mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-24 03:52:10 +00:00
f8883a1321
Voyage has introduced voyage-3-large and voyage-code-3, which feature different output dimensions by leveraging a technique called "Matryoshka Embeddings" (see blog - https://blog.voyageai.com/2024/12/04/voyage-code-3/). These two models are available in various sizes: [256, 512, 1024, 2048] (https://docs.voyageai.com/docs/embeddings#model-choices). This PR adds the option to set the required output dimension.
63 lines
2.1 KiB
Python
63 lines
2.1 KiB
Python
"""Test VoyageAI embeddings."""
|
|
|
|
from langchain_voyageai import VoyageAIEmbeddings
|
|
|
|
# Please set VOYAGE_API_KEY in the environment variables
|
|
MODEL = "voyage-2"
|
|
|
|
|
|
def test_langchain_voyageai_embedding_documents() -> None:
|
|
"""Test voyage embeddings."""
|
|
documents = ["foo bar"]
|
|
embedding = VoyageAIEmbeddings(model=MODEL) # type: ignore[call-arg]
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 1
|
|
assert len(output[0]) == 1024
|
|
|
|
|
|
def test_langchain_voyageai_embedding_documents_multiple() -> None:
|
|
"""Test voyage embeddings."""
|
|
documents = ["foo bar", "bar foo", "foo"]
|
|
embedding = VoyageAIEmbeddings(model=MODEL, batch_size=2)
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 3
|
|
assert len(output[0]) == 1024
|
|
assert len(output[1]) == 1024
|
|
assert len(output[2]) == 1024
|
|
|
|
|
|
def test_langchain_voyageai_embedding_query() -> None:
|
|
"""Test voyage embeddings."""
|
|
document = "foo bar"
|
|
embedding = VoyageAIEmbeddings(model=MODEL) # type: ignore[call-arg]
|
|
output = embedding.embed_query(document)
|
|
assert len(output) == 1024
|
|
|
|
|
|
async def test_langchain_voyageai_async_embedding_documents_multiple() -> None:
|
|
"""Test voyage embeddings."""
|
|
documents = ["foo bar", "bar foo", "foo"]
|
|
embedding = VoyageAIEmbeddings(model=MODEL, batch_size=2)
|
|
output = await embedding.aembed_documents(documents)
|
|
assert len(output) == 3
|
|
assert len(output[0]) == 1024
|
|
assert len(output[1]) == 1024
|
|
assert len(output[2]) == 1024
|
|
|
|
|
|
async def test_langchain_voyageai_async_embedding_query() -> None:
|
|
"""Test voyage embeddings."""
|
|
document = "foo bar"
|
|
embedding = VoyageAIEmbeddings(model=MODEL) # type: ignore[call-arg]
|
|
output = await embedding.aembed_query(document)
|
|
assert len(output) == 1024
|
|
|
|
|
|
def test_langchain_voyageai_embedding_documents_with_output_dimension() -> None:
|
|
"""Test voyage embeddings."""
|
|
documents = ["foo bar"]
|
|
embedding = VoyageAIEmbeddings(model="voyage-3-large", output_dimension=256) # type: ignore[call-arg]
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 1
|
|
assert len(output[0]) == 256
|