You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/community/tests/integration_tests/retrievers/test_wikipedia.py

65 lines
1.9 KiB
Python

"""Integration test for Wikipedia Retriever."""
from typing import List
import pytest
from langchain_core.documents import Document
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463) Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
10 months ago
from langchain_community.retrievers import WikipediaRetriever
@pytest.fixture
def retriever() -> WikipediaRetriever:
return WikipediaRetriever() # type: ignore[call-arg]
def assert_docs(docs: List[Document], all_meta: bool = False) -> None:
for doc in docs:
assert doc.page_content
assert doc.metadata
main_meta = {"title", "summary", "source"}
assert set(doc.metadata).issuperset(main_meta)
if all_meta:
assert len(set(doc.metadata)) > len(main_meta)
else:
assert len(set(doc.metadata)) == len(main_meta)
def test_load_success(retriever: WikipediaRetriever) -> None:
docs = retriever.invoke("HUNTER X HUNTER")
assert len(docs) > 1
assert len(docs) <= 3
assert_docs(docs, all_meta=False)
def test_load_success_all_meta(retriever: WikipediaRetriever) -> None:
retriever.load_all_available_meta = True
docs = retriever.invoke("HUNTER X HUNTER")
assert len(docs) > 1
assert len(docs) <= 3
assert_docs(docs, all_meta=True)
def test_load_success_init_args() -> None:
retriever = WikipediaRetriever( # type: ignore[call-arg]
lang="en", top_k_results=1, load_all_available_meta=True
)
docs = retriever.invoke("HUNTER X HUNTER")
assert len(docs) == 1
assert_docs(docs, all_meta=True)
def test_load_success_init_args_more() -> None:
retriever = WikipediaRetriever( # type: ignore[call-arg]
lang="en", top_k_results=20, load_all_available_meta=False
)
docs = retriever.invoke("HUNTER X HUNTER")
assert len(docs) == 20
assert_docs(docs, all_meta=False)
def test_load_no_result(retriever: WikipediaRetriever) -> None:
docs = retriever.invoke(
"NORESULTCALL_NORESULTCALL_NORESULTCALL_NORESULTCALL_NORESULTCALL_NORESULTCALL"
)
assert not docs