mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
d43d430d86
This PR adds persistence to the Chroma vector store. Users can supply a `persist_directory` with any of the `Chroma` creation methods. If supplied, the store will be automatically persisted at that directory. If a user creates a new `Chroma` instance with the same persistence directory, it will get loaded up automatically. If they use `from_texts` or `from_documents` in this way, the documents will be loaded into the existing store. There is the chance of some funky behavior if the user passes a different embedding function from the one used to create the collection - we will make this easier in future updates. For now, we log a warning.
62 lines
2.0 KiB
Python
62 lines
2.0 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"})]
|
|
|
|
|
|
def test_chroma_with_persistence() -> None:
|
|
"""Test end to end construction and search, with persistence."""
|
|
chroma_persist_dir = "./tests/persist_dir"
|
|
collection_name = "test_collection"
|
|
texts = ["foo", "bar", "baz"]
|
|
docsearch = Chroma.from_texts(
|
|
collection_name=collection_name,
|
|
texts=texts,
|
|
embedding=FakeEmbeddings(),
|
|
persist_directory=chroma_persist_dir,
|
|
)
|
|
|
|
output = docsearch.similarity_search("foo", k=1)
|
|
assert output == [Document(page_content="foo")]
|
|
|
|
docsearch.persist()
|
|
|
|
# Get a new VectorStore from the persisted directory
|
|
docsearch = Chroma(
|
|
collection_name=collection_name,
|
|
embedding_function=FakeEmbeddings(),
|
|
persist_directory=chroma_persist_dir,
|
|
)
|
|
output = docsearch.similarity_search("foo", k=1)
|
|
|
|
# Clean up
|
|
docsearch.delete_collection()
|
|
|
|
# Persist doesn't need to be called again
|
|
# Data will be automatically persisted on object deletion
|
|
# Or on program exit
|