Update app.py

app.py

@@ -7,7 +7,7 @@ import nest_asyncio
 import asyncio
 import uuid
 
-#torch.classes.__path__ = []
+
 
 # Setup for HTTP API Calls to Amplitude Analytics
 if 'device_id' not in st.session_state:
@@ -16,46 +16,52 @@ if 'device_id' not in st.session_state:
 if "feedback_key" not in st.session_state:
     st.session_state.feedback_key = 0
 
-async def main():
-    await launch_bot()
-
 if __name__ == "__main__":
-   st.set_page_config(page_title="Proa Capital Assistant", layout="wide")
-       # Load external CSS for custom styling
-   with open("style.css", "r") as f:
-       st.markdown(f"<style>{f.read()}</style>", unsafe_allow_html=True)
-   
-   st.markdown(
-       """
-        <h1>Welcome to the Proa Capital Assistant</h1>
+    # Ensure set_page_config is the first Streamlit command
+    st.set_page_config(page_title="Proa Capital Assistant", layout="centered")
+
+        # Load external CSS for custom styling
+    with open("style.css", "r") as f:
+        st.markdown(f"<style>{f.read()}</style>", unsafe_allow_html=True)
+
+    # Main UI layout
+    st.markdown(
+        """
+        <h1>Digital Bank</h1>
 
         <div class="icon-container">
             <!-- This yellowish box is the icon background -->
-            <div class="icon-box">💼</div>
-            <p class="icon-text">How may I help you?</p>
         </div>
 
         <h4>Add additional files here</h4>
-       """,
-       unsafe_allow_html=True
-   )
+        """,
+        unsafe_allow_html=True
+    )
 
-   customer_id = os.getenv("VECTARA_CUSTOMER_ID", "")
-   api_key = os.getenv("VECTARA_API_KEY", "")
-   corpus_id = os.getenv("VECTARA_CORPUS_ID", "")
-   corpus_key = os.getenv("VECTARA_CORPUS_KEY", "")
+    # Fetch credentials from environment variables
+    customer_id = os.getenv("VECTARA_CUSTOMER_ID", "")
+    api_key = os.getenv("VECTARA_API_KEY", "")
+    corpus_id = os.getenv("VECTARA_CORPUS_ID", "")
+    corpus_key = os.getenv("VECTARA_CORPUS_KEY", "")
 
     # File uploader with drag-and-drop text + limit note
-   uploaded_files = st.file_uploader(
-       "Drag and drop file here\nLimit 200MB per file",
-       type=["pdf", "docx", "xlsx"],
-       accept_multiple_files=True
-   )
-   # If credentials exist and files are uploaded, handle them
-   if uploaded_files and customer_id and api_key and corpus_id and corpus_key:
-       for file in uploaded_files:
+    uploaded_files = st.file_uploader(
+        "Drag and drop file here\nLimit 200MB per file",
+        type=["pdf", "docx", "xlsx"],
+        accept_multiple_files=True
+    )
+
+    # If credentials exist and files are uploaded, handle them
+    if uploaded_files and customer_id and api_key and corpus_id and corpus_key:
+        for file in uploaded_files:
             response = upload_file_to_vectara(file, customer_id, api_key, corpus_key)
             st.write(f"Uploaded {file.name}: {response}")
 
-   nest_asyncio.apply()
-   asyncio.run(main())
+    #if st.button("Run Queries"):
+    #    results = process_queries(customer_id, api_key, corpus_key)
+    #    for question, answer in results.items():
+    #        st.subheader(question)
+    #        st.write(answer)
+
+    nest_asyncio.apply()
+    asyncio.run(launch_bot())