doczyai-pipelines/streamlit/interface_0.py

import streamlit as st
from streamlit_extras.add_vertical_space import add_vertical_space
import os
import streamlit as st
import pandas as pd
from io import StringIO
from datetime import datetime
import boto3
import util
import requests

doczy_pipeline = 'https://8ir4vi1ri4.execute-api.us-east-2.amazonaws.com/dev/'

REDIRECT_URI = 'https://doczy.aarete.com:8500'
user_list = ['maamseek@aarete.com', 'smahdavian@aarete.com', 'ahinge@aarete.com', 'akadam@aarete.com', 'pkatariya@aarete.com'
, 'piragavarapu@aarete.com', 'umistry@aarete.com', 'ahutchison@aarete.com', 'bgrunst@aarete.com', 'ddimeglio@aarete.com'
, 'vnair@aarete.com']
st.set_page_config(layout = "wide")
# # Sidebar contents
# with st.sidebar:
#     st.title("Doczy.AI ™")
#     st.markdown(
#         """
#     ## About
#     This app extracts data from contracts
 
#     """
#     )
#     add_vertical_space(15)
#     # st.write("Doczy")

try:
    util.setup_page(REDIRECT_URI)
    _,c1= st.columns([5,1])
    c1.write(f"User: **{st.session_state.user_info['displayName']}**")
    user_mail = st.session_state.user_info['mail']
except:
    user_mail = 'maamseek@aarete.com'

if user_mail in user_list: 

    s3_client = boto3.client('s3',
        region_name="us-east-1",
    )
    objects = s3_client.list_objects_v2(Bucket='doczy-dev-infra-textract'
        , Prefix="batches/batch_1/", Delimiter='/')

    folder_list = []
    for prefix in objects['CommonPrefixes']:
        folder_list.append(prefix['Prefix'][:-1].split('/')[-1])

    # # to be deleted later
    # folder_list = ['Delaware First Health, Inc.', 'Community Health Choice, Inc','CareSource Network Partners LLC',
    #     'HealthNet of Cali', 'Oklahoma Complete Health, Inc', 'HealthFirst', 'Molina Healthcare of TX', 'AvMed', 'Arizona Care1st',
    #     'WellCare New Jersey']

    client_row = st.columns([0.1, 0.8])
    with client_row[0]:
        st.write("**Client Name**")
    with client_row[1]:
        client = st.selectbox('Client Name',(folder_list), label_visibility = "collapsed")

    # # to be deleted later
    # client = 'textract-receiver-processed-file'

    folder_objects = s3_client.list_objects_v2(Bucket='doczy-dev-infra-textract'
        , Prefix="batches/batch_1/"+client+"/", Delimiter='/')      

    folder_list_2 = []
    for prefix in folder_objects['CommonPrefixes']:
        folder_list_2.append(prefix['Prefix'][:-1].split('/')[-1])

    path_row = st.columns([0.1, 0.8])
    with path_row[0]:
        st.write("**Path to folder**")
    with path_row[1]:
        Directory = st.selectbox('**Path to folder**', folder_list_2, label_visibility = "collapsed")

    add_vertical_space(1)

    df = pd.DataFrame(columns=['Contract Name','Unique Key','Pricing Before Carveouts'
        , 'Contract Related', 'Provider', 'Timeline', 'Carveout Indicator', 'Carveout Methodology'])
    file_list = []
    file_objects = s3_client.list_objects_v2(Bucket='doczy-dev-infra-textract'
        , Prefix="batches/batch_1/"+client+"/"+Directory+"/", Delimiter='/')

    if st.button("Create Batch"):
        for obj in file_objects.get('Contents',[]):
            if not obj['Key'].endswith('/'):
                file_list.append(obj['Key'].split('/')[-1])

        df['Contract Name'] = file_list

    add_vertical_space(1)

    @st.cache_data 
    def convert_df(df):
       return df.to_csv(index=False).encode('utf-8')

    csv = convert_df(df)

    df = df.reset_index()  # make sure indexes pair with number of rows

    # contract_list = []
    # for index, row in df.iterrows():
    #     group_list = []
    #     if row['Unique Key']:
    #         group_list.append('Unique Key')
    #     if row['Pricing Before Carveouts']:
    #         group_list.append('Pricing Before Carveouts')
    #     if row['Contract Related']:
    #         group_list.append('Contract Related')
    #     if row['Provider']:
    #         group_list.append('Provider')
    #     if row['Timeline']:
    #         group_list.append('Timeline')
    #     if row['Carveout Indicator']:
    #         group_list.append('Carveout Indicator')
    #     if row['Carveout Methodology']:
    #         group_list.append('Carveout Methodology')
    #     entry_dict = {
    #         "contract_name": row['Contract Name'],
    #         "groups": group_list,
    #         "contract_source_path": "batches/batch_1/"+client+"/"+row['Contract Name']
    #     }
    #     contract_list.append(entry_dict)
    contract_list = list(df['Contract Name'])

    myobj = {
      "s3_bucket": 'doczy-dev-infra-textract',
      "batch_id": "1",
      "client_name": client,
      "username": user_mail,
      "contract_list": contract_list
    }

    buttons = st.columns([0.8, 0.2])
    with buttons[0]:
        st.download_button("Download Table", csv, "file.csv", "text/csv", key='download-csv')
    with buttons[1]:
        if st.button("Upload to DB"):
            response = requests.post(doczy_pipeline, json = myobj)
            if response.status_code >= 200 and response.status_code < 300:
                st.write("Success")
            else:
                st.write("Failed")
            # st.write(response.text)



else:
    st.write("Access Denied")