mirror of
https://github.com/hwchase17/langchain.git
synced 2025-10-12 20:42:25 +00:00
f92006de3c
0.2rc migrations - [x] Move memory - [x] Move remaining retrievers - [x] graph_qa chains - [x] some dependency from evaluation code potentially on math utils - [x] Move openapi chain from `langchain.chains.api.openapi` to `langchain_community.chains.openapi` - [x] Migrate `langchain.chains.ernie_functions` to `langchain_community.chains.ernie_functions` - [x] migrate `langchain/chains/llm_requests.py` to `langchain_community.chains.llm_requests` - [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder` -> `langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder` (namespace not ideal, but it needs to be moved to `langchain` to avoid circular deps) - [x] unit tests langchain -- add pytest.mark.community to some unit tests that will stay in langchain - [x] unit tests community -- move unit tests that depend on community to community - [x] mv integration tests that depend on community to community - [x] mypy checks Other todo - [x] Make deprecation warnings not noisy (need to use warn deprecated and check that things are implemented properly) - [x] Update deprecation messages with timeline for code removal (likely we actually won't be removing things until 0.4 release) -- will give people more time to transition their code. - [ ] Add information to deprecation warning to show users how to migrate their code base using langchain-cli - [ ] Remove any unnecessary requirements in langchain (e.g., is SQLALchemy required?) --------- Co-authored-by: Erick Friis <erick@langchain.dev>
27 lines
1.1 KiB
Python
27 lines
1.1 KiB
Python
from langchain.retrievers.contextual_compression import ContextualCompressionRetriever
|
|
from langchain.retrievers.document_compressors import EmbeddingsFilter
|
|
|
|
from langchain_community.embeddings import OpenAIEmbeddings
|
|
from langchain_community.vectorstores import FAISS
|
|
|
|
|
|
def test_contextual_compression_retriever_get_relevant_docs() -> None:
|
|
"""Test get_relevant_docs."""
|
|
texts = [
|
|
"This is a document about the Boston Celtics",
|
|
"The Boston Celtics won the game by 20 points",
|
|
"I simply love going to the movies",
|
|
]
|
|
embeddings = OpenAIEmbeddings()
|
|
base_compressor = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.75)
|
|
base_retriever = FAISS.from_texts(texts, embedding=embeddings).as_retriever(
|
|
search_kwargs={"k": len(texts)}
|
|
)
|
|
retriever = ContextualCompressionRetriever(
|
|
base_compressor=base_compressor, base_retriever=base_retriever
|
|
)
|
|
|
|
actual = retriever.invoke("Tell me about the Celtics")
|
|
assert len(actual) == 2
|
|
assert texts[-1] not in [d.page_content for d in actual]
|