Update app.py

app.py

@@ -33,61 +33,55 @@ from PyPDF2 import PdfReader
 from templates import bot_template, css, user_template
 from xml.etree import ElementTree as ET
 
-
-import streamlit as st
-from datasets import load_dataset
-
-# 📚 Load USMLE Step 1 dataset
-dataset = load_dataset("augtoma/usmle_step_1")['test']  # Using 'test' split
-
-# 🎉 Streamlit App 🎉
-st.title("USMLE Step 1 Dataset Viewer")
-
-# 🔍 Check if dataset is empty
-if len(dataset) == 0:
-    st.write("😢 The dataset is empty.")
-else:
-    st.write("""
-    🔍 Use the search box to filter questions or use the grid to scroll through the dataset.
-    """)
-
-    # 👩‍🔬 Search Box
-    search_term = st.text_input("Search for a specific question:", "")
-    # 🎛 Pagination
-    records_per_page = 100
-    num_records = len(dataset)
-    num_pages = max(int(num_records / records_per_page), 1)
-    
-    # Skip generating the slider if num_pages is 1 (i.e., all records fit in one page)
-    if num_pages > 1:
-        page_number = st.select_slider("Select page:", options=list(range(1, num_pages + 1)))
+def add_Med_Licensing_Exam_Dataset():
+    import streamlit as st
+    from datasets import load_dataset
+    dataset = load_dataset("augtoma/usmle_step_1")['test']  # Using 'test' split
+    st.title("USMLE Step 1 Dataset Viewer")
+    if len(dataset) == 0:
+        st.write("😢 The dataset is empty.")
     else:
-        page_number = 1  # Only one page
+        st.write("""
+        🔍 Use the search box to filter questions or use the grid to scroll through the dataset.
+        """)
+    
+        # 👩‍🔬 Search Box
+        search_term = st.text_input("Search for a specific question:", "")
+        # 🎛 Pagination
+        records_per_page = 100
+        num_records = len(dataset)
+        num_pages = max(int(num_records / records_per_page), 1)
+        
+        # Skip generating the slider if num_pages is 1 (i.e., all records fit in one page)
+        if num_pages > 1:
+            page_number = st.select_slider("Select page:", options=list(range(1, num_pages + 1)))
+        else:
+            page_number = 1  # Only one page
+        
+        # 📊 Display Data
+        start_idx = (page_number - 1) * records_per_page
+        end_idx = start_idx + records_per_page
     
-    # 📊 Display Data
-    start_idx = (page_number - 1) * records_per_page
-    end_idx = start_idx + records_per_page
-
-    # 🧪 Apply the Search Filter
-    filtered_data = []
-    for record in dataset[start_idx:end_idx]:
-        if isinstance(record, dict) and 'text' in record and 'id' in record:
-            if search_term:
-                if search_term.lower() in record['text'].lower():
+        # 🧪 Apply the Search Filter
+        filtered_data = []
+        for record in dataset[start_idx:end_idx]:
+            if isinstance(record, dict) and 'text' in record and 'id' in record:
+                if search_term:
+                    if search_term.lower() in record['text'].lower():
+                        filtered_data.append(record)
+                else:
                     filtered_data.append(record)
-            else:
-                filtered_data.append(record)
-
-    # 🌐 Render the Grid
-    for record in filtered_data:
-        st.write(f"## Question ID: {record['id']}")
-        st.write(f"### Question:")
-        st.write(f"{record['text']}")
-        st.write(f"### Answer:")
-        st.write(f"{record['answer']}")
-        st.write("---")
-
-    st.write(f"😊 Total Records: {num_records} | 📄 Displaying {start_idx+1} to {min(end_idx, num_records)}")
+    
+        # 🌐 Render the Grid
+        for record in filtered_data:
+            st.write(f"## Question ID: {record['id']}")
+            st.write(f"### Question:")
+            st.write(f"{record['text']}")
+            st.write(f"### Answer:")
+            st.write(f"{record['answer']}")
+            st.write("---")
+    
+        st.write(f"😊 Total Records: {num_records} | 📄 Displaying {start_idx+1} to {min(end_idx, num_records)}")
 
 
 
@@ -157,6 +151,37 @@ def add_witty_humor_buttons():
         if col7[0].button("More Funny Rhymes 🎙️"):
             StreamLLMChatResponse(descriptions["More Funny Rhymes 🎙️"])
 
+def addDocumentHTML5(result):
+    documentHTML5='''
+    <!DOCTYPE html>
+    <html>
+    <head>
+        <title>Read It Aloud</title>
+        <script type="text/javascript">
+            function readAloud() {
+                const text = document.getElementById("textArea").value;
+                const speech = new SpeechSynthesisUtterance(text);
+                window.speechSynthesis.speak(speech);
+            }
+        </script>
+    </head>
+    <body>
+        <h1>🔊 Read It Aloud</h1>
+        <textarea id="textArea" rows="10" cols="80">
+    '''
+    documentHTML5 = documentHTML5 + result
+    documentHTML5 = documentHTML5 + '''
+        </textarea>
+        <br>
+        <button onclick="readAloud()">🔊 Read Aloud</button>
+    </body>
+    </html>
+    '''
+
+    import streamlit.components.v1 as components  # Import Streamlit
+    components.html(documentHTML5, width=1280, height=1024)
+    return result
+
 
 # 3. Stream Llama Response
 @st.cache_resource
@@ -196,36 +221,7 @@ def StreamLLMChatResponse(prompt):
                     
             except:
                 st.write('Stream llm issue')
-
-        documentHTML5='''
-        <!DOCTYPE html>
-        <html>
-        <head>
-            <title>Read It Aloud</title>
-            <script type="text/javascript">
-                function readAloud() {
-                    const text = document.getElementById("textArea").value;
-                    const speech = new SpeechSynthesisUtterance(text);
-                    window.speechSynthesis.speak(speech);
-                }
-            </script>
-        </head>
-        <body>
-            <h1>🔊 Read It Aloud</h1>
-            <textarea id="textArea" rows="10" cols="80">
-        '''
-        documentHTML5 = documentHTML5 + result
-        documentHTML5 = documentHTML5 + '''
-            </textarea>
-            <br>
-            <button onclick="readAloud()">🔊 Read Aloud</button>
-        </body>
-        </html>
-        '''
-
-        import streamlit.components.v1 as components  # Import Streamlit
-        components.html(documentHTML5, width=1280, height=1024)
-        return result
+        add_documentHTML5(result)
     except:
         st.write('Llama model is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).')
 
@@ -638,6 +634,8 @@ def main():
         filename = generate_filename(user_prompt, choice)
         create_file(filename, user_prompt, response, should_save)
         st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
+
+    # Compose a file sidebar of past encounters
     all_files = glob.glob("*.*")
     all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 20]  # exclude files with short names
     all_files.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True)  # sort by file type and file name in descending order
@@ -657,6 +655,7 @@ def main():
                 with open(file, 'r') as f:
                     file_contents = f.read()
                     next_action='md'
+                    addDocumentHTML5(file_contents)
         with col2:
             st.markdown(get_table_download_link(file), unsafe_allow_html=True)
         with col3:
@@ -664,11 +663,13 @@ def main():
                 with open(file, 'r') as f:
                     file_contents = f.read()
                     next_action='open'
+                    addDocumentHTML5(file_contents)
         with col4:
             if st.button("🔍", key="read_"+file):  # search emoji button
                 with open(file, 'r') as f:
                     file_contents = f.read()
                     next_action='search'
+                    addDocumentHTML5(file_contents)
         with col5:
             if st.button("🗑", key="delete_"+file):
                 os.remove(file)