langchain[minor]: Make EmbeddingsFilters async (#22737)

Add native async implementation for EmbeddingsFilter

libs/community/tests/integration_tests/retrievers/document_compressors/test_base.py

@@ -27,3 +27,24 @@ def test_document_compressor_pipeline() -> None:
     actual = pipeline_filter.compress_documents(docs, "Tell me about farm animals")
     assert len(actual) == 1
     assert actual[0].page_content in texts[:2]
+
+
+async def test_adocument_compressor_pipeline() -> None:
+    embeddings = OpenAIEmbeddings()
+    splitter = CharacterTextSplitter(chunk_size=20, chunk_overlap=0, separator=". ")
+    redundant_filter = EmbeddingsRedundantFilter(embeddings=embeddings)
+    relevant_filter = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.8)
+    pipeline_filter = DocumentCompressorPipeline(
+        transformers=[splitter, redundant_filter, relevant_filter]
+    )
+    texts = [
+        "This sentence is about cows",
+        "This sentence was about cows",
+        "foo bar baz",
+    ]
+    docs = [Document(page_content=". ".join(texts))]
+    actual = await pipeline_filter.acompress_documents(
+        docs, "Tell me about farm animals"
+    )
+    assert len(actual) == 1
+    assert actual[0].page_content in texts[:2]

libs/community/tests/integration_tests/retrievers/document_compressors/test_embeddings_filter.py

@@ -23,6 +23,20 @@ def test_embeddings_filter() -> None:
     assert len(set(texts[:2]).intersection([d.page_content for d in actual])) == 2
 
 
+async def atest_embeddings_filter() -> None:
+    texts = [
+        "What happened to all of my cookies?",
+        "I wish there were better Italian restaurants in my neighborhood.",
+        "My favorite color is green",
+    ]
+    docs = [Document(page_content=t) for t in texts]
+    embeddings = OpenAIEmbeddings()
+    relevant_filter = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.75)
+    actual = relevant_filter.compress_documents(docs, "What did I say about food?")
+    assert len(actual) == 2
+    assert len(set(texts[:2]).intersection([d.page_content for d in actual])) == 2
+
+
 def test_embeddings_filter_with_state() -> None:
     texts = [
         "What happened to all of my cookies?",
@@ -41,3 +55,23 @@ def test_embeddings_filter_with_state() -> None:
     actual = relevant_filter.compress_documents(docs, query)
     assert len(actual) == 1
     assert texts[-1] == actual[0].page_content
+
+
+async def test_aembeddings_filter_with_state() -> None:
+    texts = [
+        "What happened to all of my cookies?",
+        "I wish there were better Italian restaurants in my neighborhood.",
+        "My favorite color is green",
+    ]
+    query = "What did I say about food?"
+    embeddings = OpenAIEmbeddings()
+    embedded_query = embeddings.embed_query(query)
+    state = {"embedded_doc": np.zeros(len(embedded_query))}
+    docs = [_DocumentWithState(page_content=t, state=state) for t in texts]
+    docs[-1].state = {"embedded_doc": embedded_query}
+    relevant_filter = EmbeddingsFilter(  # type: ignore[call-arg]
+        embeddings=embeddings, similarity_threshold=0.75, return_similarity_scores=True
+    )
+    actual = relevant_filter.compress_documents(docs, query)
+    assert len(actual) == 1
+    assert texts[-1] == actual[0].page_content

libs/community/tests/integration_tests/retrievers/test_contextual_compression.py

@@ -1,3 +1,4 @@
+import pytest
 from langchain.retrievers.contextual_compression import ContextualCompressionRetriever
 from langchain.retrievers.document_compressors import EmbeddingsFilter
 
@@ -24,3 +25,25 @@ def test_contextual_compression_retriever_get_relevant_docs() -> None:
     actual = retriever.invoke("Tell me about the Celtics")
     assert len(actual) == 2
     assert texts[-1] not in [d.page_content for d in actual]
+
+
+@pytest.mark.asyncio
+async def test_acontextual_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]