doczyai-pipelines/streamlit/interface_0.py

import json
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
from sf_conn import get_secret, save_to_sf
from io import StringIO, BytesIO
from sf_conn import get_client_names, insert_upload_logs

create_batch_url = 'https://lfksus2t62.execute-api.us-east-2.amazonaws.com/dev/create-batch'

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', 'kminhas@aarete.com', 'fmohiuddin@aarete.com', 'slitewka@aarete.com', 'qdoest@aarete.com', 'bkoryga@aarete.com', 'bcielecki@aarete.com', 'mszymanski@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")

_,c1= st.columns([5,1])
try:
    util.setup_page(REDIRECT_URI)
except:
    st.write("SSO Failed")
    st.session_state['user_info'] = {'mail': 'maamseek@aarete.com', 'displayName': 'Mayank Aamseek'}
try:
    c1.write(f"User: **{st.session_state.user_info['displayName']}**")
    user_mail = st.session_state.user_info['mail']
except KeyError as e:
    st.write("Session Expired.")
    st.stop()

if user_mail in user_list: 

    s3_client = boto3.client('s3',
        region_name="us-east-2",
    )

    client_list = ['doczy-ai-client-1', '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']
    
    # This is the list of client fetched from Snowflake 
    # TODO: Need to update the streamlit code to use the client names from this list
    # And use the s3 paths to save the objects for the respective client
    client_list, s3_paths = get_client_names()
    client_s3_paths = dict(zip(client_list, s3_paths))

    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',(client_list), label_visibility = "collapsed")

    client = client_s3_paths.get(client)
    # # to be deleted when buckets for different clients are ready; below line is added only for testing the corresponding DAG
    client = 'doczy-ai-client-1'

    file_row = st.columns([0.1, 0.8])
    with file_row[0]:
        st.write("**Upload Files**")
    with file_row[1]:
        file_list = st.file_uploader("Upload", type=None, accept_multiple_files=True, label_visibility = "collapsed")

    add_vertical_space(2)
    df = pd.DataFrame(columns=['Contract Name'])
    df['Contract Name'] = file_list
    file_names = []
    buttons = st.columns([0.4, 0.4, 0.2])
    with buttons[1]:
        if st.button("Create Batch"):

            myobj = { "client-bucket-name": client }
            response = requests.post(create_batch_url, json = myobj)
            if response.status_code >= 200 and response.status_code < 300:
                try:
                    batch_id = json.loads(json.loads(response.text)['body'])['batch_id']
                    landing_zone = json.loads(json.loads(response.text)['body'])['landing_zone']
                except:
                    st.write(myobj)
                    st.write(response.text)
                    batch_id = 'failed_cases'
                    landing_zone = 'contracts_landing_zone'
            else:
                st.write("Failed")
            for uploaded_file in file_list:
                stringio = BytesIO(uploaded_file.getvalue())
                stringio.seek(0)
                # s3_client.put_object(Bucket='doczy-dev-infra-raw-data-ingestion', Body=stringio.getvalue(), Key=
                #     'config_interface/'+str(uploaded_file.name))
                s3_client.put_object(Bucket=client, Body=stringio.getvalue(), Key=
                    batch_id+'/'+landing_zone+'/'+str(uploaded_file.name))
                
                # TODO: Test this insert function with snowflake 
                upload_log = insert_upload_logs(batch_id, client, str(uploaded_file.name), datetime.now().strftime("%Y-%m-%d %H:%M:%S"), user_mail)
                st.write(upload_log)
                
                file_names.append(str(uploaded_file.name))
            st.write(f"{batch_id} created")
            st.write(f"Files uploaded to s3://{client}/{batch_id}/{landing_zone}")


    # @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")