Spaces:
Sleeping
Sleeping
File size: 1,569 Bytes
cfd3735 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
from typing import List
from langchain.document_loaders.arxiv import ArxivLoader
from langchain.schema import Document
def assert_docs(docs: List[Document]) -> None:
for doc in docs:
assert doc.page_content
assert doc.metadata
assert set(doc.metadata) == {"Published", "Title", "Authors", "Summary"}
def test_load_success() -> None:
"""Test that returns one document"""
loader = ArxivLoader(query="1605.08386", load_max_docs=2)
docs = loader.load()
assert len(docs) == 1
print(docs[0].metadata)
print(docs[0].page_content)
assert_docs(docs)
def test_load_returns_no_result() -> None:
"""Test that returns no docs"""
loader = ArxivLoader(query="1605.08386WWW", load_max_docs=2)
docs = loader.load()
assert len(docs) == 0
def test_load_returns_limited_docs() -> None:
"""Test that returns several docs"""
expected_docs = 2
loader = ArxivLoader(query="ChatGPT", load_max_docs=expected_docs)
docs = loader.load()
assert len(docs) == expected_docs
assert_docs(docs)
def test_load_returns_full_set_of_metadata() -> None:
"""Test that returns several docs"""
loader = ArxivLoader(query="ChatGPT", load_max_docs=1, load_all_available_meta=True)
docs = loader.load()
assert len(docs) == 1
for doc in docs:
assert doc.page_content
assert doc.metadata
assert set(doc.metadata).issuperset(
{"Published", "Title", "Authors", "Summary"}
)
print(doc.metadata)
assert len(set(doc.metadata)) > 4
|