Update app.py

debugging file uploader

app.py

@@ -19,7 +19,7 @@ st.markdown("<h3 style='text-align: left; color:#F63366; font-size:18px;'><b>Wha
 st.write("Extractive question answering is a Natural Language Processing task where text is provided for a model so that the model can refer to it and make predictions about where the answer to a question is.")
 
 # store the model in cache resources to enhance efficiency (ref: https://docs.streamlit.io/library/advanced-features/caching)
-@st.cache_resource(show_spinner=True)
+@st.cache_resource(show_spinner=False)
 def question_model():
     # call my model for question answering
     model_name = "kxx-kkk/FYP_ms_squad"
@@ -40,7 +40,7 @@ def question_answering(context, question):
         container = st.container(border=True)
         container.write("<h5><b>Answer:</b></h5>"+answer+"<p><small>(F1 score: "+answer_score+")</small></p><br>", unsafe_allow_html=True)
 
-@st.cache_data(show_spinner=True)
+@st.cache_data(show_spinner=False)
 def extract_text(file_path):
     text = ""
     image_text = ""
@@ -56,17 +56,10 @@ def extract_text(file_path):
 
         images = convert_from_path(file_path)  # Convert PDF pages to images
         for i, image in enumerate(images):
-            # st.write(f"Page {i + 1}")
             image_text += pytesseract.image_to_string(image)
             
-        # st.write("text")
-        # st.write(text)
-        # st.write("image_text")
-        # st.write(image_text)
-
-        text = text + image_text
-        # st.write("plus")
-        # st.write(text)  # Display the extracted text from the image
+        # text = text + image_text
+        text = image_text
     return text
 
 
@@ -118,19 +111,13 @@ with tab2:
 
     # transfer file to context and allow ask question, then perform question answering 
     if uploaded_file is not None:
-        # if uploaded_file.type is "txt":
-        #     st.write("success txt")
-        #     raw_text = str(uploaded_file.read(),"utf-8")            
-        # elif uploaded_file.type is "pdf":
-        st.write("success pdf")
         with tempfile.NamedTemporaryFile(delete=False) as temp_file:
-            st.write("success pdf 2")
             temp_file.write(uploaded_file.read())  # Save uploaded file to a temporary path                  
             raw_text = extract_text(temp_file.name)
-            st.session_state.contextInput2 = str(raw_text)
+            st.session_state.contextInput2 = raw_text
         
         context2 = st.session_state.contextInput2
-        
+
         question2 = st.text_input(label="Enter your question",value=question2, key="questionInput2")
         context2 = st.text_area("Your essay context: ", value=context2, height=330, key="contextInput2")