update

requirements.txt

@@ -1,3 +1,4 @@
 altair
 pandas
-streamlit
+streamlit
+datasets

src/streamlit_app.py

@@ -1,40 +1,23 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+from datasets import load_dataset
 
-"""
-# Welcome to Streamlit!
+st.set_page_config(page_title="Paper Explorer", layout="wide")
+st.title("📚 Paper Explorer")
 
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+# Streaming=True ensures we don't download the 1GB at once!
+dataset = load_dataset("pwc-archive/papers-with-abstracts", split="train", streaming=True)
 
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
+# Simple Pagination in Sidebar
+st.sidebar.header("Navigation")
+page_size = st.sidebar.slider("Papers per page", 5, 25, 10)
+offset = st.sidebar.number_input("Start at row", min_value=0, step=page_size)
 
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
+# Fetch rows
+papers = list(dataset.skip(offset).take(page_size))
 
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+# Display
+for p in papers:
+    with st.expander(f"Title: {p['title']}", expanded=True):
+        st.write(f"**Abstract:** {p['abstract'][:500]}...")
+        if p['arxiv_id']:
+            st.link_button("View on ArXiv", f"https://arxiv.org/abs/{p['arxiv_id']}")