Update app.py

app.py

@@ -6,7 +6,7 @@ from haystack.document_stores import InMemoryDocumentStore
 from haystack import Document, Pipeline
 from haystack.nodes import BM25Retriever
 from pprint import pprint
-import chainlit as cl
+import streamlit as st
 import logging
 from dotenv import load_dotenv
 load_dotenv()
@@ -25,7 +25,7 @@ def extract_text_from_pdf(pdf_path):
     return text
 
 # Extract text from the PDF file
-pdf_file_path = "Data/MR. MPROFY.pdf" 
+pdf_file_path = "Data/MR. MPROFY.pdf"
 pdf_text = extract_text_from_pdf(pdf_file_path)
 if not pdf_text:
     raise ValueError("No text extracted from PDF.")
@@ -70,14 +70,16 @@ rag_pipeline = Pipeline()
 rag_pipeline.add_node(component=retriever, name="retriever", inputs=["Query"])
 rag_pipeline.add_node(component=prompt_node, name="prompt_node", inputs=["retriever"])
 
-# Chainlit Function for Handling Messages
-@cl.on_message
-async def handle_message(message: cl.Message):
-    query_text = message.content  # Extract the text content from the message
-    response = await cl.make_async(rag_pipeline.run)(query=query_text)
-    answer = response["answers"][0].answer if response["answers"] else "No answer found."
-    await cl.Message(author="Mprofier", content=answer).send()
+# Streamlit Function for Handling Input and Displaying Output
+def run_streamlit_app():
+    st.title("Mprofier - AI Assistant")
+    query_text = st.text_input("Enter your question:")
+    
+    if st.button("Get Answer"):
+        response = rag_pipeline.run(query=query_text)
+        answer = response["answers"][0].answer if response["answers"] else "No answer found."
+        st.write(answer)
 
-# Start the Chainlit application
+# Start the Streamlit application
 if __name__ == "__main__":
-    cl.run()
+    run_streamlit_app()