mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-13 13:36:15 +00:00
add dashscope text embedding (#5929)
#### What I do Adding embedding api for [DashScope](https://help.aliyun.com/product/610100.html), which is the DAMO Academy's multilingual text unified vector model based on the LLM base. It caters to multiple mainstream languages worldwide and offers high-quality vector services, helping developers quickly transform text data into high-quality vector data. Currently supported languages include Chinese, English, Spanish, French, Portuguese, Indonesian, and more. #### Who can review? Models - @hwchase17 - @agola11 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
55
tests/integration_tests/embeddings/test_dashscope.py
Normal file
55
tests/integration_tests/embeddings/test_dashscope.py
Normal file
@@ -0,0 +1,55 @@
|
||||
"""Test dashscope embeddings."""
|
||||
import numpy as np
|
||||
|
||||
from langchain.embeddings.dashscope import DashScopeEmbeddings
|
||||
|
||||
|
||||
def test_dashscope_embedding_documents() -> None:
|
||||
"""Test dashscope embeddings."""
|
||||
documents = ["foo bar"]
|
||||
embedding = DashScopeEmbeddings(model="text-embedding-v1")
|
||||
output = embedding.embed_documents(documents)
|
||||
assert len(output) == 1
|
||||
assert len(output[0]) == 1536
|
||||
|
||||
|
||||
def test_dashscope_embedding_documents_multiple() -> None:
|
||||
"""Test dashscope embeddings."""
|
||||
documents = ["foo bar", "bar foo", "foo"]
|
||||
embedding = DashScopeEmbeddings(model="text-embedding-v1")
|
||||
output = embedding.embed_documents(documents)
|
||||
assert len(output) == 3
|
||||
assert len(output[0]) == 1536
|
||||
assert len(output[1]) == 1536
|
||||
assert len(output[2]) == 1536
|
||||
|
||||
|
||||
def test_dashscope_embedding_query() -> None:
|
||||
"""Test dashscope embeddings."""
|
||||
document = "foo bar"
|
||||
embedding = DashScopeEmbeddings(model="text-embedding-v1")
|
||||
output = embedding.embed_query(document)
|
||||
assert len(output) == 1536
|
||||
|
||||
|
||||
def test_dashscope_embedding_with_empty_string() -> None:
|
||||
"""Test dashscope embeddings with empty string."""
|
||||
import dashscope
|
||||
|
||||
document = ["", "abc"]
|
||||
embedding = DashScopeEmbeddings(model="text-embedding-v1")
|
||||
output = embedding.embed_documents(document)
|
||||
assert len(output) == 2
|
||||
assert len(output[0]) == 1536
|
||||
expected_output = dashscope.TextEmbedding.call(
|
||||
input="", model="text-embedding-v1", text_type="document"
|
||||
).output["embeddings"][0]["embedding"]
|
||||
assert np.allclose(output[0], expected_output)
|
||||
assert len(output[1]) == 1536
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_dashscope_embedding_documents()
|
||||
test_dashscope_embedding_documents_multiple()
|
||||
test_dashscope_embedding_query()
|
||||
test_dashscope_embedding_with_empty_string()
|
Reference in New Issue
Block a user