The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
chroma[patch]: ruff fixes and rules (#31900)
Mason Daugherty38bd1abb8c67
diff --git a/libs/partners/chroma/langchain_chroma/vectorstores.py b/libs/partners/chroma/langchain_chroma/vectorstores.pyindex 227da2d230..2b966f662f 100644--- a/libs/partners/chroma/langchain_chroma/vectorstores.py+++ b/libs/partners/chroma/langchain_chroma/vectorstores.py@@ -79,11 +79,14 @@ def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:X = np.array(X)Y = np.array(Y)if X.shape[1] != Y.shape[1]:- raise ValueError(+ msg = ("Number of columns in X and Y must be the same. X has shape"f"{X.shape} "f"and Y has shape {Y.shape}.")+ raise ValueError(+ msg,+ )X_norm = np.linalg.norm(X, axis=1)Y_norm = np.linalg.norm(Y, axis=1)@@ -285,7 +288,7 @@ class Chroma(VectorStore):collection_metadata: Optional[dict] = None,client: Optional[chromadb.ClientAPI] = None,relevance_score_fn: Optional[Callable[[float], float]] = None,- create_collection_if_not_exists: Optional[bool] = True,+ create_collection_if_not_exists: Optional[bool] = True, # noqa: FBT002) -> None:"""Initialize with a Chroma client.@@ -351,10 +354,13 @@ class Chroma(VectorStore):def _collection(self) -> chromadb.Collection:"""Returns the underlying Chroma collection or throws an exception."""if self._chroma_collection is None:- raise ValueError(+ msg = ("Chroma collection not initialized. ""Use `reset_collection` to re-create and initialize the collection. ")+ raise ValueError(+ msg,+ )return self._chroma_collection@property@@ -392,10 +398,10 @@ class Chroma(VectorStore):"""return self._collection.query(query_texts=query_texts,- query_embeddings=query_embeddings, # type: ignore+ query_embeddings=query_embeddings, # type: ignore[arg-type]n_results=n_results,- where=where, # type: ignore- where_document=where_document, # type: ignore+ where=where, # type: ignore[arg-type]+ where_document=where_document, # type: ignore[arg-type]**kwargs,)@@ -432,11 +438,12 @@ class Chroma(VectorStore):if ids is None:ids = [str(uuid.uuid4()) for _ in uris]else:- ids = [id if id is not None else str(uuid.uuid4()) for id in ids]+ ids = [id_ if id_ is not None else str(uuid.uuid4()) for id_ in ids]embeddings = None# Set embeddingsif self._embedding_function is not None and hasattr(- self._embedding_function, "embed_image"+ self._embedding_function,+ "embed_image",):embeddings = self._embedding_function.embed_image(uris=uris)if metadatas:@@ -461,8 +468,8 @@ class Chroma(VectorStore):ids_with_metadata = [ids[idx] for idx in non_empty_ids]try:self._collection.upsert(- metadatas=metadatas, # type: ignore- embeddings=embeddings_with_metadatas, # type: ignore+ metadatas=metadatas, # type: ignore[arg-type]+ embeddings=embeddings_with_metadatas, # type: ignore[arg-type]documents=images_with_metadatas,ids=ids_with_metadata,)@@ -473,8 +480,7 @@ class Chroma(VectorStore):"langchain_community.vectorstores.utils.filter_complex_metadata.")raise ValueError(e.args[0] + "\n\n" + msg)- else:- raise e+ raise eif empty_ids:images_without_metadatas = [b64_texts[j] for j in empty_ids]embeddings_without_metadatas = (@@ -519,7 +525,7 @@ class Chroma(VectorStore):if ids is None:ids = [str(uuid.uuid4()) for _ in texts]else:- ids = [id if id is not None else str(uuid.uuid4()) for id in ids]+ ids = [id_ if id_ is not None else str(uuid.uuid4()) for id_ in ids]embeddings = Nonetexts = list(texts)@@ -549,8 +555,8 @@ class Chroma(VectorStore):ids_with_metadata = [ids[idx] for idx in non_empty_ids]try:self._collection.upsert(- metadatas=metadatas, # type: