chore(langchain): select ALL rules with exclusions (#31930)

Co-authored-by: Mason Daugherty <mason@langchain.dev>

libs/langchain/langchain/agents/agent.py

@@ -1551,7 +1551,7 @@ class AgentExecutor(Chain):
             ],
         )
 
-        # TODO This could yield each result as it becomes available
+        # TODO: This could yield each result as it becomes available
         for chunk in result:
             yield chunk
 

libs/langchain/langchain/agents/loading.py

@@ -14,7 +14,7 @@ from langchain.agents.agent import BaseMultiActionAgent, BaseSingleActionAgent
 from langchain.agents.types import AGENT_TO_CLASS
 from langchain.chains.loading import load_chain, load_chain_from_config
 
-logger = logging.getLogger(__file__)
+logger = logging.getLogger(__name__)
 
 URL_BASE = "https://raw.githubusercontent.com/hwchase17/langchain-hub/master/agents/"
 

libs/langchain/langchain/agents/openai_functions_multi_agent/base.py

@@ -72,7 +72,7 @@ def _parse_ai_message(message: BaseMessage) -> Union[list[AgentAction], AgentFin
                 del _tool_input["action_name"]
             function_name = tool_schema["action_name"]
 
-            # HACK HACK HACK:
+            # A hack here:
             # The code that encodes tool input into Open AI uses a special variable
             # name called `__arg1` to handle old style tools that do not expose a
             # schema and expect a single string argument as an input.

libs/langchain/langchain/agents/output_parsers/openai_functions.py

@@ -55,7 +55,7 @@ class OpenAIFunctionsAgentOutputParser(AgentOutputParser):
                 )
                 raise OutputParserException(msg) from e
 
-            # HACK HACK HACK:
+            # A hack here:
             # The code that encodes tool input into Open AI uses a special variable
             # name called `__arg1` to handle old style tools that do not expose a
             # schema and expect a single string argument as an input.

libs/langchain/langchain/agents/output_parsers/tools.py

@@ -56,7 +56,7 @@ def parse_ai_message_to_tool_action(
                 )
                 raise OutputParserException(msg) from e
     for tool_call in tool_calls:
-        # HACK HACK HACK:
+        # A hack here:
         # The code that encodes tool input into Open AI uses a special variable
         # name called `__arg1` to handle old style tools that do not expose a
         # schema and expect a single string argument as an input.

libs/langchain/langchain/callbacks/streaming_aiter.py

@@ -8,7 +8,7 @@ from langchain_core.callbacks import AsyncCallbackHandler
 from langchain_core.outputs import LLMResult
 from typing_extensions import override
 
-# TODO If used by two LLM runs in parallel this won't work as expected
+# TODO: If used by two LLM runs in parallel this won't work as expected
 
 
 class AsyncIteratorCallbackHandler(AsyncCallbackHandler):
@@ -51,7 +51,7 @@ class AsyncIteratorCallbackHandler(AsyncCallbackHandler):
     async def on_llm_error(self, error: BaseException, **kwargs: Any) -> None:
         self.done.set()
 
-    # TODO implement the other methods
+    # TODO: implement the other methods
 
     async def aiter(self) -> AsyncIterator[str]:
         """Asynchronous iterator that yields tokens."""

libs/langchain/langchain/chains/natbot/crawler.py

@@ -1,3 +1,4 @@
+import logging
 import time
 from sys import platform
 from typing import (
@@ -11,6 +12,8 @@ from typing import (
 if TYPE_CHECKING:
     from playwright.sync_api import Browser, CDPSession, Page
 
+logger = logging.getLogger(__name__)
+
 black_listed_elements: set[str] = {
     "html",
     "head",
@@ -298,7 +301,7 @@ class Crawler:
 
             try:
                 cursor = layout_node_index.index(index)
-                # TODO replace this with proper cursoring, ignoring the fact this is
+                # TODO: replace this with proper cursoring, ignoring the fact this is
                 # O(n^2) for the moment
             except ValueError:
                 continue

libs/langchain/langchain/chat_models/base.py

@@ -535,12 +535,6 @@ def _check_pkg(pkg: str, *, pkg_kebab: Optional[str] = None) -> None:
         raise ImportError(msg)
 
 
-def _remove_prefix(s: str, prefix: str) -> str:
-    if s.startswith(prefix):
-        s = s[len(prefix) :]
-    return s
-
-
 _DECLARATIVE_METHODS = ("bind_tools", "with_structured_output")
 
 
@@ -608,7 +602,7 @@ class _ConfigurableModel(Runnable[LanguageModelInput, Any]):
     def _model_params(self, config: Optional[RunnableConfig]) -> dict:
         config = ensure_config(config)
         model_params = {
-            _remove_prefix(k, self._config_prefix): v
+            k.removeprefix(self._config_prefix): v
             for k, v in config.get("configurable", {}).items()
             if k.startswith(self._config_prefix)
         }
@@ -630,7 +624,7 @@ class _ConfigurableModel(Runnable[LanguageModelInput, Any]):
         remaining_config["configurable"] = {
             k: v
             for k, v in config.get("configurable", {}).items()
-            if _remove_prefix(k, self._config_prefix) not in model_params
+            if k.removeprefix(self._config_prefix) not in model_params
         }
         queued_declarative_operations = list(self._queued_declarative_operations)
         if remaining_config:

libs/langchain/pyproject.toml

@@ -143,70 +143,42 @@ ignore-regex = ".*(Stati Uniti|Tense=Pres).*"
 ignore-words-list = "momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure,damon,crate,aadd,symbl,precesses,accademia,nin"
 
