2023-10-12 14:47:32 -07:00
|
|
|
from unstructured.documents.elements import Text
|
2024-02-14 09:24:52 -08:00
|
|
|
from unstructured.embed.openai import OpenAIEmbeddingConfig, OpenAIEmbeddingEncoder
|
2023-10-12 14:47:32 -07:00
|
|
|
|
|
|
|
|
|
|
|
def test_embed_documents_does_not_break_element_to_dict(mocker):
|
|
|
|
# Mocked client with the desired behavior for embed_documents
|
|
|
|
mock_client = mocker.MagicMock()
|
|
|
|
mock_client.embed_documents.return_value = [1, 2]
|
|
|
|
|
2023-12-26 17:33:19 -05:00
|
|
|
# Mock create_client to return our mock_client
|
|
|
|
mocker.patch.object(OpenAIEmbeddingEncoder, "create_client", return_value=mock_client)
|
2023-10-12 14:47:32 -07:00
|
|
|
|
2024-02-14 09:24:52 -08:00
|
|
|
encoder = OpenAIEmbeddingEncoder(config=OpenAIEmbeddingConfig(api_key="api_key"))
|
2023-10-12 14:47:32 -07:00
|
|
|
elements = encoder.embed_documents(
|
|
|
|
elements=[Text("This is sentence 1"), Text("This is sentence 2")],
|
|
|
|
)
|
|
|
|
assert len(elements) == 2
|
|
|
|
assert elements[0].to_dict()["text"] == "This is sentence 1"
|
|
|
|
assert elements[1].to_dict()["text"] == "This is sentence 2"
|