Skip to content

The agent engineering platform.

chore(langchain): add ruff rules D1 (except D100 and D104) (#32123)

Christophe Bornet12ae42c5e90b
diff --git a/libs/langchain/langchain/agents/agent.py b/libs/langchain/langchain/agents/agent.py
index 198ab1f33c..323afb3342 100644
--- a/libs/langchain/langchain/agents/agent.py
+++ b/libs/langchain/langchain/agents/agent.py
@@ -64,6 +64,7 @@ class BaseSingleActionAgent(BaseModel):
return ["output"]
def get_allowed_tools(self) -> Optional[list[str]]:
+ """Get allowed tools."""
return None
@abstractmethod
diff --git a/libs/langchain/langchain/agents/agent_iterator.py b/libs/langchain/langchain/agents/agent_iterator.py
index 12ef5a198c..34479ab857 100644
--- a/libs/langchain/langchain/agents/agent_iterator.py
+++ b/libs/langchain/langchain/agents/agent_iterator.py
@@ -157,6 +157,12 @@ class AgentExecutorIterator:
outputs: dict[str, Any],
run_manager: Union[CallbackManagerForChainRun, AsyncCallbackManagerForChainRun],
) -> AddableDict:
+ """Make final outputs for the iterator.
+
+ Args:
+ outputs: The outputs from the agent executor.
+ run_manager: The run manager to use for callbacks.
+ """
# have access to intermediate steps by design in iterator,
# so return only outputs may as well always be true.
@@ -172,6 +178,7 @@ class AgentExecutorIterator:
return prepared_outputs
def __iter__(self: AgentExecutorIterator) -> Iterator[AddableDict]:
+ """Create an async iterator for the AgentExecutor."""
logger.debug("Initialising AgentExecutorIterator")
self.reset()
callback_manager = CallbackManager.configure(
diff --git a/libs/langchain/langchain/agents/openai_assistant/base.py b/libs/langchain/langchain/agents/openai_assistant/base.py
index c1e862b1d6..83a0829818 100644
--- a/libs/langchain/langchain/agents/openai_assistant/base.py
+++ b/libs/langchain/langchain/agents/openai_assistant/base.py
@@ -229,7 +229,7 @@ class OpenAIAssistantRunnable(RunnableSerializable[dict, OutputType]):
"""Use as a LangChain agent, compatible with the AgentExecutor."""
@model_validator(mode="after")
- def validate_async_client(self) -> Self:
+ def _validate_async_client(self) -> Self:
if self.async_client is None:
import openai
diff --git a/libs/langchain/langchain/agents/openai_functions_multi_agent/base.py b/libs/langchain/langchain/agents/openai_functions_multi_agent/base.py
index 5b25239131..5f9c06a269 100644
--- a/libs/langchain/langchain/agents/openai_functions_multi_agent/base.py
+++ b/libs/langchain/langchain/agents/openai_functions_multi_agent/base.py
@@ -125,7 +125,7 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
return [t.name for t in self.tools]
@model_validator(mode="after")
- def validate_prompt(self) -> Self:
+ def _validate_prompt(self) -> Self:
prompt: BasePromptTemplate = self.prompt
if "agent_scratchpad" not in prompt.input_variables:
msg = (
diff --git a/libs/langchain/langchain/agents/output_parsers/json.py b/libs/langchain/langchain/agents/output_parsers/json.py
index c78c3562d7..4e8cdd35fc 100644
--- a/libs/langchain/langchain/agents/output_parsers/json.py
+++ b/libs/langchain/langchain/agents/output_parsers/json.py
@@ -6,6 +6,7 @@ from typing import Union
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
