Added LLM support

README.md

@@ -4,10 +4,10 @@ emoji: ✉️
 colorFrom: purple
 colorTo: yellow
 sdk: streamlit
-sdk_version: 1.10.0
+sdk_version: 1.25.0
+python_version: 3.9
 app_file: app.py
 pinned: false
-duplicated_from: loxzdigital/Model-CC-Space
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -7,6 +7,8 @@ from io import StringIO
 import boto3
 from urlextract import URLExtract
 import time
+from utils import * 
+
 # from joblib import dump, load
 
 import joblib
@@ -14,15 +16,18 @@ import joblib
 from bokeh.models.widgets import Div
 
 import email
+import os
 #from ipyfilechooser import FileChooser
 
 #from IPython.display import display
-from io import BytesIO
 from bs4 import BeautifulSoup
 import matplotlib.pyplot as plt
 import numpy as np
 import timeit
+import shutil
 
+CURRENT_THEME = "blue"
+IS_DARK_THEME = True
 
 def table_data():
     # creating table data
@@ -179,7 +184,7 @@ def add_bg_from_url():
         f"""
          <style>
          .stApp {{
-             background-image: linear-gradient(#45eff5,#1C8D99);
+             background-image: linear-gradient(135deg,#061c2c,#084e69 35%,#3e7e89);
              background-attachment: fixed;
              background-size: cover
             
@@ -262,6 +267,10 @@ target_variables = [
 uploaded_file = st.file_uploader(
     "Please upload your email (In HTML Format)", type=["html"])
 
+def save_file(uploaded_file):
+    with open(os.path.join("./",uploaded_file.name),"wb") as f:
+        f.write(uploaded_file.getbuffer())
+
 if uploaded_file is None:
     # upload_img = PIL.Image.open(uploaded_file)
     upload_img = None
@@ -298,7 +307,6 @@ st.markdown("""---""")
 def get_files_from_aws(bucket, prefix):
     """
         get files from aws s3 bucket
-
     bucket (STRING): bucket name
     prefix (STRING): file location in s3 bucket
     """
@@ -317,12 +325,17 @@ def get_files_from_aws(bucket, prefix):
 
 # st.info([industry,campaign,target,char_reco_preference])
 
+act=st.button('Generate Predictions')
+if st.session_state.get('button') != True:
+    st.session_state['button'] = act
 
-if st.button('Generate Predictions'):
+# if act:
+if st.session_state.get('button') == True:
     start_time = time.time()
     if uploaded_file is None:
         st.error('Please upload a email (HTML format)')
     else:
+        save_file(uploaded_file)
         placeholder = st.empty()
         placeholder.text('Loading Data')
 
@@ -372,7 +385,7 @@ if st.button('Generate Predictions'):
             print(
                 "Sorry, Current model couldn't provide predictions on the target variable you selected.")
         else:
-            st.markdown('#### Current Character Count in Your Email is: <span style="color:blue">{}</span>'.format(
+            st.markdown('##### Current Character Count in Your Email is: <span style="color:yellow">{}</span>'.format(
                 character_cnt), unsafe_allow_html=True)
             # st.info('The model predicts that it achieves a {} of {}%'.format(target, str(round(output_rate*100,2))))
             if target == 'conversion_rate':
@@ -380,7 +393,7 @@ if st.button('Generate Predictions'):
             else:
                 target_vis = 'Open_Rate'
                 
-            st.markdown('#### The model predicts that it achieves a <span style="color:blue">{}</span> of <span style="color:blue">{}</span>%'.format(
+            st.markdown('##### The model predicts that it achieves a <span style="color:yellow">{}</span> of <span style="color:yellow">{}</span>%'.format(
                 target_vis, str(round(output_rate*100, 3))), unsafe_allow_html=True)
             selected_industry_code = industry_code_dict.get(industry)
 
@@ -432,10 +445,10 @@ if st.button('Generate Predictions'):
             if selected_variable == "Click_Through_Rate":
                 selected_variable = "Conversion_Rate"
 
