u

app.py

@@ -1,39 +1,39 @@
 import streamlit as st
 import pandas as pd
-from fuzzywuzzy import process
-
 
+# 假设你的数据存储在一个CSV文件中，我们将从这个文件中读取数据
 def load_data():
     return pd.read_csv("benchmark_data.csv")
 
-
-def fuzzy_search(data, query, column):
-    if query:  
-        choices = data[column].unique() 
-        results = process.extract(query, choices, limit=10)  
-        selected = [res[0] for res in results]
-        return data[data[column].isin(selected)]  
+# 不区分大小写的搜索功能
+def case_insensitive_search(data, query, column):
+    if query:  # 如果用户输入了搜索词
+        return data[data[column].str.lower().str.contains(query.lower())]
     return data
 
-
+# 页面布局和功能
 def main():
     st.title("Multihop-RAG Benchmark Space")
 
     data = load_data()
 
+    # 添加搜索框
     st.sidebar.header("Search Options")
     framework_query = st.sidebar.text_input("Search by Framework")
     model_query = st.sidebar.text_input("Search by Model")
 
+    # 根据输入执行搜索
     if framework_query:
-        data = fuzzy_search(data, framework_query, 'framework')
+        data = case_insensitive_search(data, framework_query, 'framework')
     if model_query:
-        data = fuzzy_search(data, model_query, 'model')
+        data = case_insensitive_search(data, model_query, 'model')
 
+    # 显示数据
     st.header("Benchmark Results")
     st.write("Displaying results for MRR@10 and Hit@10 across different frameworks, models, and chunk sizes.")
     st.dataframe(data)
 
+    # 数据统计和图表
     if st.sidebar.checkbox("Show Metrics Distribution"):
         st.subheader("Metrics Distribution")
         st.bar_chart(data[['MRR@10', 'Hit@10']])