mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
ed58eeb9c5
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
70 lines
1.9 KiB
Python
70 lines
1.9 KiB
Python
import random
|
|
|
|
import pytest
|
|
import requests
|
|
|
|
from langchain_community.document_loaders import NewsURLLoader
|
|
|
|
|
|
def get_random_news_url() -> str:
|
|
from bs4 import BeautifulSoup
|
|
|
|
response = requests.get("https://news.google.com")
|
|
soup = BeautifulSoup(response.text, "html.parser")
|
|
|
|
article_links = [
|
|
a["href"] for a in soup.find_all("a", href=True) if "/articles/" in a["href"]
|
|
]
|
|
random_article_link = random.choice(article_links)
|
|
|
|
return "https://news.google.com" + random_article_link
|
|
|
|
|
|
def test_news_loader() -> None:
|
|
loader = NewsURLLoader([get_random_news_url()])
|
|
docs = loader.load()
|
|
|
|
assert docs[0] is not None
|
|
assert hasattr(docs[0], "page_content")
|
|
assert hasattr(docs[0], "metadata")
|
|
|
|
metadata = docs[0].metadata
|
|
assert "title" in metadata
|
|
assert "link" in metadata
|
|
assert "authors" in metadata
|
|
assert "language" in metadata
|
|
assert "description" in metadata
|
|
assert "publish_date" in metadata
|
|
|
|
|
|
def test_news_loader_with_nlp() -> None:
|
|
loader = NewsURLLoader([get_random_news_url()], nlp=True)
|
|
docs = loader.load()
|
|
|
|
assert docs[0] is not None
|
|
assert hasattr(docs[0], "page_content")
|
|
assert hasattr(docs[0], "metadata")
|
|
|
|
metadata = docs[0].metadata
|
|
assert "title" in metadata
|
|
assert "link" in metadata
|
|
assert "authors" in metadata
|
|
assert "language" in metadata
|
|
assert "description" in metadata
|
|
assert "publish_date" in metadata
|
|
assert "keywords" in metadata
|
|
assert "summary" in metadata
|
|
|
|
|
|
def test_continue_on_failure_true() -> None:
|
|
"""Test exception is not raised when continue_on_failure=True."""
|
|
loader = NewsURLLoader(["badurl.foobar"])
|
|
loader.load()
|
|
|
|
|
|
def test_continue_on_failure_false() -> None:
|
|
"""Test exception is raised when continue_on_failure=False."""
|
|
loader = NewsURLLoader(["badurl.foobar"], continue_on_failure=False)
|
|
with pytest.raises(Exception):
|
|
loader.load()
|