update

app.py

@@ -1,4 +1,42 @@
 import streamlit as st
+import pandas as pd
+from fuzzywuzzy import process
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+
+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)]  
+    return data
+
+
+def main():
+    st.title("Multihop-RAG Benchmark Space")
+
+    data = load_data()
+
+    st.sidebar.header("Search Options")
+    framework_query = st.sidebar.text_input("Search by Framework")
+    model_query = st.sidebar.text_input("Search by Model")
+
+    if framework_query:
+        data = fuzzy_search(data, framework_query, 'framework')
+    if model_query:
+        data = fuzzy_search(data, model_query, 'model')
+
+    st.header("Benchmark Results")
+    st.write("Displaying results for MRR@10 and Hit@10 across different frameworks, models, and chunk sizes.")
+    st.dataframe(data)
+
+    if st.sidebar.checkbox("Show Metrics Distribution"):
+        st.subheader("Metrics Distribution")
+        st.bar_chart(data[['MRR@10', 'Hit@10']])
+
+if __name__ == "__main__":
+    main()

benchmark_data.csv

@@ -0,0 +1,11 @@
+framework,model,chunk size,MRR@10,Hit@10
+Transformers,BERT-base,128,0.32,0.45
+Transformers,BERT-large,256,0.37,0.50
+Fairseq,ROBERTA-base,128,0.35,0.48
+Fairseq,ROBERTA-large,256,0.40,0.55
+HuggingFace,GPT-2,128,0.30,0.44
+HuggingFace,GPT-3,256,0.42,0.57
+TensorFlow,T5-small,128,0.31,0.46
+TensorFlow,T5-large,256,0.39,0.51
+PyTorch,BART-base,128,0.33,0.47
+PyTorch,BART-large,256,0.38,0.53