mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-15 13:05:54 +00:00

Currently when the OpenAIEmbeddingEncoder adds embeddings to Elements in `_add_embeddings_to_elements` it overwrites each Element's `to_dict` method, mistakenly resulting in each Element having identical values with the exception of the actual embedding value. This was due to the way it leverages a nested `new_to_dict` method to overwrite. Instead, this updates the original definition of Element itself to accommodate the `embeddings` field when available. This also adds a test to validate that values are not duplicated.
20 lines
823 B
Python
20 lines
823 B
Python
from unstructured.documents.elements import Text
|
|
from unstructured.embed.openai import OpenAIEmbeddingEncoder
|
|
|
|
|
|
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]
|
|
|
|
# Mock get_openai_client to return our mock_client
|
|
mocker.patch.object(OpenAIEmbeddingEncoder, "get_openai_client", return_value=mock_client)
|
|
|
|
encoder = OpenAIEmbeddingEncoder(api_key="api_key")
|
|
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"
|