docs/integrations/document_loaders/arxiv/

[giscus[bot]]

docs/integrations/document_loaders/arxiv/

arXiv is an open-access archive for 2 million scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics.

https://python.langchain.com/docs/integrations/document_loaders/arxiv/

[ranahasany2k]

from langchain_community.document_loaders import ArxivLoader

Correctly formatted title search

loader = ArxivLoader(query='ti:"Attention is all you need"', load_max_docs=1)
docs = loader.load() # Should now succeed

print(docs[0].metadata)
print(docs[0].page_content[:500]) # preview first 500 characters

I am getting this error which is weird.

HTTPError: Page request resulted in HTTP 400 (https://export.arxiv.org/api/query?search_query=ti%22Attention+is+all+you+need%22&id_list=&sortBy=relevance&sortOrder=descending&start=0&max_results=100)