You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/community/tests/integration_tests/embeddings/test_fastembed.py

75 lines
2.6 KiB
Python

"""Test FastEmbed embeddings."""
import pytest
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463) Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
10 months ago
from langchain_community.embeddings.fastembed import FastEmbedEmbeddings
@pytest.mark.parametrize(
"model_name", ["sentence-transformers/all-MiniLM-L6-v2", "BAAI/bge-small-en-v1.5"]
)
@pytest.mark.parametrize("max_length", [50, 512])
@pytest.mark.parametrize("doc_embed_type", ["default", "passage"])
@pytest.mark.parametrize("threads", [0, 10])
def test_fastembed_embedding_documents(
model_name: str, max_length: int, doc_embed_type: str, threads: int
) -> None:
"""Test fastembed embeddings for documents."""
documents = ["foo bar", "bar foo"]
embedding = FastEmbedEmbeddings(
model_name=model_name,
max_length=max_length,
doc_embed_type=doc_embed_type,
threads=threads,
)
output = embedding.embed_documents(documents)
assert len(output) == 2
assert len(output[0]) == 384
@pytest.mark.parametrize(
"model_name", ["sentence-transformers/all-MiniLM-L6-v2", "BAAI/bge-small-en-v1.5"]
)
@pytest.mark.parametrize("max_length", [50, 512])
def test_fastembed_embedding_query(model_name: str, max_length: int) -> None:
"""Test fastembed embeddings for query."""
document = "foo bar"
embedding = FastEmbedEmbeddings(model_name=model_name, max_length=max_length)
output = embedding.embed_query(document)
assert len(output) == 384
@pytest.mark.parametrize(
"model_name", ["sentence-transformers/all-MiniLM-L6-v2", "BAAI/bge-small-en-v1.5"]
)
@pytest.mark.parametrize("max_length", [50, 512])
@pytest.mark.parametrize("doc_embed_type", ["default", "passage"])
@pytest.mark.parametrize("threads", [0, 10])
async def test_fastembed_async_embedding_documents(
model_name: str, max_length: int, doc_embed_type: str, threads: int
) -> None:
"""Test fastembed embeddings for documents."""
documents = ["foo bar", "bar foo"]
embedding = FastEmbedEmbeddings(
model_name=model_name,
max_length=max_length,
doc_embed_type=doc_embed_type,
threads=threads,
)
output = await embedding.aembed_documents(documents)
assert len(output) == 2
assert len(output[0]) == 384
@pytest.mark.parametrize(
"model_name", ["sentence-transformers/all-MiniLM-L6-v2", "BAAI/bge-small-en-v1.5"]
)
@pytest.mark.parametrize("max_length", [50, 512])
async def test_fastembed_async_embedding_query(
model_name: str, max_length: int
) -> None:
"""Test fastembed embeddings for query."""
document = "foo bar"
embedding = FastEmbedEmbeddings(model_name=model_name, max_length=max_length)
output = await embedding.aembed_query(document)
assert len(output) == 384