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/document_loaders/test_unstructured.py

101 lines
2.7 KiB
Python

import os
from contextlib import ExitStack
from pathlib import Path
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.document_loaders import (
UnstructuredAPIFileIOLoader,
UnstructuredAPIFileLoader,
UnstructuredFileLoader,
)
EXAMPLE_DOCS_DIRECTORY = str(Path(__file__).parent.parent / "examples/")
def test_unstructured_loader_with_post_processor() -> None:
def add_the_end(text: str) -> str:
return text + "THE END!"
file_path = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper.pdf")
loader = UnstructuredFileLoader(
file_path=file_path,
post_processors=[add_the_end],
strategy="fast",
mode="elements",
)
docs = loader.load()
assert len(docs) > 1
assert docs[0].page_content.endswith("THE END!")
def test_unstructured_api_file_loader() -> None:
"""Test unstructured loader."""
file_path = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper.pdf")
loader = UnstructuredAPIFileLoader(
file_path=file_path,
api_key="FAKE_API_KEY",
strategy="fast",
mode="elements",
)
docs = loader.load()
assert len(docs) > 1
def test_unstructured_api_file_loader_multiple_files() -> None:
"""Test unstructured loader."""
file_paths = [
os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper.pdf"),
os.path.join(EXAMPLE_DOCS_DIRECTORY, "whatsapp_chat.txt"),
]
loader = UnstructuredAPIFileLoader(
file_path=file_paths,
api_key="FAKE_API_KEY",
strategy="fast",
mode="elements",
)
docs = loader.load()
assert len(docs) > 1
def test_unstructured_api_file_io_loader() -> None:
"""Test unstructured loader."""
file_path = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper.pdf")
with open(file_path, "rb") as f:
loader = UnstructuredAPIFileIOLoader(
file=f,
api_key="FAKE_API_KEY",
strategy="fast",
mode="elements",
file_filename=file_path,
)
docs = loader.load()
assert len(docs) > 1
def test_unstructured_api_file_loader_io_multiple_files() -> None:
"""Test unstructured loader."""
file_paths = [
os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper.pdf"),
os.path.join(EXAMPLE_DOCS_DIRECTORY, "whatsapp_chat.txt"),
]
with ExitStack() as stack:
files = [stack.enter_context(open(file_path, "rb")) for file_path in file_paths]
loader = UnstructuredAPIFileIOLoader(
file=files, # type: ignore
api_key="FAKE_API_KEY",
strategy="fast",
mode="elements",
file_filenames=file_paths,
)
docs = loader.load()
assert len(docs) > 1