Update app.py

app.py

@@ -47,22 +47,24 @@ def index_pdf(pdf):
 
     return "PDF indexed successfully!"
 
-# Function to handle chatbot queries
-def chatbot_query(query):
-    if vector_store is None:
-        return "Please upload and index a PDF first."
+# # Function to handle chatbot queries
+# def chatbot_query(query):
+#     if vector_store is None:
+#         return "Please upload and index a PDF first."
     
-    # Create a retrieval-based QA chain
-    retriever = vector_store.as_retriever()
-    qa_chain = RetrievalQA(llm=OpenAI(), retriever=retriever)
+#     # Create a retrieval-based QA chain
+#     retriever = vector_store.as_retriever()
+#     qa_chain = RetrievalQA(llm=OpenAI(), retriever=retriever)
     
-    # Get the response from the QA chain
-    response = qa_chain.run(query)
+#     # Get the response from the QA chain
+#     response = qa_chain.run(query)
     
-    return response
-
+#     return response
 
 
+def format_docs(docs):
+    return "\n\n".join(doc.page_content for doc in docs)
+    
 
 def generate_response(query, history, model, temperature, max_tokens, top_p, seed):
     if vector_store is None:
@@ -70,11 +72,11 @@ def generate_response(query, history, model, temperature, max_tokens, top_p, see
 
     if seed == 0:
         seed = random.randint(1, 100000)
-        
-    llm = ChatGroq(groq_api_key=os.environ.get("GROQ_API_KEY"), model=model)
 
+    retriever = vector_store.as_retriever(search_type="similarity", search_kwargs={"k": 8})
+    llm = ChatGroq(groq_api_key=os.environ.get("GROQ_API_KEY"), model=model)
     custom_rag_prompt = PromptTemplate.from_template(template)
-    
+   
     rag_chain = (
         {"context": retriever | format_docs, "question": RunnablePassthrough()}
         | custom_rag_prompt