ignore- embeddings=embeddings_with_metadatas, # type: ignore+ metadatas=metadatas, # type: ignore[arg-type]+ embeddings=embeddings_with_metadatas, # type: ignore[arg-type]documents=texts_with_metadatas,ids=ids_with_metadata,)@@ -561,8 +567,7 @@ class Chroma(VectorStore):"langchain_community.vectorstores.utils.filter_complex_metadata.")raise ValueError(e.args[0] + "\n\n" + msg)- else:- raise e+ raise eif empty_ids:texts_without_metadatas = [texts[j] for j in empty_ids]embeddings_without_metadatas = (@@ -570,13 +575,13 @@ class Chroma(VectorStore):)ids_without_metadatas = [ids[j] for j in empty_ids]self._collection.upsert(- embeddings=embeddings_without_metadatas, # type: ignore+ embeddings=embeddings_without_metadatas, # type: ignore[arg-type]documents=texts_without_metadatas,ids=ids_without_metadatas,)else:self._collection.upsert(- embeddings=embeddings, # type: ignore+ embeddings=embeddings, # type: ignore[arg-type]documents=texts,ids=ids,)@@ -586,7 +591,7 @@ class Chroma(VectorStore):self,query: str,k: int = DEFAULT_K,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002**kwargs: Any,) -> list[Document]:"""Run similarity search with Chroma.@@ -601,7 +606,10 @@ class Chroma(VectorStore):List of documents most similar to the query text."""docs_and_scores = self.similarity_search_with_score(- query, k, filter=filter, **kwargs+ query,+ k,+ filter=filter,+ **kwargs,)return [doc for doc, _ in docs_and_scores]@@ -609,7 +617,7 @@ class Chroma(VectorStore):self,embedding: list[float],k: int = DEFAULT_K,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002where_document: Optional[dict[str, str]] = None,**kwargs: Any,) -> list[Document]:@@ -639,7 +647,7 @@ class Chroma(VectorStore):self,embedding: list[float],k: int = DEFAULT_K,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002where_document: Optional[dict[str, str]] = None,**kwargs: Any,) -> list[tuple[Document, float]]:@@ -670,7 +678,7 @@ class Chroma(VectorStore):self,query: str,k: int = DEFAULT_K,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002where_document: Optional[dict[str, str]] = None,**kwargs: Any,) -> list[tuple[Document, float]]:@@ -712,7 +720,7 @@ class Chroma(VectorStore):self,query: str,k: int = DEFAULT_K,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002where_document: Optional[dict[str, str]] = None,**kwargs: Any,) -> list[tuple[Document, np.ndarray]]:@@ -780,22 +788,24 @@ class Chroma(VectorStore):if distance == "cosine":return self._cosine_relevance_score_fn- elif distance == "l2":+ if distance == "l2":return self._euclidean_relevance_score_fn- elif distance == "ip":+ if distance == "ip":return self._max_inner_product_relevance_score_fn- else:- raise ValueError(- "No supported normalization function"- f" for distance metric of type: {distance}."- "Consider providing relevance_score_fn to Chroma constructor."- )+ msg = (+ "No supported normalization function"+ f" for distance metric of type: {distance}."+ "Consider providing relevance_score_fn to Chroma constructor."+ )+ raise ValueError(+ msg,+ )def similarity_search_by_image(self,uri: str,k: int = DEFAULT_K,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002**kwargs: Any,) -> list[Document]:"""Search for similar images based on the given image URI.@@ -817,29 +827,29 @@ class Chroma(VectorStore):ValueError: If the embedding function does not support image embeddings."""if self._embedding_function is None or not hasattr(- self._embedding_function, "embed_image"+ self._embedding_function,+ "embed_image",):- raise ValueError("The embedding function must support image embedding.")