-            st.markdown('#### To get higher, <span style="color:blue">{}</span>, the model recommends the following options:'.format(
+            st.markdown('##### To get higher, <span style="color:yellow">{}</span>, the model recommends the following options:'.format(
                 selected_variable), unsafe_allow_html=True)
             if len(df_reco_opt_rank) == 0:
-                st.markdown('#### You ve already achieved the highest, <span style="color:blue">{}</span>, with the current character count!'.format(
+                st.markdown('##### You ve already achieved the highest, <span style="color:yellow">{}</span>, with the current character count!'.format(
                     selected_variable), unsafe_allow_html=True)
             else:
                 #for _, row in df_reco_opt_rank.iterrows():
@@ -453,8 +466,13 @@ if st.button('Generate Predictions'):
                     selected_variable_number = row[3]
                     chars.append(int(Character_Count))
                     sel_var_values.append(round(selected_variable_number, 3)*100)
-                    st.write(f"·Number of Characters: {int(Character_Count)}, Target Rate: {round(round(selected_variable_number, 3)*100, 3)}", "%")
+                    # st.write(f"·Number of Characters: {int(Character_Count)}, Target Rate: {round(round(selected_variable_number, 3)*100, 3)}", "%")
                 st.write("\n")
+                df_modelpred=pd.DataFrame(list(zip(chars, sel_var_values)), columns=["Number of Characters", "Target_Rate"])
+                # st.checkbox("Use container width", value=False, key="use_container_width")
+                # st.dataframe(df_modelpred.style.highlight_max(axis=0), use_container_width=st.session_state.use_container_width)
+                df_modelpred.sort_values(by='Target_Rate', ascending=False, inplace = True)
+                st.dataframe(df_modelpred)
 
                 if len(chars) > 1:
                     #fig = plt.figure()
@@ -465,7 +483,7 @@ if st.button('Generate Predictions'):
                     #ax.bar_label(bars)
 
                     ax.set_yticks(np.arange(len(chars)))
-                    ax.set_yticklabels(np.array(chars), fontsize=14)
+                    ax.set_yticklabels(tuple(chars), fontsize=14)
                     ax.set_title('Character Counts vs. Target Variable Rates', fontsize=18)
                     ax.set_ylabel('Character Counts', fontsize=16)
                     ax.set_xlabel('Target Rates %', fontsize=16)
@@ -481,12 +499,34 @@ if st.button('Generate Predictions'):
                     
                     st.plotly_chart(fig, use_container_width=True)
 
-                    st.write("\n")
+                    # st.write("\n")
+                    chars_out = dict(zip(chars, sel_var_values))
+                    sorted_chars_out = sorted(chars_out.items(), key=lambda x: x[1], reverse=True)
+            prefrence_variables=res=["charcter counts: "+str(x)+", Target Rate: "+str(y) for x,y in zip(chars,sel_var_values)]
+            preference = st.selectbox(
+                        'Please select your preferences',
+                        prefrence_variables,
+                        index=1
+                    )
+            if st.button('Generate AI Recommended Email'):
+                if(preference is None):
+                    st.error('Please upload a email (HTML format)')
+                else:
+                    ai_generated_email=generate_example_email_with_context(email_body, campaign, industry, target, sorted_chars_out, preference)
+                    st.markdown('##### Here is the recommended Generated Email for you:')
+                    st.markdown('{}:'.format(ai_generated_email),unsafe_allow_html=True)
+    # st.session_state['button'] = False
+        # preference= "character counts: "+str(573)+", Target Rate: "+str(37.2)
+        # ai_generated_email=generate_example_email_with_context(email_body, campaign, industry, target, sorted_chars_out, preference)
+        # print("ai_generated_email: ",ai_generated_email)
+        # st.markdown('##### Here is the recommended Generated Email for you:')
+        # st.markdown('####### {}'.format(ai_generated_email),unsafe_allow_html=True)
                     #st.write(np.array(chars))
-                chars_out = dict(zip(chars, sel_var_values))
-                sorted_chars_out = sorted(chars_out.items(), key=lambda x: x[1], reverse=True)
-                
 
-        placeholder.empty()
-        #st.write(time.time() - start_time)
 
+# chars_out = dict(zip(chars, sel_var_values))
+# sorted_chars_out = sorted(chars_out.items(), key=lambda x: x[1], reverse=True)
+
+
+# placeholder.empty()
+        #st.write(time.time() - start_time)

config.py

@@ -5,7 +5,7 @@ import os
 import argparse
 
 class Config(object): 
-    OPEN_API_KEY='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'
+    OPEN_API_KEY='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'
     OPENAI_MODEL_TYPE='text-davinci-003'
     OPENAI_MODEL_TEMP=0.3
     MODELCC_DATA_S3PATH='s3://emailcampaigntrainingdata/modelCC'

main_app.py

@@ -1,15 +0,0 @@
-import streamlit as st
-
-st.set_page_config(layout="wide")
-
-st.markdown(
-    """
-<style>
-body {
-    background-image: linear-gradient(#2e7bcf,#2e7bcf);
-    color: white;
-}
-</style>
-""",
-    unsafe_allow_html=True,
-)

requirements.txt

@@ -1,11 +1,18 @@
-bokeh==2.4.1
+# transformers
+# torch
+streamlit
+altair<5
+pickle5
+numpy
+pandas
+scikit-learn==0.24.1
+Cython==0.29.36
+bokeh==2.4.3
 joblib
 boto3
-pandas
 urlextract
-scikit-learn==0.24.1
 bs4
 matplotlib
-numpy
 plotly
-streamlit==1.21.0
+streamlit==1.25.0
+openai==0.8.0