2023-06-12 04:14:20 +00:00
|
|
|
"""Test dashscope embeddings."""
|
|
|
|
import numpy as np
|
|
|
|
|
2023-12-11 21:53:30 +00:00
|
|
|
from langchain_community.embeddings.dashscope import DashScopeEmbeddings
|
2023-06-12 04:14:20 +00:00
|
|
|
|
|
|
|
|
|
|
|
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."""
|
Fixing the Issue with DashScopeEmbeddings Handling More than 25 Rows of Data (#14662)
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
This change addresses the issue where DashScopeEmbeddingAPI limits
requests to 25 lines of data, and DashScopeEmbeddings did not handle
cases with more than 25 lines, leading to errors. I have implemented a
fix to manage data exceeding this limit efficiently.
---------
Co-authored-by: xuxiang <xuxiang@aliyun.com>
2024-01-02 00:50:13 +00:00
|
|
|
documents = [
|
|
|
|
"foo bar",
|
|
|
|
"bar foo",
|
|
|
|
"foo",
|
|
|
|
"foo0",
|
|
|
|
"foo1",
|
|
|
|
"foo2",
|
|
|
|
"foo3",
|
|
|
|
"foo4",
|
|
|
|
"foo5",
|
|
|
|
"foo6",
|
|
|
|
"foo7",
|
|
|
|
"foo8",
|
|
|
|
"foo9",
|
|
|
|
"foo10",
|
|
|
|
"foo11",
|
|
|
|
"foo12",
|
|
|
|
"foo13",
|
|
|
|
"foo14",
|
|
|
|
"foo15",
|
|
|
|
"foo16",
|
|
|
|
"foo17",
|
|
|
|
"foo18",
|
|
|
|
"foo19",
|
|
|
|
"foo20",
|
|
|
|
"foo21",
|
|
|
|
"foo22",
|
|
|
|
"foo23",
|
|
|
|
"foo24",
|
|
|
|
]
|
2023-06-12 04:14:20 +00:00
|
|
|
embedding = DashScopeEmbeddings(model="text-embedding-v1")
|
|
|
|
output = embedding.embed_documents(documents)
|
Fixing the Issue with DashScopeEmbeddings Handling More than 25 Rows of Data (#14662)
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
This change addresses the issue where DashScopeEmbeddingAPI limits
requests to 25 lines of data, and DashScopeEmbeddings did not handle
cases with more than 25 lines, leading to errors. I have implemented a
fix to manage data exceeding this limit efficiently.
---------
Co-authored-by: xuxiang <xuxiang@aliyun.com>
2024-01-02 00:50:13 +00:00
|
|
|
assert len(output) == 28
|
2023-06-12 04:14:20 +00:00
|
|
|
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()
|