app.py

import datetime
import json

from langchain_community.retrievers import BM25Retriever
from langchain_core.documents import Document
import streamlit as st


def load_docs_from_json(json_path):
    with open(json_path) as f:
        papers = json.load(f)

    docs = []
    for paper in papers:
        page_content = f"Title: {paper['title']}\n\nAbstract: {paper['abstract']}"
        doc = Document(
            page_content=page_content,
            metadata={
                'title': paper['title'],
                'link': paper['link'],
                'authors': paper['authors'],
                'submitter': paper['submitter'],
                'date': paper['date'],
                }
            )
        docs.append(doc)
    
    return docs


# init
json_path = "hf_daily_papers_2023-05-04_2024-06-27.json"
docs = load_docs_from_json(json_path)
retriever = BM25Retriever.from_documents(docs)
retriever.k = 10

dates = [datetime.datetime.strptime(doc.metadata['date'], '%Y-%m-%d') for doc in docs]
oldest_date = min(dates)
newest_date = max(dates)

# streamlit
st.title("HF Daily Papers Search")
st.markdown(f"Search papers from [HF daily papers](https://huggingface.co/papers).\n\nNmber of documents: {len(docs)}\n\nfrom {oldest_date.strftime('%Y-%m-%d')} to {newest_date.strftime('%Y-%m-%d')}")

user_query = st.text_input("Search anything...")
if st.button('→'):
    results = retriever.invoke(user_query)
    st.text(f"hit {len(results)} papers")

    for result in results:
        with st.expander(label=result.metadata['title'], expanded=False):
            for k in result.metadata:
                st.write(f"{k}: {result.metadata[k]}")
            st.divider()
            st.markdown(result.page_content)