Update app.py

app.py

@@ -1,3 +1,4 @@
+import random
 import gradio as gr
 from langchain_community.document_loaders import PyPDFLoader
 from langchain_text_splitters import RecursiveCharacterTextSplitter
@@ -13,6 +14,18 @@ from langchain_core.runnables import RunnablePassthrough
 # Initialize the FAISS vector store
 vector_store = None
 
+template = \
+"""Use the following pieces of context to answer the question at the end.
+If you don't know the answer, just say that you don't know, don't try to make up an answer.
+Always say "Thanks for asking!" at the end of the answer.
+
+{context}
+
+Question: {question}
+
+Answer:
+"""
+
 # Function to handle PDF upload and indexing
 def index_pdf(pdf):
     global vector_store
@@ -48,10 +61,28 @@ def chatbot_query(query):
     return response
 
 
+
+
 def generate_response(query, history, model, temperature, max_tokens, top_p, seed):
-    response = query + "\n"
-    response = response + model + "\n"
+    if vector_store is None:
+        return "Please upload and index a PDF at the Indexing tab."
 
+    if seed == 0:
+        seed = random.randint(1, 100000)
+        
+    llm = ChatGroq(groq_api_key=userdata.get('GROQ_API_KEY'), model=model)
+
+    custom_rag_prompt = PromptTemplate.from_template(template)
+    
+    rag_chain = (
+        {"context": retriever | format_docs, "question": RunnablePassthrough()}
+        | custom_rag_prompt
+        | llm
+        | StrOutputParser()
+    )
+
+    response = rag_chain.invoke(query)
+   
     return response