mirror of
https://github.com/kennethreitz/langchain.git
synced 2026-06-05 23:00:18 +00:00
Anton Troynikov
78abd277ff
Chroma is a simple to use, open-source, zero-config, zero setup vectorstore. Simply `pip install chromadb`, and you're good to go. Out-of-the-box Chroma is suitable for most LangChain workloads, but is highly flexible. I tested to 1M embs on my M1 mac, with out issues and reasonably fast query times. Look out for future releases as we integrate more Chroma features with LangChain!
29 lines
1.0 KiB
Python
29 lines
1.0 KiB
Python
"""Test Chroma functionality."""
|
|
from langchain.docstore.document import Document
|
|
from langchain.vectorstores import Chroma
|
|
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
|
|
|
|
|
|
def test_chroma() -> None:
|
|
"""Test end to end construction and search."""
|
|
texts = ["foo", "bar", "baz"]
|
|
docsearch = Chroma.from_texts(
|
|
collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()
|
|
)
|
|
output = docsearch.similarity_search("foo", k=1)
|
|
assert output == [Document(page_content="foo")]
|
|
|
|
|
|
def test_chroma_with_metadatas() -> None:
|
|
"""Test end to end construction and search."""
|
|
texts = ["foo", "bar", "baz"]
|
|
metadatas = [{"page": str(i)} for i in range(len(texts))]
|
|
docsearch = Chroma.from_texts(
|
|
collection_name="test_collection",
|
|
texts=texts,
|
|
embedding=FakeEmbeddings(),
|
|
metadatas=metadatas,
|
|
)
|
|
output = docsearch.similarity_search("foo", k=1)
|
|
assert output == [Document(page_content="foo", metadata={"page": "0"})]
|