from langchain_core.utils.json import parse_json_markdown
+from typing_extensions import override
from langchain.agents.agent import AgentOutputParser
@@ -40,6 +41,7 @@ class JSONAgentOutputParser(AgentOutputParser):
```
"""
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
try:
response = parse_json_markdown(text)
diff --git a/libs/langchain/langchain/agents/output_parsers/openai_functions.py b/libs/langchain/langchain/agents/output_parsers/openai_functions.py
index 586cf98046..e452d8d604 100644
--- a/libs/langchain/langchain/agents/output_parsers/openai_functions.py
+++ b/libs/langchain/langchain/agents/output_parsers/openai_functions.py
@@ -9,6 +9,7 @@ from langchain_core.messages import (
BaseMessage,
)
from langchain_core.outputs import ChatGeneration, Generation
+from typing_extensions import override
from langchain.agents.agent import AgentOutputParser
@@ -79,6 +80,7 @@ class OpenAIFunctionsAgentOutputParser(AgentOutputParser):
log=str(message.content),
)
+ @override
def parse_result(
self,
result: list[Generation],
@@ -91,6 +93,7 @@ class OpenAIFunctionsAgentOutputParser(AgentOutputParser):
message = result[0].message
return self.parse_ai_message(message)
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
msg = "Can only parse messages"
raise ValueError(msg)
diff --git a/libs/langchain/langchain/agents/output_parsers/openai_tools.py b/libs/langchain/langchain/agents/output_parsers/openai_tools.py
index df995af548..8db0ceb663 100644
--- a/libs/langchain/langchain/agents/output_parsers/openai_tools.py
+++ b/libs/langchain/langchain/agents/output_parsers/openai_tools.py
@@ -3,6 +3,7 @@ from typing import Union
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.messages import BaseMessage
from langchain_core.outputs import ChatGeneration, Generation
+from typing_extensions import override
from langchain.agents.agent import MultiActionAgentOutputParser
from langchain.agents.output_parsers.tools import (
@@ -53,6 +54,7 @@ class OpenAIToolsAgentOutputParser(MultiActionAgentOutputParser):
def _type(self) -> str:
return "openai-tools-agent-output-parser"
+ @override
def parse_result(
self,
result: list[Generation],
@@ -65,6 +67,7 @@ class OpenAIToolsAgentOutputParser(MultiActionAgentOutputParser):
message = result[0].message
return parse_ai_message_to_openai_tool_action(message)
+ @override
def parse(self, text: str) -> Union[list[AgentAction], AgentFinish]:
msg = "Can only parse messages"
raise ValueError(msg)
diff --git a/libs/langchain/langchain/agents/output_parsers/react_json_single_input.py b/libs/langchain/langchain/agents/output_parsers/react_json_single_input.py
index 2d5721c0f5..82782cd023 100644
--- a/libs/langchain/langchain/agents/output_parsers/react_json_single_input.py
+++ b/libs/langchain/langchain/agents/output_parsers/react_json_single_input.py
@@ -5,6 +5,7 @@ from typing import Union
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
+from typing_extensions import override
from langchain.agents.agent import AgentOutputParser
from langchain.agents.chat.prompt import FORMAT_INSTRUCTIONS
@@ -46,9 +47,11 @@ class ReActJsonSingleInputOutputParser(AgentOutputParser):
pattern: Pattern = re.compile(r"^.*?`{3}(?:json)?\n?(.*?)`{3}.*?$", re.DOTALL)
"""Regex pattern to parse the output."""
