Update pages/3_Earnings_Semantic_Search_🔎_.py

pages/3_Earnings_Semantic_Search_🔎_.py

@@ -1,29 +1,62 @@
 import streamlit as st
 from functions import *
+from langchain.chains import QAGenerationChain
+import itertools
+
 
 st.set_page_config(page_title="Earnings Question/Answering", page_icon="🔎")
+
 st.sidebar.header("Semantic Search")
-st.markdown("## Earnings Semantic Search with LangChain, OpenAI & SBert")
 
-def gen_sentiment(text):
-    '''Generate sentiment of given text'''
-    return sent_pipe(text)[0]['label']
+st.markdown("## Earnings Semantic Search with LangChain, OpenAI & SBert")
 
-def gen_annotated_text(df):
-    '''Generate annotated text'''
+st.markdown(
+    """
+    <style>
     
-    tag_list=[]
-    for row in df.itertuples():
-        label = row[2]
-        text = row[1]
-        if label == 'Positive':
-            tag_list.append((text,label,'#8fce00'))
-        elif label == 'Negative':
-            tag_list.append((text,label,'#f44336'))
-        else:
-            tag_list.append((text,label,'#000000'))
+    #MainMenu {visibility: hidden;
+    # }
+        footer {visibility: hidden;
+        }
+        .css-card {
+            border-radius: 0px;
+            padding: 30px 10px 10px 10px;
+            background-color: black;
+            box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
+            margin-bottom: 10px;
+            font-family: "IBM Plex Sans", sans-serif;
+        }
+        
+        .card-tag {
+            border-radius: 0px;
+            padding: 1px 5px 1px 5px;
+            margin-bottom: 10px;
+            position: absolute;
+            left: 0px;
+            top: 0px;
+            font-size: 0.6rem;
+            font-family: "IBM Plex Sans", sans-serif;
+            color: white;
+            background-color: green;
+            }
+            
+        .css-zt5igj {left:0;
+        }
+        
+        span.css-10trblm {margin-left:0;
+        }
         
-    return tag_list
+        div.css-1kyxreq {margin-top: -40px;
+        }
+        
+       
+   
+        
+      
+    </style>
+    """,
+    unsafe_allow_html=True,
+)
 
 bi_enc_dict = {'mpnet-base-v2':"all-mpnet-base-v2",
               'instructor-base': 'hkunlp/instructor-base'}
@@ -33,8 +66,10 @@ search_input = st.text_input(
         
 sbert_model_name = st.sidebar.selectbox("Embedding Model", options=list(bi_enc_dict.keys()), key='sbox')
         
-chunk_size = st.sidebar.slider("Number of Chars per Chunk of Text",min_value=500,max_value=2000,value=1000)
-overlap_size = st.sidebar.slider("Number of Overlap Chars in Search Response",min_value=50,max_value=300,value=50)
+chunk_size = 1000
+overlap_size = 50
+
+
 
 try:
 
@@ -47,6 +82,24 @@ try:
 
             title = st.session_state['title']
 
+            earnings_text = ','.join(st.session_state['earnings_passages'])
+
+            st.session_state.eval_set = generate_eval(
+            earnings_text, 10, 3000)
+
+            # Display the question-answer pairs in the sidebar with smaller text
+            for i, qa_pair in enumerate(st.session_state.eval_set):
+                st.sidebar.markdown(
+                    f"""
+                    <div class="css-card">
+                    <span class="card-tag">Question {i + 1}</span>
+                        <p style="font-size: 12px;">{qa_pair['question']}</p>
+                        <p style="font-size: 12px;">{qa_pair['answer']}</p>
+                    </div>
+                    """,
+                    unsafe_allow_html=True,
+                )
+
             embedding_model = bi_enc_dict[sbert_model_name]
                             
             with st.spinner(