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/test_nuclia_transformer.py

64 lines
2.0 KiB
Python

import asyncio
import json
from typing import Any
from unittest import mock
multiple: langchain 0.2 in master (#21191) 0.2rc migrations - [x] Move memory - [x] Move remaining retrievers - [x] graph_qa chains - [x] some dependency from evaluation code potentially on math utils - [x] Move openapi chain from `langchain.chains.api.openapi` to `langchain_community.chains.openapi` - [x] Migrate `langchain.chains.ernie_functions` to `langchain_community.chains.ernie_functions` - [x] migrate `langchain/chains/llm_requests.py` to `langchain_community.chains.llm_requests` - [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder` -> `langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder` (namespace not ideal, but it needs to be moved to `langchain` to avoid circular deps) - [x] unit tests langchain -- add pytest.mark.community to some unit tests that will stay in langchain - [x] unit tests community -- move unit tests that depend on community to community - [x] mv integration tests that depend on community to community - [x] mypy checks Other todo - [x] Make deprecation warnings not noisy (need to use warn deprecated and check that things are implemented properly) - [x] Update deprecation messages with timeline for code removal (likely we actually won't be removing things until 0.4 release) -- will give people more time to transition their code. - [ ] Add information to deprecation warning to show users how to migrate their code base using langchain-cli - [ ] Remove any unnecessary requirements in langchain (e.g., is SQLALchemy required?) --------- Co-authored-by: Erick Friis <erick@langchain.dev>
5 months ago
from langchain_core.documents import Document
from langchain_community.document_transformers.nuclia_text_transform import (
NucliaTextTransformer,
)
from langchain_community.tools.nuclia.tool import NucliaUnderstandingAPI
def fakerun(**args: Any) -> Any:
async def run(self: Any, **args: Any) -> str:
await asyncio.sleep(0.1)
data = {
"extracted_text": [{"body": {"text": "Hello World"}}],
"file_extracted_data": [{"language": "en"}],
"field_metadata": [
{
"metadata": {
"metadata": {
"paragraphs": [
{"end": 66, "sentences": [{"start": 1, "end": 67}]}
]
}
}
}
],
}
return json.dumps(data)
return run
async def test_nuclia_loader() -> None:
with mock.patch(
"langchain_community.tools.nuclia.tool.NucliaUnderstandingAPI._arun",
new_callable=fakerun,
):
with mock.patch("os.environ.get", return_value="_a_key_"):
nua = NucliaUnderstandingAPI(enable_ml=False)
documents = [
Document(page_content="Hello, my name is Alice", metadata={}),
Document(page_content="Hello, my name is Bob", metadata={}),
]
nuclia_transformer = NucliaTextTransformer(nua)
transformed_documents = await nuclia_transformer.atransform_documents(
documents
)
assert len(transformed_documents) == 2
assert (
transformed_documents[0].metadata["nuclia"]["file"]["language"] == "en"
)
assert (
len(
transformed_documents[1].metadata["nuclia"]["metadata"]["metadata"][
"metadata"
]["paragraphs"]
)
== 1
)