mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
9218684759
Added AwaDB vector store, which is a wrapper over the AwaDB, that can be used as a vector storage and has an efficient similarity search. Added integration tests for the vector store Added jupyter notebook with the example Delete a unneeded empty file and resolve the conflict(https://github.com/hwchase17/langchain/pull/5886) Please check, Thanks! @dev2049 @hwchase17 --------- <!-- Thank you for contributing to LangChain! Your PR will appear in our release under the title you set. Please make sure it highlights your valuable contribution. Replace this with a description of the change, the issue it fixes (if applicable), and relevant context. List any dependencies required for this change. After you're done, someone will review your PR. They may suggest improvements. If no one reviews your PR within a few days, feel free to @-mention the same people again, as notifications can get lost. Finally, we'd love to show appreciation for your contribution - if you'd like us to shout you out on Twitter, please also include your handle! --> <!-- Remove if not applicable --> Fixes # (issue) #### Before submitting <!-- If you're adding a new integration, please include: 1. a test for the integration - favor unit tests that does not rely on network access. 2. an example notebook showing its use See contribution guidelines for more information on how to write tests, lint etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md --> #### Who can review? Tag maintainers/contributors who might be interested: <!-- For a quicker response, figure out the right person to tag with @ @hwchase17 - project lead Tracing / Callbacks - @agola11 Async - @agola11 DataLoaders - @eyurtsev Models - @hwchase17 - @agola11 Agents / Tools / Toolkits - @vowelparrot VectorStores / Retrievers / Memory - @dev2049 --> --------- Co-authored-by: ljeagle <vincent_jieli@yeah.net> Co-authored-by: vincent <awadb.vincent@gmail.com>
56 lines
1.9 KiB
Python
56 lines
1.9 KiB
Python
"""Test AwaDB functionality."""
|
|
from langchain.docstore.document import Document
|
|
from langchain.vectorstores import AwaDB
|
|
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
|
|
|
|
|
|
def test_awadb() -> None:
|
|
"""Test end to end construction and search."""
|
|
texts = ["foo", "bar", "baz"]
|
|
docsearch = AwaDB.from_texts(
|
|
table_name="test_awadb", texts=texts, embedding=FakeEmbeddings()
|
|
)
|
|
output = docsearch.similarity_search("foo", k=1)
|
|
assert output == [Document(page_content="foo")]
|
|
|
|
|
|
def test_awadb_with_metadatas() -> None:
|
|
"""Test end to end construction and search."""
|
|
texts = ["foo", "bar", "baz"]
|
|
metadatas = [{"page": i} for i in range(len(texts))]
|
|
docsearch = AwaDB.from_texts(
|
|
table_name="test_awadb",
|
|
texts=texts,
|
|
embedding=FakeEmbeddings(),
|
|
metadatas=metadatas,
|
|
)
|
|
output = docsearch.similarity_search("foo", k=1)
|
|
assert output == [Document(page_content="foo", metadata={"page": 0})]
|
|
|
|
|
|
def test_awadb_with_metadatas_with_scores() -> None:
|
|
"""Test end to end construction and scored search."""
|
|
texts = ["foo", "bar", "baz"]
|
|
metadatas = [{"page": str(i)} for i in range(len(texts))]
|
|
docsearch = AwaDB.from_texts(
|
|
table_name="test_awadb",
|
|
texts=texts,
|
|
embedding=FakeEmbeddings(),
|
|
metadatas=metadatas,
|
|
)
|
|
output = docsearch.similarity_search_with_score("foo", k=1)
|
|
assert output == [(Document(page_content="foo", metadata={"page": "0"}), 0.0)]
|
|
|
|
|
|
def test_awadb_add_texts() -> None:
|
|
"""Test end to end adding of texts."""
|
|
# Create initial doc store.
|
|
texts = ["foo", "bar", "baz"]
|
|
docsearch = AwaDB.from_texts(
|
|
table_name="test_awadb", texts=texts, embedding=FakeEmbeddings()
|
|
)
|
|
# Test adding a similar document as before.
|
|
docsearch.add_texts(["foo"])
|
|
output = docsearch.similarity_search("foo", k=2)
|
|
assert output == [Document(page_content="foo"), Document(page_content="foo")]
|