Update app.py

app.py

@@ -50,22 +50,20 @@ def get_conversational_chain():
     return chain
 
 def user_input(user_question, api_key):
-    with st.spinner("Processing..."):
-        embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=api_key, model_name="sentence-transformers/all-MiniLM-l6-v2")
-        new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
-        docs = new_db.similarity_search(user_question)
-        chain = get_conversational_chain()
-        response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
-        st.success("Processed")
-        st.write("Replies:")
-        if isinstance(response["output_text"], str):
-            response_list = [response["output_text"]]
-        else:
-            response_list = response["output_text"]
-        for text in response_list:
-            st.write(text)
-            # Convert text to speech for each response
-            text_to_speech(text)
+    embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=api_key, model_name="sentence-transformers/all-MiniLM-l6-v2")
+    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+    docs = new_db.similarity_search(user_question)
+    chain = get_conversational_chain()
+    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+    st.write("Replies:")
+    if isinstance(response["output_text"], str):
+        response_list = [response["output_text"]]
+    else:
+        response_list = response["output_text"]
+    for text in response_list:
+        st.write(text)
+        # Convert text to speech for each response
+        text_to_speech(text)
 
 def main():
     st.set_page_config(layout="wide")
@@ -81,10 +79,6 @@ def main():
     # Main column for displaying extracted text and user interaction
     col1, col2 = st.columns([1, 2])
 
-    # Initialize raw_text as None initially
-    raw_text = None
-    submitted = False
-
     if pdf_docs:
         with col1:
             if st.button("Submit"):
@@ -93,25 +87,24 @@ def main():
                     text_chunks = get_text_chunks(raw_text)
                     get_vector_store(text_chunks, api_key)
                     st.success("Processing Complete")
-                    submitted = True
-            
-    if pdf_docs:
+    
+    # Check if PDF documents are uploaded and processing is complete
+    if pdf_docs and raw_text:
         with col1:
             user_question = st.text_input("Ask a question from the Docs")
             if user_question:
                 user_input(user_question, api_key)
-                raw_text = get_pdf_text(pdf_docs)
-                submitted = True
-    else:
-        with col1:
-            st.write("Please upload a document first to ask questions.")
 
-    # Display extracted text and handle user interaction if raw_text is not None
-    if raw_text is not None:
+    # Display extracted text if available
+    if raw_text:
         with col2:
             st.subheader("Extracted Text from PDF:")
             st.text(raw_text)
-            
+
+    # Show message if no PDF documents are uploaded
+    if not pdf_docs:
+        with col1:
+            st.write("Please upload a document first to proceed.")
 
 if __name__ == "__main__":
     main()