+ @override
def get_format_instructions(self) -> str:
return FORMAT_INSTRUCTIONS
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
includes_answer = FINAL_ANSWER_ACTION in text
try:
diff --git a/libs/langchain/langchain/agents/output_parsers/react_single_input.py b/libs/langchain/langchain/agents/output_parsers/react_single_input.py
index 20a66dbdbf..74626db59d 100644
--- a/libs/langchain/langchain/agents/output_parsers/react_single_input.py
+++ b/libs/langchain/langchain/agents/output_parsers/react_single_input.py
@@ -3,6 +3,7 @@ from typing import Union
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
+from typing_extensions import override
from langchain.agents.agent import AgentOutputParser
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
@@ -45,9 +46,11 @@ class ReActSingleInputOutputParser(AgentOutputParser):
"""
+ @override
def get_format_instructions(self) -> str:
return FORMAT_INSTRUCTIONS
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
includes_answer = FINAL_ANSWER_ACTION in text
regex = (
diff --git a/libs/langchain/langchain/agents/output_parsers/self_ask.py b/libs/langchain/langchain/agents/output_parsers/self_ask.py
index 4f0c101a88..be4d468ff1 100644
--- a/libs/langchain/langchain/agents/output_parsers/self_ask.py
+++ b/libs/langchain/langchain/agents/output_parsers/self_ask.py
@@ -3,6 +3,7 @@ from typing import Union
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
+from typing_extensions import override
from langchain.agents.agent import AgentOutputParser
@@ -35,6 +36,7 @@ class SelfAskOutputParser(AgentOutputParser):
followups: Sequence[str] = ("Follow up:", "Followup:")
finish_string: str = "So the final answer is: "
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
last_line = text.split("\n")[-1]
if not any(follow in last_line for follow in self.followups):
diff --git a/libs/langchain/langchain/agents/output_parsers/tools.py b/libs/langchain/langchain/agents/output_parsers/tools.py
index c7bf005553..10ebd3c3df 100644
--- a/libs/langchain/langchain/agents/output_parsers/tools.py
+++ b/libs/langchain/langchain/agents/output_parsers/tools.py
@@ -10,11 +10,14 @@ from langchain_core.messages import (
ToolCall,
)
from langchain_core.outputs import ChatGeneration, Generation
+from typing_extensions import override
from langchain.agents.agent import MultiActionAgentOutputParser
class ToolAgentAction(AgentActionMessageLog):
+ """ "Tool agent action."""
+
tool_call_id: str
"""Tool call that this message is responding to."""
@@ -90,6 +93,7 @@ class ToolsAgentOutputParser(MultiActionAgentOutputParser):
def _type(self) -> str:
return "tools-agent-output-parser"
+ @override
def parse_result(
self,
result: list[Generation],
@@ -102,6 +106,7 @@ class ToolsAgentOutputParser(MultiActionAgentOutputParser):
message = result[0].message
return parse_ai_message_to_tool_action(message)
+ @override
def parse(self, text: str) -> Union[list[AgentAction], AgentFinish]:
msg = "Can only parse messages"
raise ValueError(msg)
diff --git a/libs/langchain/langchain/agents/output_parsers/xml.py b/libs/langchain/langchain/agents/output_parsers/xml.py
index 7d3e73c7ba..3db5117e7c 100644
--- a/libs/langchain/langchain/agents/output_parsers/xml.py
+++ b/libs/langchain/langchain/agents/output_parsers/xml.py
@@ -3,6 +3,7 @@ from typing import Literal, Optional, Union
from langchain_core.agents import AgentAction, AgentFinish
from pydantic import Field
+from typing_extensions import override
from langchain.agents import AgentOutputParser
@@ -65,6 +66,7 @@ class XMLAgentOutputParser(AgentOutputParser):
None - no escaping is applied, which may lead to parsing conflicts.
"""
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
# Check for tool invocation first
tool_matches = re.findall(r"<tool>(.*?)</tool>", text, re.DOTALL)
@@ -115,6 +117,7 @@ class XMLAgentOutputParser(AgentOutputParser):
)
raise ValueError(msg)
+ @override
def get_format_instructions(self) -> str:
raise NotImplementedError
diff --git a/libs/langchain/langchain/agents/react/output_parser.py b/libs/langchain/langchain/agents/react/output_parser.py
index eceaa27eda..f4118a157f 100644
--- a/libs/langchain/langchain/agents/react/output_parser.py
+++ b/libs/langchain/langchain/agents/react/output_parser.py
@@ -3,6 +3,7 @@ from typing import Union
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
+from typing_extensions import override
from langchain.agents.agent import AgentOutputParser
@@ -10,6 +11,7 @@ from langchain.agents.agent import AgentOutputParser
class ReActOutputParser(AgentOutputParser):
"""Output parser for the ReAct agent."""
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
action_prefix = "Action: "
if not text.strip().split("\n")[-1].startswith(action_prefix):
diff --git a/libs/langchain/langchain/agents/schema.py b/libs/langchain/langchain/agents/schema.py
index 7cad47f4c4..74a0c9c498 100644
--- a/libs/langchain/langchain/agents/schema.py
+++ b/libs/langchain/langchain/agents/schema.py
@@ -2,12 +2,14 @@ from typing import Any
from langchain_core.agents import AgentAction
from langchain_core.prompts.chat import ChatPromptTemplate
+from typing_extensions import override
class AgentScratchPadChatPromptTemplate(ChatPromptTemplate):
"""Chat prompt template for the agent scratchpad."""