+ msg = "The embedding function must support image embedding."+ raise ValueError(msg)# Obtain image embedding# Assuming embed_image returns a single embeddingimage_embedding = self._embedding_function.embed_image(uris=[uri])# Perform similarity search based on the obtained embedding- results = self.similarity_search_by_vector(+ return self.similarity_search_by_vector(embedding=image_embedding,k=k,filter=filter,**kwargs,)- return results-def similarity_search_by_image_with_relevance_score(self,uri: str,k: int = DEFAULT_K,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002**kwargs: Any,) -> list[tuple[Document, float]]:"""Search for similar images based on the given image URI.@@ -861,31 +871,31 @@ class Chroma(VectorStore):ValueError: If the embedding function does not support image embeddings."""if self._embedding_function is None or not hasattr(- self._embedding_function, "embed_image"+ self._embedding_function,+ "embed_image",):- raise ValueError("The embedding function must support image embedding.")+ msg = "The embedding function must support image embedding."+ raise ValueError(msg)# Obtain image embedding# Assuming embed_image returns a single embeddingimage_embedding = self._embedding_function.embed_image(uris=[uri])# Perform similarity search based on the obtained embedding- results = self.similarity_search_by_vector_with_relevance_scores(+ return self.similarity_search_by_vector_with_relevance_scores(embedding=image_embedding,k=k,filter=filter,**kwargs,)- return results-def max_marginal_relevance_search_by_vector(self,embedding: list[float],k: int = DEFAULT_K,fetch_k: int = 20,lambda_mult: float = 0.5,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002where_document: Optional[dict[str, str]] = None,**kwargs: Any,) -> list[Document]:@@ -928,8 +938,7 @@ class Chroma(VectorStore):candidates = _results_to_docs(results)- selected_results = [r for i, r in enumerate(candidates) if i in mmr_selected]- return selected_results+ return [r for i, r in enumerate(candidates) if i in mmr_selected]def max_marginal_relevance_search(self,@@ -937,7 +946,7 @@ class Chroma(VectorStore):k: int = DEFAULT_K,fetch_k: int = 20,lambda_mult: float = 0.5,- filter: Optional[dict[str, str]] = None,+ filter: Optional[dict[str, str]] = None, # noqa: A002where_document: Optional[dict[str, str]] = None,**kwargs: Any,) -> list[Document]:@@ -966,8 +975,9 @@ class Chroma(VectorStore):ValueError: If the embedding function is not provided."""if self._embedding_function is None:+ msg = "For MMR search, you must specify an embedding function on creation."raise ValueError(- "For MMR search, you must specify an embedding function on creation."+ msg,)embedding = self._embedding_function.embed_query(query)@@ -1032,7 +1042,7 @@ class Chroma(VectorStore):if include is not None:kwargs["include"] = include- return self._collection.get(**kwargs) # type: ignore+ return self._collection.get(**kwargs) # type: ignore[arg-type, return-value]def get_by_ids(self, ids: Sequence[str], /) -> list[Document]:"""Get documents by their IDs.@@ -1062,7 +1072,9 @@ class Chroma(VectorStore):return [Document(page_content=doc, metadata=meta, id=doc_id)for doc, meta, doc_id in zip(- results["documents"], results["metadatas"], results["ids"]+ results["documents"],+ results["metadatas"],+ results["ids"],)]@@ -1075,7 +1087,6 @@ class Chroma(VectorStore):"""return self.update_documents([document_id], [document])- # type: ignoredef update_documents(self, ids: list[str], documents: list[Document]) -> None:"""Update a document in the collection.@@ -1089,24 +1100,27 @@ class Chroma(VectorStore):text = [document.page_content for document in documents]metadata = [document.metadata for document in documents]if self._embedding_function is None:+ msg = "For update, you must specify an embedding function on creation."raise ValueError(- "For update, you must specify an embedding function on creation."+ msg,)embeddings = self._embedding_function.embed_documents(text)if hasattr(- self._collection._client, "get_max_batch_size"+ self._collection._client, # noqa: SLF001+ "get_max_batch_size",) or hasattr( # for Chroma 0.5.1 and above- self._collection._client, "max_batch_size"+ self._collection._client, # noqa: SLF001+ "max_batch_size",): # for Chroma 0.4.10 and abovefrom chromadb.utils.batch_utils import create_batchesfor batch in create_batches(- api=self._collection._client,+ api=self._collection._client, # noqa: SLF001ids=ids,- metadatas=metadata, # type: ignore+ metadatas=metadata, # type: ignore[arg-type]documents=text,- embeddings=embeddings, # type: ignore+ embeddings=embeddings, # type: ignore[arg-type]):self._collection.update(ids=batch[0],@@ -1117,9 +1131,9 @@ class Chroma(VectorStore):else:self._collection.update(ids=ids,- embeddings=embeddings, # type: ignore+ embeddings=embeddings, # type: ignore[arg-type]documents=text,- metadatas=metadata, # type: ignore+ metadatas=metadata, # type: ignore[arg-type])@classmethod@@ -1170,23 +1184,25 @@ class Chroma(VectorStore):if ids is None:ids = [str(uuid.uuid4()) for _ in texts]else:- ids = [id if id is not None else str(uuid.uuid4()) for id in ids]+ ids = [id_ if id_ is not None else str(uuid.uuid4()) for id_ in ids]if hasattr(- chroma_collection._client, "get_max_batch_size"+ chroma_collection._client, # noqa: SLF001+ "get_max_batch_size",) or hasattr( # for Chroma 0.5.1 and above- chroma_collection._client, "max_batch_size"+ chroma_collection._client, # noqa: SLF001+ "max_batch_size",): # for Chroma 0.4.10 and abovefrom chromadb.utils.batch_utils import create_batchesfor batch in create_batches(- api=chroma_collection._client,+ api=chroma_collection._client, # noqa: SLF001ids=ids,- metadatas=metadatas, # type: ignore+ metadatas=metadatas, # type: ignore[arg-type]documents=texts,):chroma_collection.add_texts(texts=batch[3] if batch[3] else [],- metadatas=batch[2] if batch[2] else None, # type: ignore+ metadatas=batch[2] if batch[2] else None, # type: ignore[arg-type]ids=batch[0],)else:diff --git a/libs/partners/chroma/pyproject.toml b/libs/partners/chroma/pyproject.tomlindex 73825651b4..dc1d6a6d5e 100644--- a/libs/partners/chroma/pyproject.toml+++ b/libs/partners/chroma/pyproject.toml@@ -62,8 +62,52 @@ disallow_untyped_defs = truetarget-version = "py39"[tool.ruff.lint]-select = ["E", "F", "I", "T201", "D", "UP", "S"]-ignore = [ "UP007", ]+select = [+ "A", # flake8-builtins+ "ASYNC", # flake8-async+ "C4", # flake8-comprehensions+ "COM", # flake8-commas+ "D", # pydocstyle+ "DOC", # pydoclint+ "E", # pycodestyle error+ "EM", # flake8-errmsg+ "F", # pyflakes+ "FA", # flake8-future-annotations+ "FBT", # flake8-boolean-trap+ "FLY", # flake8-flynt+ "I", # isort+ "ICN", # flake8-import-conventions+ "INT", # flake8-gettext+ "ISC", # isort-comprehensions+ "PGH", # pygrep-hooks+ "PIE", # flake8-pie+ "PERF", # flake8-perf+ "PYI", # flake8-pyi+ "Q", # flake8-quotes+ "RET", # flake8-return+ "RSE", # flake8-rst-docstrings+ "RUF", # ruff+ "S", # flake8-bandit+ "SLF", # flake8-self+ "SLOT", # flake8-slots+ "SIM", # flake8-simplify+ "T10", # flake8-debugger+ "T20", # flake8-print+ "TID", # flake8-tidy-imports+ "UP", # pyupgrade+ "W", # pycodestyle warning+ "YTT", # flake8-2020+]+ignore = [+ "D100", # Missing docstring in public module+ "D101", # Missing docstring in public class+ "D102", # Missing docstring in public method+ "D103", # Missing docstring in public function+ "D104", # Missing docstring in public package+ "D105", # Missing docstring in magic method+ "D107", # Missing docstring in __init__+ "UP007", # pyupgrade: non-pep604-annotation-union+][tool.coverage.run]omit = ["tests/*"]@@ -84,6 +128,7 @@ convention = "google"[tool.ruff.lint.extend-per-file-ignores]"tests/**/*.py" = [- "S101", # Tests need assertions- "S311", # Standard pseudo-random generators are not suitable for cryptographic purposes+ "S101", # Tests need assertions+ "S311", # Standard pseudo-random generators are not suitable for cryptographic purposes+ "SLF001", # Private member access in tests]\ No newline at end of filediff --git a/libs/partners/chroma/scripts/check_imports.py b/libs/partners/chroma/scripts/check_imports.pyindex a7fcbc5ca6..b850913e53 100644--- a/libs/partners/chroma/scripts/check_imports.py+++ b/libs/partners/chroma/scripts/check_imports.py@@ -10,7 +10,7 @@ if __name__ == "__main__":for file in files:try:SourceFileLoader("x", file).load_module()- except Exception:+ except Exception: # noqa: PERF203has_failure = Trueprint(file) # noqa: T201traceback.print_exc()diff --git a/libs/partners/chroma/tests/integration_tests/fake_embeddings.py b/libs/partners/chroma/tests/integration_tests/fake_embeddings.pyindex e04f295782..9f318b60cf 100644--- a/libs/partners/chroma/tests/integration_tests/fake_embeddings.py+++ b/libs/partners/chroma/tests/integration_tests/fake_embeddings.py@@ -44,7 +44,7 @@ class ConsistentFakeEmbeddings(FakeEmbeddings):if text not in self.known_texts:self.known_texts.append(text)vector = [1.0] * (self.dimensionality - 1) + [- float(self.known_texts.index(text))+ float(self.known_texts.index(text)),]out_vectors.append(vector)return out_vectorsdiff --git a/libs/partners/chroma/tests/integration_tests/test_compile.py b/libs/partners/chroma/tests/integration_tests/test_compile.pyindex 5196f4c0f8..5c812af314 100644--- a/libs/partners/chroma/tests/integration_tests/test_compile.py+++ b/libs/partners/chroma/tests/integration_tests/test_compile.py@@ -4,4 +4,3 @@ import pytest # type: ignore[import-not-found]@pytest.mark.compiledef test_placeholder() -> None:"""Used for compiling integration tests without running any real tests."""- passdiff --git a/libs/partners/chroma/tests/integration_tests/test_vectorstores.py b/libs/partners/chroma/tests/integration_tests/test_vectorstores.pyindex a42ba95254..f5794c3875 100644--- a/libs/partners/chroma/tests/integration_tests/test_vectorstores.py+++ b/libs/partners/chroma/tests/integration_tests/test_vectorstores.py@@ -28,8 +28,8 @@ class MyEmbeddingFunction:def __init__(self, fak: Fak):self.fak = fak- def __call__(self, input: Embeddable) -> list[list[float]]:- texts = cast(list[str], input)+ def __call__(self, input_: Embeddable) -> list[list[float]]:+ texts = cast(list[str], input_)return self.fak.embed_documents(texts=texts)@@ -44,7 +44,9 @@ 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()+ collection_name="test_collection",+ texts=texts,+ embedding=FakeEmbeddings(),)output = docsearch.similarity_search("foo", k=1)@@ -92,7 +94,9 @@ async def test_chroma_async() -> None:"""Test end to end construction and search."""texts = ["foo", "bar", "baz"]docsearch = Chroma.from_texts(- collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()+ collection_name="test_collection",+ texts=texts,+ embedding=FakeEmbeddings(),)output = await docsearch.asimilarity_search("foo", k=1)@@ -173,7 +177,7 @@ def test_chroma_with_metadatas_with_scores_and_ids() -> None:output = docsearch.similarity_search_with_score("foo", k=1)docsearch.delete_collection()assert output == [- (Document(page_content="foo", metadata={"page": "0"}, id="id_0"), 0.0)+ (Document(page_content="foo", metadata={"page": "0"}, id="id_0"), 0.0),]@@ -211,11 +215,12 @@ def test_chroma_with_metadatas_with_scores_using_vector() -> None:)embedded_query = embeddings.embed_query("foo")output = docsearch.similarity_search_by_vector_with_relevance_scores(- embedding=embedded_query, k=1+ embedding=embedded_query,+ k=1,)docsearch.delete_collection()assert output == [- (Document(page_content="foo", metadata={"page": "0"}, id="id_0"), 0.0)+ (Document(page_content="foo", metadata={"page": "0"}, id="id_0"), 0.0),]@@ -235,10 +240,10 @@ def test_chroma_search_filter() -> None:output2 = docsearch.similarity_search("far", k=1, filter={"first_letter": "b"})docsearch.delete_collection()assert output1 == [- Document(page_content="far", metadata={"first_letter": "f"}, id="id_0")+ Document(page_content="far", metadata={"first_letter": "f"}, id="id_0"),]assert output2 == [- Document(page_content="bar", metadata={"first_letter": "b"}, id="id_1")+ Document(page_content="bar", metadata={"first_letter": "b"}, id="id_1"),]@@ -255,17 +260,21 @@ def test_chroma_search_filter_with_scores() -> None:ids=ids,)output1 = docsearch.similarity_search_with_score(- "far", k=1, filter={"first_letter": "f"}+ "far",+ k=1,+ filter={"first_letter": "f"},)output2 = docsearch.similarity_search_with_score(- "far", k=1, filter={"first_letter": "b"}+ "far",+ k=1,+ filter={"first_letter": "b"},)docsearch.delete_collection()assert output1 == [- (Document(page_content="far", metadata={"first_letter": "f"}, id="id_0"), 0.0)+ (Document(page_content="far", metadata={"first_letter": "f"}, id="id_0"), 0.0),]assert output2 == [- (Document(page_content="bar", metadata={"first_letter": "b"}, id="id_1"), 1.0)+ (Document(page_content="bar", metadata={"first_letter": "b"}, id="id_1"), 1.0),]@@ -365,7 +374,9 @@ def test_chroma_mmr() -> None:"""Test end to end construction and search."""texts = ["foo", "bar", "baz"]docsearch = Chroma.from_texts(- collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()+ collection_name="test_collection",+ texts=texts,+ embedding=FakeEmbeddings(),)output = docsearch.max_marginal_relevance_search("foo", k=1)docsearch.delete_collection()@@ -379,7 +390,9 @@ def test_chroma_mmr_by_vector() -> None:texts = ["foo", "bar", "baz"]embeddings = FakeEmbeddings()docsearch = Chroma.from_texts(- collection_name="test_collection", texts=texts, embedding=embeddings+ collection_name="test_collection",+ texts=texts,+ embedding=embeddings,)embedded_query = embeddings.embed_query("foo")output = docsearch.max_marginal_relevance_search_by_vector(embedded_query, k=1)@@ -393,7 +406,9 @@ def test_chroma_with_include_parameter() -> None:"""Test end to end construction and include parameter."""texts = ["foo", "bar", "baz"]docsearch = Chroma.from_texts(- collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()+ collection_name="test_collection",+ texts=texts,+ embedding=FakeEmbeddings(),)output1 = docsearch.get(include=["embeddings"])output2 = docsearch.get()@@ -424,7 +439,7 @@ def test_chroma_update_document() -> None:embedding=embedding,ids=[document_id],)- old_embedding = docsearch._collection.peek()["embeddings"][ # type: ignore+ old_embedding = docsearch._collection.peek()["embeddings"][ # type: ignore[index]docsearch._collection.peek()["ids"].index(document_id)]@@ -441,7 +456,7 @@ def test_chroma_update_document() -> None:output = docsearch.similarity_search(updated_content, k=1)# Assert that the new embedding is correct- new_embedding = docsearch._collection.peek()["embeddings"][ # type: ignore+ new_embedding = docsearch._collection.peek()["embeddings"][ # type: ignore[index]docsearch._collection.peek()["ids"].index(document_id)]@@ -449,7 +464,7 @@ def test_chroma_update_document() -> None:# Assert that the updated document is returned by the searchassert output == [- Document(page_content=updated_content, metadata={"page": "0"}, id=document_id)+ Document(page_content=updated_content, metadata={"page": "0"}, id=document_id),]assert list(new_embedding) == list(embedding.embed_documents([updated_content])[0])@@ -470,7 +485,9 @@ def test_chroma_update_document_with_id() -> None:# Create an instance of Document with initial content and metadataoriginal_doc = Document(- page_content=initial_content, metadata={"page": "0"}, id=document_id+ page_content=initial_content,+ metadata={"page": "0"},+ id=document_id,)# Initialize a Chroma instance with the original document@@ -479,7 +496,7 @@ def test_chroma_update_document_with_id() -> None:documents=[original_doc],embedding=embedding,)- old_embedding = docsearch._collection.peek()["embeddings"][ # type: ignore+ old_embedding = docsearch._collection.peek()["embeddings"][ # type: ignore[index]docsearch._collection.peek()["ids"].index(document_id)]@@ -488,7 +505,9 @@ def test_chroma_update_document_with_id() -> None:# Create a new Document instance with the updated content and the same idupdated_doc = Document(- page_content=updated_content, metadata={"page": "0"}, id=document_id+ page_content=updated_content,+ metadata={"page": "0"},+ id=document_id,)# Update the document in the Chroma instance@@ -498,7 +517,7 @@ def test_chroma_update_document_with_id() -> None:output = docsearch.similarity_search(updated_content, k=1)# Assert that the new embedding is correct- new_embedding = docsearch._collection.peek()["embeddings"][ # type: ignore+ new_embedding = docsearch._collection.peek()["embeddings"][ # type: ignore[index]docsearch._collection.peek()["ids"].index(document_id)]@@ -506,7 +525,7 @@ def test_chroma_update_document_with_id() -> None:# Assert that the updated document is returned by the searchassert output == [- Document(page_content=updated_content, metadata={"page": "0"}, id=document_id)+ Document(page_content=updated_content, metadata={"page": "0"}, id=document_id),]assert list(new_embedding) == list(embedding.embed_documents([updated_content])[0])@@ -568,7 +587,8 @@ def test_chroma_add_documents_mixed_metadata() -> None:assert actual_ids == idsassert sorted(search, key=lambda d: d.page_content) == sorted(- docs, key=lambda d: d.page_content+ docs,+ key=lambda d: d.page_content,)@@ -582,9 +602,7 @@ def is_api_accessible(url: str) -> bool:def batch_support_chroma_version() -> bool:major, minor, patch = chromadb.__version__.split(".")