("Answer:", result)
+else:
+    st.error("Failed to extract content from the document.")