langchain/libs/community/tests/integration_tests/test_nuclia_transformer.py
Eugene Yurtsev f92006de3c
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>
2024-05-08 16:46:52 -04:00

64 lines
2.0 KiB
Python

import asyncio
import json
from typing import Any
from unittest import mock
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
)