 [tool.ruff.lint]
-select = [
+select = [ "ALL",]
-    "A",      # flake8-builtins
-    "ARG",    # flake8-unused-arguments
-    "ASYNC",  # flake8-async
-    "B",      # flake8-bugbear
-    "C4",     # flake8-comprehensions
-    "COM",    # flake8-commas
-    "D1",     # pydocstyle: missing docstring
-    "DTZ",    # flake8-datetimez
-    "E",      # pycodestyle error
-    "EM",     # flake8-errmsg
-    "F",      # pyflakes
-    "FA",     # flake8-future-annotations
-    "FBT",    # flake8-boolean-trap
-    "FLY",    # flake8-flynt
-    "G",      # flake8-logging-format
-    "I",      # isort
-    "ICN",    # flake8-import-conventions
-    "INT",    # flake8-gettext
-    "ISC",    # isort-comprehensions
-    "PERF",   # flake8-perf
-    "PGH",    # pygrep-hooks
-    "PIE",    # flake8-pie
-    "PL",     # pylint
-    "PT",     # flake8-pytest-style
-    "PTH",    # flake8-use-pathlib
-    "PYI",    # flake8-pyi
-    "Q",      # flake8-quotes
-    "RET",    # flake8-return
-    "RSE",    # flake8-rst-docstrings
-    "RUF",    # ruff
-    "S",      # flake8-bandit
-    "SIM",    # flake8-simplify
-    "SLF",    # flake8-self
-    "SLOT",   # flake8-slots
-    "T10",    # flake8-debugger
-    "T20",    # flake8-print
-    "TC",     # flake8-type-checking
-    "TID",    # flake8-tidy-imports
-    "TRY",    # tryceratops
-    "UP",     # pyupgrade
-    "W",      # pycodestyle warning
-    "YTT",    # flake8-2020
-]
 ignore = [
+    "C90",     # McCabe complexity
     "COM812",  # Messes with the formatter
-    "ISC001",  # Messes with the formatter
+    "FIX002",  # Line contains TODO
     "PERF203", # Rarely useful
-    "PLR09",   # Too many something (args, statements, etc)
+    "PLR09",   # Too many something (arg, statements, etc)
-    "S112",    # Rarely useful
     "RUF012",  # Doesn't play well with Pydantic
     "TC001",   # Doesn't play well with Pydantic
     "TC002",   # Doesn't play well with Pydantic
     "TC003",   # Doesn't play well with Pydantic
-    "UP007",   # pyupgrade: non-pep604-annotation-union
+    "TD002",   # Missing author in TODO
+    "TD003",   # Missing issue link in TODO
 
     # TODO rules
+    "ANN401",
+    "BLE",
     "D100",    # pydocstyle: missing docstring in public module
     "D104",    # pydocstyle: missing docstring in public package
+    "D2",
+    "D3",
+    "D4",
+    "ERA",
+    "N",
     "PLC0415", # pylint: import-outside-top-level
     "TRY301",  # tryceratops: raise-within-try
 ]
-unfixable = ["B028"] # People should intentionally tune the stacklevel
+unfixable = [
+    "B028",    # People should intentionally tune the stacklevel
+    "PLW1510", # People should intentionally set the check argument
+]
 
+flake8-annotations.allow-star-arg-any = true
+flake8-annotations.mypy-init-return = true
+flake8-type-checking.runtime-evaluated-base-classes = ["pydantic.BaseModel","langchain_core.load.serializable.Serializable","langchain_core.runnables.base.RunnableSerializable"]
+pep8-naming.classmethod-decorators = [ "classmethod", "langchain_core.utils.pydantic.pre_init", "pydantic.field_validator", "pydantic.v1.root_validator",]
 pydocstyle.convention = "google"
 pyupgrade.keep-runtime-typing = true
 
@@ -218,6 +190,13 @@ pyupgrade.keep-runtime-typing = true
     "SLF001",  # Private member access in tests
     "PLR2004", # Magic value comparisons
 ]
+"tests/integration_tests/examples/*.py" = [
+    "INP001",   # Not a package
+    "EXE001",   # Only examples
+]
+"scripts/*.py" = [
+    "INP001",   # Not a package
+]
 "langchain/chains/constitutional_ai/principles.py" = [
     "E501", # Line too long
 ]

libs/langchain/tests/unit_tests/agents/test_agent_iterator.py

@@ -229,8 +229,8 @@ def test_agent_iterator_properties_and_setters() -> None:
 
     assert isinstance(agent_iter, AgentExecutorIterator)
     assert isinstance(agent_iter.inputs, dict)
-    assert isinstance(agent_iter.callbacks, type(None))
+    assert agent_iter.callbacks is None
-    assert isinstance(agent_iter.tags, type(None))
+    assert agent_iter.tags is None
     assert isinstance(agent_iter.agent_executor, AgentExecutor)
 
     agent_iter.inputs = "New input"  # type: ignore[assignment]

libs/langchain/tests/unit_tests/chains/test_hyde.py

@@ -22,12 +22,12 @@ class FakeEmbeddings(Embeddings):
     @override
     def embed_documents(self, texts: list[str]) -> list[list[float]]:
         """Return random floats."""
-        return [list(np.random.uniform(0, 1, 10)) for _ in range(10)]
+        return [list(np.random.default_rng().uniform(0, 1, 10)) for _ in range(10)]
 
     @override
     def embed_query(self, text: str) -> list[float]:
         """Return random floats."""
-        return list(np.random.uniform(0, 1, 10))
+        return list(np.random.default_rng().uniform(0, 1, 10))
 
 
 class FakeLLM(BaseLLM):