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
diff --git a/libs/langchain/langchain/agents/structured_chat/base.py b/libs/langchain/langchain/agents/structured_chat/base.py
index 04379142e5..320fd8273b 100644
--- a/libs/langchain/langchain/agents/structured_chat/base.py
+++ b/libs/langchain/langchain/agents/structured_chat/base.py
@@ -16,6 +16,7 @@ from langchain_core.runnables import Runnable, RunnablePassthrough
from langchain_core.tools import BaseTool
from langchain_core.tools.render import ToolsRenderer
from pydantic import Field
+from typing_extensions import override
from langchain.agents.agent import Agent, AgentOutputParser
from langchain.agents.format_scratchpad import format_log_to_str
@@ -78,10 +79,12 @@ class StructuredChatAgent(Agent):
return StructuredChatOutputParserWithRetries.from_llm(llm=llm)
@property
+ @override
def _stop(self) -> list[str]:
return ["Observation:"]
@classmethod
+ @override
def create_prompt(
cls,
tools: Sequence[BaseTool],
diff --git a/libs/langchain/langchain/agents/structured_chat/output_parser.py b/libs/langchain/langchain/agents/structured_chat/output_parser.py
index 94d3c12c9b..151e7f12e3 100644
--- a/libs/langchain/langchain/agents/structured_chat/output_parser.py
+++ b/libs/langchain/langchain/agents/structured_chat/output_parser.py
@@ -10,6 +10,7 @@ from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
from langchain_core.language_models import BaseLanguageModel
from pydantic import Field
+from typing_extensions import override
from langchain.agents.agent import AgentOutputParser
from langchain.agents.structured_chat.prompt import FORMAT_INSTRUCTIONS
@@ -27,10 +28,12 @@ class StructuredChatOutputParser(AgentOutputParser):
pattern: Pattern = re.compile(r"```(?:json\s+)?(\W.*?)```", re.DOTALL)
"""Regex pattern to parse the output."""
+ @override
def get_format_instructions(self) -> str:
"""Returns formatting instructions for the given output parser."""
return self.format_instructions
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
try:
action_match = self.pattern.search(text)
@@ -65,9 +68,11 @@ class StructuredChatOutputParserWithRetries(AgentOutputParser):
output_fixing_parser: Optional[OutputFixingParser] = None
"""The output fixing parser to use."""
+ @override
def get_format_instructions(self) -> str:
return FORMAT_INSTRUCTIONS
+ @override
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
try:
if self.output_fixing_parser is not None:
@@ -83,6 +88,14 @@ class StructuredChatOutputParserWithRetries(AgentOutputParser):
llm: Optional[BaseLanguageModel] = None,
base_parser: Optional[StructuredChatOutputParser] = None,
) -> StructuredChatOutputParserWithRetries:
+ """Create a StructuredChatOutputParserWithRetries from a language model.
+
+ Args:
+ llm: The language model to use.
+ base_parser: An optional StructuredChatOutputParser to use.
+ Returns:
+ An instance of StructuredChatOutputParserWithRetries.
+ """
if llm is not None:
base_parser = base_parser or StructuredChatOutputParser()
output_fixing_parser: OutputFixingParser = OutputFixingParser.from_llm(
diff --git a/libs/langchain/langchain/agents/xml/base.py b/libs/langchain/langchain/agents/xml/base.py
index d6a77c9dee..13bc7a66bc 100644
--- a/libs/langchain/langchain/agents/xml/base.py
+++ b/libs/langchain/langchain/agents/xml/base.py
@@ -10,6 +10,7 @@ from langchain_core.prompts.chat import AIMessagePromptTemplate, ChatPromptTempl
from langchain_core.runnables import Runnable, RunnablePassthrough
from langchain_core.tools import BaseTool
from langchain_core.tools.render import ToolsRenderer, render_text_description
+from typing_extensions import override
from langchain.agents.agent import BaseSingleActionAgent
from langchain.agents.format_scratchpad import format_xml
@@ -45,11 +46,13 @@ class XMLAgent(BaseSingleActionAgent):
"""Chain to use to predict action."""
