Update app.py

app.py

@@ -1,15 +1,36 @@
 import time
 import streamlit as st
 import pandas as pd
-from docx import Document
+import os
+from dotenv import load_dotenv
+import search  # Import the search module
 from reportlab.lib.pagesizes import letter
 from reportlab.pdfgen import canvas
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import search  # Import the search module
+from docx import Document
 
-# Initialize the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", trust_remote_code=True)
+load_dotenv()
+
+st.set_page_config(
+        page_title="DocGPT GT",
+        page_icon="speech_balloon",
+        layout="wide",
+    )
+
+hide_streamlit_style = """
+            <style>
+            #MainMenu {visibility: hidden;}
+            footer {visibility: hidden;}
+            footer:after {
+	content:'2023'; 
+	visibility: visible;
+	display: block;
+	position: relative;
+	padding: 5px;
+	top: 2px;
+}
+            </style>
+            """
+st.markdown(hide_streamlit_style, unsafe_allow_html=True)
 
 def save_as_pdf(conversation):
     pdf_filename = "conversation.pdf"
@@ -68,7 +89,7 @@ def main():
     if uploaded_files:
         df = pd.DataFrame(columns=["page_num", "paragraph_num", "content", "tokens"])
         for uploaded_file in uploaded_files:
-            paragraphs = search.read_pdf(uploaded_file) if uploaded_file.type == "application/pdf" else search.read_docx(uploaded_file)
+            paragraphs = search.read_pdf_pdfminer(uploaded_file) if uploaded_file.type == "application/pdf" else search.read_docx(uploaded_file)
             temp_df = pd.DataFrame(
                 [(p.page_num, p.paragraph_num, p.content, search.count_tokens(p.content))
                 for p in paragraphs],
@@ -82,7 +103,7 @@ def main():
         answer = ""
         if question != st.session_state.get("last_question", ""):
             st.text("Searching...")
-            answer = search.answer_query_with_context(question, df, tokenizer, model)
+            answer = search.answer_query_with_context(question, df)
             st.session_state["interactions"].append((question, answer))
             st.write(answer)