Update app.py

app.py

@@ -50,22 +50,22 @@ def get_conversational_chain():
     return chain
 
 def user_input(user_question, api_key):
-    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)
+    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)
 
 def main():
     st.set_page_config(layout="wide")
@@ -83,6 +83,7 @@ def main():
 
     # Initialize raw_text as None initially
     raw_text = None
+    submitted = False
 
     if pdf_docs:
         with col1:
@@ -92,8 +93,9 @@ 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 and st.success("Processing Complete"):
+    if submitted:
         with col1:
             user_question = st.text_input("Ask a question from the Docs")
             if user_question: