Install and use ruff format instead of black for code formatting. (l…

…angchain-ai#12585) Best to review one commit at a time, since two of the commits are 100% autogenerated changes from running `ruff format`: - Install and use `ruff format` instead of black for code formatting. - Output of `ruff format .` in the `langchain` package. - Use `ruff format` in experimental package. - Format changes in experimental package by `ruff format`. - Manual formatting fixes to make `ruff .` pass.
manukychen · Oct 31, 2023 · f94e24d · f94e24d
1 parent bfd719f
commit f94e24d
Show file tree

Hide file tree

Showing 61 changed files with 246 additions and 399 deletions.
diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
@@ -134,7 +134,7 @@ Run these locally before submitting a PR; the CI system will check also.
 
 #### Code Formatting
 
-Formatting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/) and [ruff](https://docs.astral.sh/ruff/rules/).
+Formatting for this project is done via [ruff](https://docs.astral.sh/ruff/rules/).
 
 To run formatting for docs, cookbook and templates:
 
@@ -159,7 +159,7 @@ This is especially useful when you have made changes to a subset of the project
 
 #### Linting
 
-Linting for this project is done via a combination of [Black](https://black.readthedocs.io/en/stable/), [ruff](https://docs.astral.sh/ruff/rules/), and [mypy](http://mypy-lang.org/).
+Linting for this project is done via a combination of [ruff](https://docs.astral.sh/ruff/rules/) and [mypy](http://mypy-lang.org/).
 
 To run linting for docs, cookbook and templates:
 
@@ -302,8 +302,8 @@ make api_docs_linkcheck
 
 ### Verify Documentation changes
 
-After pushing documentation changes to the repository, you can preview and verify that the changes are 
-what you wanted by clicking the `View deployment` or `Visit Preview` buttons on the pull request `Conversation` page. 
+After pushing documentation changes to the repository, you can preview and verify that the changes are
+what you wanted by clicking the `View deployment` or `Visit Preview` buttons on the pull request `Conversation` page.
 This will take you to a preview of the documentation changes.
 This preview is created by [Vercel](https://vercel.com/docs/getting-started-with-vercel).
 

diff --git a/Makefile b/Makefile
@@ -43,10 +43,10 @@ spell_fix:
 
 lint:
 	poetry run ruff docs templates cookbook
-	poetry run black docs templates cookbook --check
+	poetry run ruff format docs templates cookbook --diff
 
 format format_diff:
-	poetry run black docs templates cookbook
+	poetry run ruff format docs templates cookbook
 	poetry run ruff --select I --fix docs templates cookbook
 
 ######################

diff --git a/libs/experimental/Makefile b/libs/experimental/Makefile
@@ -9,7 +9,7 @@ TEST_FILE ?= tests/unit_tests/
 test:
 	poetry run pytest $(TEST_FILE)
 
-tests: 
+tests:
 	poetry run pytest $(TEST_FILE)
 
 test_watch:
@@ -33,11 +33,11 @@ lint_diff format_diff: PYTHON_FILES=$(shell git diff --relative=libs/experimenta
 
 lint lint_diff:
 	poetry run mypy $(PYTHON_FILES)
-	poetry run black $(PYTHON_FILES) --check
+	poetry run ruff format $(PYTHON_FILES) --diff
 	poetry run ruff .
 
 format format_diff:
-	poetry run black $(PYTHON_FILES)
+	poetry run ruff format $(PYTHON_FILES)
 	poetry run ruff --select I --fix $(PYTHON_FILES)
 
 spell_check:

diff --git a/libs/experimental/langchain_experimental/tabular_synthetic_data/openai.py b/libs/experimental/langchain_experimental/tabular_synthetic_data/openai.py
@@ -16,7 +16,7 @@ def create_openai_data_generator(
     llm: ChatOpenAI,
     prompt: BasePromptTemplate,
     output_parser: Optional[BaseLLMOutputParser] = None,
-    **kwargs: Any
+    **kwargs: Any,
 ) -> SyntheticDataGenerator:
     """
     Create an instance of SyntheticDataGenerator tailored for OpenAI models.

diff --git a/libs/experimental/langchain_experimental/tot/thought_generation.py b/libs/experimental/langchain_experimental/tot/thought_generation.py
@@ -29,7 +29,7 @@ def next_thought(
         self,
         problem_description: str,
         thoughts_path: Tuple[str, ...] = (),
-        **kwargs: Any
+        **kwargs: Any,
     ) -> str:
         """
         Generate the next thought given the problem description and the thoughts
@@ -52,7 +52,7 @@ def next_thought(
         self,
         problem_description: str,
         thoughts_path: Tuple[str, ...] = (),
-        **kwargs: Any
+        **kwargs: Any,
     ) -> str:
         response_text = self.predict_and_parse(
             problem_description=problem_description, thoughts=thoughts_path, **kwargs
@@ -76,14 +76,14 @@ def next_thought(
         self,
         problem_description: str,
         thoughts_path: Tuple[str, ...] = (),
-        **kwargs: Any
+        **kwargs: Any,
     ) -> str:
         if thoughts_path not in self.tot_memory or not self.tot_memory[thoughts_path]:
             new_thoughts = self.predict_and_parse(
                 problem_description=problem_description,
                 thoughts=thoughts_path,
                 n=self.c,
-                **kwargs
+                **kwargs,
             )
             if not new_thoughts:
                 return ""

diff --git a/libs/experimental/poetry.lock b/libs/experimental/poetry.lock
diff --git a/libs/experimental/pyproject.toml b/libs/experimental/pyproject.toml
@@ -18,8 +18,7 @@ vowpal-wabbit-next = {version = "0.6.0", optional = true}
 sentence-transformers = {version = "^2", optional = true}
 
 [tool.poetry.group.lint.dependencies]
-ruff = "^0.1"
-black = "^23.10.0"
+ruff = "^0.1.3"
 
 [tool.poetry.group.typing.dependencies]
 mypy = "^0.991"

diff --git a/libs/experimental/tests/unit_tests/rl_chain/test_pick_best_chain_call.py b/libs/experimental/tests/unit_tests/rl_chain/test_pick_best_chain_call.py
@@ -95,7 +95,8 @@ def test_update_with_delayed_score_with_auto_validator_throws() -> None:
     assert selection_metadata.selected.score == 3.0  # type: ignore
     with pytest.raises(RuntimeError):
         chain.update_with_delayed_score(
-            chain_response=response, score=100  # type: ignore
+            chain_response=response,
+            score=100,  # type: ignore
         )
 
 
@@ -121,7 +122,9 @@ def test_update_with_delayed_score_force() -> None:
     selection_metadata = response["selection_metadata"]  # type: ignore
     assert selection_metadata.selected.score == 3.0  # type: ignore
     chain.update_with_delayed_score(
-        chain_response=response, score=100, force_score=True  # type: ignore
+        chain_response=response,
+        score=100,
+        force_score=True,  # type: ignore
     )
     assert selection_metadata.selected.score == 100.0  # type: ignore
 

diff --git a/libs/langchain/Makefile b/libs/langchain/Makefile
@@ -50,11 +50,11 @@ lint lint_diff:
 	./scripts/check_pydantic.sh .
 	./scripts/check_imports.sh
 	poetry run ruff .
-	[ "$(PYTHON_FILES)" = "" ] || poetry run black $(PYTHON_FILES) --check
+	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff
 	[ "$(PYTHON_FILES)" = "" ] || poetry run mypy $(PYTHON_FILES)
 
 format format_diff:
-	[ "$(PYTHON_FILES)" = "" ] || poetry run black $(PYTHON_FILES)
+	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES)
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff --select I --fix $(PYTHON_FILES)
 
 spell_check:

diff --git a/libs/langchain/langchain/_api/path.py b/libs/langchain/langchain/_api/path.py
@@ -22,7 +22,7 @@ def as_import_path(
     file: Union[Path, str],
     *,
     suffix: Optional[str] = None,
-    relative_to: Path = PACKAGE_DIR
+    relative_to: Path = PACKAGE_DIR,
 ) -> str:
     """Path of the file as a LangChain import exclude langchain top namespace."""
     if isinstance(file, str):

diff --git a/libs/langchain/langchain/agents/agent_toolkits/conversational_retrieval/openai_functions.py b/libs/langchain/langchain/agents/agent_toolkits/conversational_retrieval/openai_functions.py
@@ -32,7 +32,7 @@ def create_conversational_retrieval_agent(
     system_message: Optional[SystemMessage] = None,
     verbose: bool = False,
     max_token_limit: int = 2000,
-    **kwargs: Any
+    **kwargs: Any,
 ) -> AgentExecutor:
     """A convenience method for creating a conversational retrieval agent.
 
@@ -83,5 +83,5 @@ def create_conversational_retrieval_agent(
         memory=memory,
         verbose=verbose,
         return_intermediate_steps=remember_intermediate_steps,
-        **kwargs
+        **kwargs,
     )
diff --git a/libs/langchain/langchain/callbacks/argilla_callback.py b/libs/langchain/langchain/callbacks/argilla_callback.py
@@ -284,7 +284,8 @@ def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
                             },
                         }
                         for prompt, output in zip(
-                            prompts, chain_output_val  # type: ignore
+                            prompts,  # type: ignore
+                            chain_output_val,
                         )
                     ]
                 )

diff --git a/libs/langchain/langchain/callbacks/flyte_callback.py b/libs/langchain/langchain/callbacks/flyte_callback.py
@@ -195,7 +195,9 @@ def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
                         )
                     )
 
-                    complexity_metrics: Dict[str, float] = generation_resp.pop("text_complexity_metrics")  # type: ignore  # noqa: E501
+                    complexity_metrics: Dict[str, float] = generation_resp.pop(
+                        "text_complexity_metrics"
+                    )  # type: ignore  # noqa: E501
                     self.deck.append(
                         self.markdown_renderer().to_html("#### Text Complexity Metrics")
                     )

diff --git a/libs/langchain/langchain/callbacks/manager.py b/libs/langchain/langchain/callbacks/manager.py
@@ -64,20 +64,14 @@
 openai_callback_var: ContextVar[Optional[OpenAICallbackHandler]] = ContextVar(
     "openai_callback", default=None
 )
-tracing_callback_var: ContextVar[
-    Optional[LangChainTracerV1]
-] = ContextVar(  # noqa: E501
+tracing_callback_var: ContextVar[Optional[LangChainTracerV1]] = ContextVar(  # noqa: E501
     "tracing_callback", default=None
 )
-wandb_tracing_callback_var: ContextVar[
-    Optional[WandbTracer]
-] = ContextVar(  # noqa: E501
+wandb_tracing_callback_var: ContextVar[Optional[WandbTracer]] = ContextVar(  # noqa: E501
     "tracing_wandb_callback", default=None
 )
 
-tracing_v2_callback_var: ContextVar[
-    Optional[LangChainTracer]
-] = ContextVar(  # noqa: E501
+tracing_v2_callback_var: ContextVar[Optional[LangChainTracer]] = ContextVar(  # noqa: E501
     "tracing_callback_v2", default=None
 )
 run_collector_var: ContextVar[

diff --git a/libs/langchain/langchain/callbacks/mlflow_callback.py b/libs/langchain/langchain/callbacks/mlflow_callback.py
@@ -371,7 +371,9 @@ def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
                         nlp=self.nlp,
                     )
                 )
-                complexity_metrics: Dict[str, float] = generation_resp.pop("text_complexity_metrics")  # type: ignore  # noqa: E501
+                complexity_metrics: Dict[str, float] = generation_resp.pop(
+                    "text_complexity_metrics"
+                )  # type: ignore  # noqa: E501
                 self.mlflg.metrics(
                     complexity_metrics,
                     step=self.metrics["step"],

diff --git a/libs/langchain/langchain/callbacks/streaming_stdout.py b/libs/langchain/langchain/callbacks/streaming_stdout.py
@@ -19,7 +19,7 @@ def on_chat_model_start(
         self,
         serialized: Dict[str, Any],
         messages: List[List[BaseMessage]],
-        **kwargs: Any
+        **kwargs: Any,
     ) -> None:
         """Run when LLM starts running."""
 

diff --git a/libs/langchain/langchain/callbacks/streaming_stdout_final_only.py b/libs/langchain/langchain/callbacks/streaming_stdout_final_only.py
@@ -32,7 +32,7 @@ def __init__(
         *,
         answer_prefix_tokens: Optional[List[str]] = None,
         strip_tokens: bool = True,
-        stream_prefix: bool = False
+        stream_prefix: bool = False,
     ) -> None:
         """Instantiate FinalStreamingStdOutCallbackHandler.
 

diff --git a/libs/langchain/langchain/callbacks/tracers/root_listeners.py b/libs/langchain/langchain/callbacks/tracers/root_listeners.py
@@ -11,7 +11,7 @@ def __init__(
         *,
         on_start: Optional[Callable[[Run], None]],
         on_end: Optional[Callable[[Run], None]],
-        on_error: Optional[Callable[[Run], None]]
+        on_error: Optional[Callable[[Run], None]],
     ) -> None:
         super().__init__()
 

diff --git a/libs/langchain/langchain/chains/api/openapi/chain.py b/libs/langchain/langchain/chains/api/openapi/chain.py
@@ -171,7 +171,7 @@ def from_url_and_method(
         llm: BaseLanguageModel,
         requests: Optional[Requests] = None,
         return_intermediate_steps: bool = False,
-        **kwargs: Any
+        **kwargs: Any,
         # TODO: Handle async
     ) -> "OpenAPIEndpointChain":
         """Create an OpenAPIEndpoint from a spec at the specified url."""
@@ -194,7 +194,7 @@ def from_api_operation(
         return_intermediate_steps: bool = False,
         raw_response: bool = False,
         callbacks: Callbacks = None,
-        **kwargs: Any
+        **kwargs: Any,
         # TODO: Handle async
     ) -> "OpenAPIEndpointChain":
         """Create an OpenAPIEndpointChain from an operation and a spec."""

diff --git a/libs/langchain/langchain/chains/openai_functions/tagging.py b/libs/langchain/langchain/chains/openai_functions/tagging.py
@@ -32,7 +32,7 @@ def create_tagging_chain(
     schema: dict,
     llm: BaseLanguageModel,
     prompt: Optional[ChatPromptTemplate] = None,
-    **kwargs: Any
+    **kwargs: Any,
 ) -> Chain:
     """Creates a chain that extracts information from a passage
      based on a schema.
@@ -62,7 +62,7 @@ def create_tagging_chain_pydantic(
     pydantic_schema: Any,
     llm: BaseLanguageModel,
     prompt: Optional[ChatPromptTemplate] = None,
-    **kwargs: Any
+    **kwargs: Any,
 ) -> Chain:
     """Creates a chain that extracts information from a passage
      based on a pydantic schema.

diff --git a/libs/langchain/langchain/chat_models/promptlayer_openai.py b/libs/langchain/langchain/chat_models/promptlayer_openai.py
@@ -44,7 +44,7 @@ def _generate(
         stop: Optional[List[str]] = None,
         run_manager: Optional[CallbackManagerForLLMRun] = None,
         stream: Optional[bool] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> ChatResult:
         """Call ChatOpenAI generate and then call PromptLayer API to log the request."""
         from promptlayer.utils import get_api_key, promptlayer_api_request
@@ -86,7 +86,7 @@ async def _agenerate(
         stop: Optional[List[str]] = None,
         run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
         stream: Optional[bool] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> ChatResult:
         """Call ChatOpenAI agenerate and then call PromptLayer to log."""
         from promptlayer.utils import get_api_key, promptlayer_api_request_async

