Update app.py

app.py

@@ -1,13 +1,45 @@
 import streamlit as st
 from transformers import pipeline
 from TransformationQA_ZongqianLi.transformationqa import create_qa_database
+from numpy import linspace
+import jsonlines
+import json
 
 st.markdown("# 🎓 Auto-generating Question-Answering Datasets with Domain-Specific Knowledge for Language Models in Scientific Tasks", unsafe_allow_html=True)
 
+
+
+##########
 # Transformation Algorithm
+##########
 st.markdown('## 🖥️ QA Dataset Auto Generation', unsafe_allow_html=True)
 
+cde_lst = ["./CDE_properties.jsonl"]
+paper_lst = ["./reference_paper.json"]
+
+st.session_state['cde'] = "./CDE_properties.jsonl"
+st.session_state['cde'] = st.selectbox("ChemDataExtractor generated database path:", cde_lst)
+st.write("Example of the ChemDataExtractor generated database: ")
+with open(st.session_state['cde'], 'r') as file:
+    for line in file:
+        json_data = json.loads(line.strip())
+        json_string = json.dumps(json_data, indent=4)
+        st.text_area("", value=json_string, height=100)
+
+paper = st.selectbox("Paper collection path:", paper_lst)
+
+databases = []
+with open(args.databases_location,'r+', encoding = "utf-8") as f:
+    for item in jsonlines.Reader(f):
+        databases.append(item)
+
+        
+
+
+
+##########
 # Question Answering
+##########
 st.markdown('## 📖 Question Answering', unsafe_allow_html=True)
 st.markdown('### Select a model: ', unsafe_allow_html=True)