mirror of
https://github.com/hwchase17/langchain
synced 2024-11-18 09:25:54 +00:00
ed58eeb9c5
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
90 lines
2.7 KiB
Python
90 lines
2.7 KiB
Python
"""Test openai embeddings."""
|
|
import numpy as np
|
|
import pytest
|
|
|
|
from langchain_community.embeddings.openai import OpenAIEmbeddings
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_openai_embedding_documents() -> None:
|
|
"""Test openai embeddings."""
|
|
documents = ["foo bar"]
|
|
embedding = OpenAIEmbeddings()
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 1
|
|
assert len(output[0]) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_openai_embedding_documents_multiple() -> None:
|
|
"""Test openai embeddings."""
|
|
documents = ["foo bar", "bar foo", "foo"]
|
|
embedding = OpenAIEmbeddings(chunk_size=2)
|
|
embedding.embedding_ctx_length = 8191
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 3
|
|
assert len(output[0]) == 1536
|
|
assert len(output[1]) == 1536
|
|
assert len(output[2]) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
async def test_openai_embedding_documents_async_multiple() -> None:
|
|
"""Test openai embeddings."""
|
|
documents = ["foo bar", "bar foo", "foo"]
|
|
embedding = OpenAIEmbeddings(chunk_size=2)
|
|
embedding.embedding_ctx_length = 8191
|
|
output = await embedding.aembed_documents(documents)
|
|
assert len(output) == 3
|
|
assert len(output[0]) == 1536
|
|
assert len(output[1]) == 1536
|
|
assert len(output[2]) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_openai_embedding_query() -> None:
|
|
"""Test openai embeddings."""
|
|
document = "foo bar"
|
|
embedding = OpenAIEmbeddings()
|
|
output = embedding.embed_query(document)
|
|
assert len(output) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
async def test_openai_embedding_async_query() -> None:
|
|
"""Test openai embeddings."""
|
|
document = "foo bar"
|
|
embedding = OpenAIEmbeddings()
|
|
output = await embedding.aembed_query(document)
|
|
assert len(output) == 1536
|
|
|
|
|
|
@pytest.mark.skip(reason="Unblock scheduled testing. TODO: fix.")
|
|
@pytest.mark.scheduled
|
|
def test_openai_embedding_with_empty_string() -> None:
|
|
"""Test openai embeddings with empty string."""
|
|
import openai
|
|
|
|
document = ["", "abc"]
|
|
embedding = OpenAIEmbeddings()
|
|
output = embedding.embed_documents(document)
|
|
assert len(output) == 2
|
|
assert len(output[0]) == 1536
|
|
expected_output = openai.Embedding.create(input="", model="text-embedding-ada-002")[
|
|
"data"
|
|
][0]["embedding"]
|
|
assert np.allclose(output[0], expected_output)
|
|
assert len(output[1]) == 1536
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_embed_documents_normalized() -> None:
|
|
output = OpenAIEmbeddings().embed_documents(["foo walked to the market"])
|
|
assert np.isclose(np.linalg.norm(output[0]), 1.0)
|
|
|
|
|
|
@pytest.mark.scheduled
|
|
def test_embed_query_normalized() -> None:
|
|
output = OpenAIEmbeddings().embed_query("foo walked to the market")
|
|
assert np.isclose(np.linalg.norm(output), 1.0)
|