From 8c762424281f162c31f7efd3005d4dd88a02c663 Mon Sep 17 00:00:00 2001
From: "AARETE\\agupta" <agupta@aarete.com>
Date: Tue, 4 Jun 2024 12:57:14 -0500
Subject: [PATCH] Made changes for the PDF viewer to be able to pull the bytes
 from the S3 Bucket and display it.

---
 streamlit/interface_2.py             | 74 ++++++++++++++++++++++------
 streamlit/local/local_interface_2.py |  2 +-
 2 files changed, 59 insertions(+), 17 deletions(-)

diff --git a/streamlit/interface_2.py b/streamlit/interface_2.py
index ed8c494..824509a 100644
--- a/streamlit/interface_2.py
+++ b/streamlit/interface_2.py
@@ -10,6 +10,7 @@ from langchain.chains import RetrievalQA
 
 import streamlit as st
 from streamlit_extras.add_vertical_space import add_vertical_space
+from streamlit_pdf_viewer import pdf_viewer     # needs to be installed on the server
 import os
 import pandas as pd
 import numpy as np
@@ -18,24 +19,26 @@ import anthropic
 from pydantic import BaseModel
 from typing import List
 import re
+import base64
 from sf_conn import get_snowflake_conn
+import io
 
 REDIRECT_URI = 'https://doczydev.aarete.com:8502'
 user_list = USER_LIST
 
 st.set_page_config(layout = "wide")
 # Sidebar contents
-with st.sidebar:
-    st.title("Doczy.AI ™")
-    st.markdown(
-        """
-    ## About
-    This app extracts data from contracts
+# with st.sidebar:
+#     st.title("Doczy.AI ™")
+#     st.markdown(
+#         """
+#     ## About
+#     This app extracts data from contracts
  
-    """
-    )
-    add_vertical_space(15)
-    # st.write("Doczy")
+#     """
+#     )
+#     add_vertical_space(15)
+#     # st.write("Doczy")
 
 _,c1= st.columns([5,1])
 try:
@@ -91,13 +94,11 @@ for obj in objects['Contents']:
 
 contract_list = sorted(file_list)
 
-
-
 file_row = st.columns([0.2, 0.7, 0.1])
 with file_row[0]:
     st.write("**Contract Name**")
 with file_row[1]:
-    file_name = st.selectbox('Select a file', contract_list + ['All'], label_visibility = "collapsed")
+    file_name = st.selectbox('Select a file', ['All'] + contract_list, label_visibility = "collapsed", index= None) # MODIFIED - Append 'All' in the front instead of at the end
 
 field_row = st.columns([0.2, 0.7, 0.1])
 with field_row[0]:
@@ -107,7 +108,7 @@ with field_row[1]:
         , 'Pricing Before Carveouts - II', 'Carveout Indicator, Code Type and Code #s - I'
         , 'Carveout Indicator, Code Type and Code #s - II', 'Carveout Indicator, Code Type and Code #s - III'
         , 'Optimize Carving Indic.', 'Carveout Method - I', 'Carveout Method - II', 'Provider'
-        , 'Timeline'), label_visibility = "collapsed")
+        , 'Timeline'), label_visibility = "collapsed", index = None)
 
 if field_group == 'Unique Key':
     fields = fields[fields['PRIORITY'] == 'A']
@@ -151,10 +152,51 @@ if st.button("Show Results"):
     df2 = pd.DataFrame.from_records(iter(cur), columns=[x[0] for x in cur.description])
 
     # get this dataframe from snowflake table
-    # df2 = pd.DataFrame(columns=['Contract Name','Field Name', 'SF_DB_COL_NAME', 'Snippet','Page Number'
-        # , 'Field Extracted Value', 'Actual Value','Imputed Value'])
+    df2 = pd.DataFrame(columns=['Contract Name','Field Name', 'SF_DB_COL_NAME', 'Snippet','Page Number'
+        , 'Field Extracted Value', 'Actual Value','Imputed Value'])
     df2.to_csv('temp2.csv', index=False)
 
+if st.button("Show PDF"):
+    if file_name == None or file_name == "All":
+        st.error("Choose one specific file.")
+    else:
+        with st.sidebar:
+            st.markdown(
+                """
+                <style>
+                    section[data-testid="stSidebar"] {
+                        width: 550px !important; # Set the width to your desired value
+                    }
+                </style>
+                """,
+                unsafe_allow_html=True,
+            )
+            s3_client.Object(bucket,file_name)
+            data=obj.get()['Body'].read()
+            pdf_viewer(io.BytesIO(data), width=1500)
+
+# if st.button("Show PDF"):
+#     if file_name == None or file_name == "All":
+#         st.error("Choose one specific file.")
+#     else:
+#         with st.sidebar:
+#             with open(file_name, "rb") as f:
+#                 base64_pdf = base64.b64encode(f.read()).decode('utf-8')
+#             # Embedding PDF in HTML
+#             pdf_display = F'<iframe src="data:application/pdf;base64,{base64_pdf}" width="500" height="1000" type="application/pdf"></iframe>'
+#             # Displaying File
+#             st.markdown(
+#                 """
+#                 <style>
+#                     section[data-testid="stSidebar"] {
+#                         width: 600px !important; # Set the width to your desired value
+#                     }
+#                 </style>
+#                 """,
+#                 unsafe_allow_html=True,
+#             )
+#             st.markdown(pdf_display, unsafe_allow_html=True)
+
 df2 = pd.read_csv('temp2.csv')
 df2['Imputed Value'] = ''
 edited_df = st.data_editor(df2)
diff --git a/streamlit/local/local_interface_2.py b/streamlit/local/local_interface_2.py
index 7e40615..18702f3 100644
--- a/streamlit/local/local_interface_2.py
+++ b/streamlit/local/local_interface_2.py
@@ -10,7 +10,7 @@ from langchain.chains import RetrievalQA
 
 import streamlit as st
 from streamlit_extras.add_vertical_space import add_vertical_space
-from streamlit_pdf_viewer import pdf_viewer
+from streamlit_pdf_viewer import pdf_viewer     # needs to be installed on the server
 import os
 import pandas as pd
 import numpy as np