diff --git a/libs/langchain/langchain/document_loaders/azure_blob_storage_container.py b/libs/langchain/langchain/document_loaders/azure_blob_storage_container.py
@@ -36,7 +36,9 @@ def load(self) -> List[Document]:
         blob_list = container.list_blobs(name_starts_with=self.prefix)
         for blob in blob_list:
             loader = AzureBlobStorageFileLoader(
-                self.conn_str, self.container, blob.name  # type: ignore
+                self.conn_str,
+                self.container,
+                blob.name,  # type: ignore
             )
             docs.extend(loader.load())
         return docs
diff --git a/libs/langchain/langchain/document_loaders/blackboard.py b/libs/langchain/langchain/document_loaders/blackboard.py
@@ -211,7 +211,9 @@ def _load_documents(self) -> List[Document]:
         """
         # Create the document loader
         loader = DirectoryLoader(
-            path=self.folder_path, glob="*.pdf", loader_cls=PyPDFLoader  # type: ignore
+            path=self.folder_path,
+            glob="*.pdf",
+            loader_cls=PyPDFLoader,  # type: ignore
         )
         # Load the documents
         documents = loader.load()

diff --git a/libs/langchain/langchain/embeddings/johnsnowlabs.py b/libs/langchain/langchain/embeddings/johnsnowlabs.py
@@ -25,7 +25,7 @@ def __init__(
         self,
         model: Any = "embed_sentence.bert",
         hardware_target: str = "cpu",
-        **kwargs: Any
+        **kwargs: Any,
     ):
         """Initialize the johnsnowlabs model."""
         super().__init__(**kwargs)

diff --git a/libs/langchain/langchain/embeddings/localai.py b/libs/langchain/langchain/embeddings/localai.py
@@ -269,9 +269,7 @@ def _embedding_func(self, text: str, *, engine: str) -> List[float]:
             self,
             input=[text],
             **self._invocation_params,
-        )["data"][
-            0
-        ]["embedding"]
+        )["data"][0]["embedding"]
 
     async def _aembedding_func(self, text: str, *, engine: str) -> List[float]:
         """Call out to LocalAI's embedding endpoint."""

diff --git a/libs/langchain/langchain/embeddings/nlpcloud.py b/libs/langchain/langchain/embeddings/nlpcloud.py
@@ -26,7 +26,7 @@ def __init__(
         self,
         model_name: str = "paraphrase-multilingual-mpnet-base-v2",
         gpu: bool = False,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> None:
         super().__init__(model_name=model_name, gpu=gpu, **kwargs)
 

diff --git a/libs/langchain/langchain/embeddings/openai.py b/libs/langchain/langchain/embeddings/openai.py
@@ -393,9 +393,7 @@ def _get_len_safe_embeddings(
                     self,
                     input="",
                     **self._invocation_params,
-                )[
-                    "data"
-                ][0]["embedding"]
+                )["data"][0]["embedding"]
             else:
                 average = np.average(_result, axis=0, weights=num_tokens_in_batch[i])
             embeddings[i] = (average / np.linalg.norm(average)).tolist()

diff --git a/libs/langchain/langchain/indexes/vectorstore.py b/libs/langchain/langchain/indexes/vectorstore.py
@@ -34,7 +34,7 @@ def query(
         question: str,
         llm: Optional[BaseLanguageModel] = None,
         retriever_kwargs: Optional[Dict[str, Any]] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> str:
         """Query the vectorstore."""
         llm = llm or OpenAI(temperature=0)
@@ -49,7 +49,7 @@ def query_with_sources(
         question: str,
         llm: Optional[BaseLanguageModel] = None,
         retriever_kwargs: Optional[Dict[str, Any]] = None,
-        **kwargs: Any
+        **kwargs: Any,
     ) -> dict:
         """Query the vectorstore and get back sources."""
         llm = llm or OpenAI(temperature=0)