- if int(major) == 0 and int(minor) >= 4 and int(patch) >= 10:- return True- return False+ return bool(int(major) == 0 and int(minor) >= 4 and int(patch) >= 10)@pytest.mark.requires("chromadb")@@ -601,9 +619,9 @@ def test_chroma_large_batch() -> None:embedding_function = MyEmbeddingFunction(fak=Fak(size=255))col = client.get_or_create_collection("my_collection",- embedding_function=embedding_function, # type: ignore+ embedding_function=embedding_function, # type: ignore[arg-type])- docs = ["This is a test document"] * (client.get_max_batch_size() + 100) # type: ignore+ docs = ["This is a test document"] * (client.get_max_batch_size() + 100)db = Chroma.from_texts(client=client,collection_name=col.name,@@ -629,9 +647,9 @@ def test_chroma_large_batch_update() -> None:embedding_function = MyEmbeddingFunction(fak=Fak(size=255))col = client.get_or_create_collection("my_collection",- embedding_function=embedding_function, # type: ignore+ embedding_function=embedding_function, # type: ignore[arg-type])- docs = ["This is a test document"] * (client.get_max_batch_size() + 100) # type: ignore+ docs = ["This is a test document"] * (client.get_max_batch_size() + 100)ids = [str(uuid.uuid4()) for _ in range(len(docs))]db = Chroma.from_texts(client=client,@@ -642,11 +660,12 @@ def test_chroma_large_batch_update() -> None:)new_docs = [Document(- page_content="This is a new test document", metadata={"doc_id": f"{i}"}+ page_content="This is a new test document",+ metadata={"doc_id": f"{i}"},)for i in range(len(docs) - 10)]- new_ids = [_id for _id in ids[: len(new_docs)]]+ new_ids = list(ids[: len(new_docs)])db.update_documents(ids=new_ids, documents=new_docs)db.delete_collection()@@ -658,14 +677,15 @@ def test_chroma_large_batch_update() -> None:reason="API not accessible",)@pytest.mark.skipif(- batch_support_chroma_version(), reason="ChromaDB version does not support batching"+ batch_support_chroma_version(),+ reason="ChromaDB version does not support batching",)def test_chroma_legacy_batching() -> None:client = chromadb.HttpClient()embedding_function = Fak(size=255)col = client.get_or_create_collection("my_collection",- embedding_function=MyEmbeddingFunction, # type: ignore+ embedding_function=MyEmbeddingFunction, # type: ignore[arg-type])docs = ["This is a test document"] * 100db = Chroma.from_texts(@@ -683,7 +703,9 @@ def test_create_collection_if_not_exist_default() -> None:"""Tests existing behaviour without the new create_collection_if_not_exists flag."""texts = ["foo", "bar", "baz"]docsearch = Chroma.from_texts(- collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()+ collection_name="test_collection",+ texts=texts,+ embedding=FakeEmbeddings(),)assert docsearch._client.get_collection("test_collection") is not Nonedocsearch.delete_collection()@@ -798,7 +820,7 @@ def test_delete_where_clause(client: chromadb.ClientAPI) -> None:[Document(page_content="foo", metadata={"test": "bar"}),Document(page_content="bar", metadata={"test": "foo"}),- ]+ ],)assert vectorstore._collection.count() == 2vectorstore.delete(where={"test": "bar"})diff --git a/libs/partners/chroma/tests/unit_tests/test_standard.py b/libs/partners/chroma/tests/unit_tests/test_standard.pyindex e933339a45..b2aa15d9a9 100644--- a/libs/partners/chroma/tests/unit_tests/test_standard.py+++ b/libs/partners/chroma/tests/unit_tests/test_standard.py@@ -9,11 +9,10 @@ from langchain_chroma import Chromaclass TestChromaStandard(VectorStoreIntegrationTests):@pytest.fixture()- def vectorstore(self) -> Generator[VectorStore, None, None]: # type: ignore+ def vectorstore(self) -> Generator[VectorStore, None, None]: # type: ignore[override]"""Get an empty vectorstore for unit tests."""store = Chroma(embedding_function=self.get_embeddings())try:yield storefinally:store.delete_collection()- pass