@property
+ @override
def input_keys(self) -> list[str]:
return ["input"]
@staticmethod
def get_default_prompt() -> ChatPromptTemplate:
+ """Return the default prompt for the XML agent."""
base_prompt = ChatPromptTemplate.from_template(agent_instructions)
return base_prompt + AIMessagePromptTemplate.from_template(
"{intermediate_steps}",
@@ -57,8 +60,10 @@ class XMLAgent(BaseSingleActionAgent):
@staticmethod
def get_default_output_parser() -> XMLAgentOutputParser:
+ """Return an XMLAgentOutputParser."""
return XMLAgentOutputParser()
+ @override
def plan(
self,
intermediate_steps: list[tuple[AgentAction, str]],
@@ -83,6 +88,7 @@ class XMLAgent(BaseSingleActionAgent):
response = self.llm_chain(inputs, callbacks=callbacks)
return response[self.llm_chain.output_key]
+ @override
async def aplan(
self,
intermediate_steps: list[tuple[AgentAction, str]],
diff --git a/libs/langchain/langchain/callbacks/streaming_aiter.py b/libs/langchain/langchain/callbacks/streaming_aiter.py
index ff58c3f8e3..f00e4f3e09 100644
--- a/libs/langchain/langchain/callbacks/streaming_aiter.py
+++ b/libs/langchain/langchain/callbacks/streaming_aiter.py
@@ -6,6 +6,7 @@ from typing import Any, Literal, Union, cast
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
@@ -19,12 +20,15 @@ class AsyncIteratorCallbackHandler(AsyncCallbackHandler):
@property
def always_verbose(self) -> bool:
+ """Always verbose."""
return True
def __init__(self) -> None:
+ """Instantiate AsyncIteratorCallbackHandler."""
self.queue = asyncio.Queue()
self.done = asyncio.Event()
+ @override
async def on_llm_start(
self,
serialized: dict[str, Any],
@@ -34,19 +38,23 @@ class AsyncIteratorCallbackHandler(AsyncCallbackHandler):
# If two calls are made in a row, this resets the state
self.done.clear()
+ @override
async def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
if token is not None and token != "":
self.queue.put_nowait(token)
+ @override
async def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
self.done.set()
+ @override
async def on_llm_error(self, error: BaseException, **kwargs: Any) -> None:
self.done.set()
# TODO implement the other methods
async def aiter(self) -> AsyncIterator[str]:
+ """Asynchronous iterator that yields tokens."""
while not self.queue.empty() or not self.done.is_set():
# Wait for the next token in the queue,
# but stop waiting if the done event is set
diff --git a/libs/langchain/langchain/callbacks/streaming_aiter_final_only.py b/libs/langchain/langchain/callbacks/streaming_aiter_final_only.py
index b9f91788e3..dbf125bd17 100644
--- a/libs/langchain/langchain/callbacks/streaming_aiter_final_only.py
+++ b/libs/langchain/langchain/callbacks/streaming_aiter_final_only.py
@@ -3,6 +3,7 @@ from __future__ import annotations
from typing import Any, Optional
from langchain_core.outputs import LLMResult
+from typing_extensions import override
from langchain.callbacks.streaming_aiter import AsyncIteratorCallbackHandler
@@ -15,6 +16,7 @@ class AsyncFinalIteratorCallbackHandler(AsyncIteratorCallbackHandler):
"""
def append_to_last_tokens(self, token: str) -> None:
+ """Append token to the last tokens."""
self.last_tokens.append(token)
self.last_tokens_stripped.append(token.strip())
if len(self.last_tokens) > len(self.answer_prefix_tokens):
@@ -22,6 +24,7 @@ class AsyncFinalIteratorCallbackHandler(AsyncIteratorCallbackHandler):
self.last_tokens_stripped.pop(0)
def check_if_answer_reached(self) -> bool:
+ """Check if the answer has been reached."""
if self.strip_tokens:
return self.last_tokens_stripped == self.answer_prefix_tokens_stripped
return self.last_tokens == self.answer_prefix_tokens
@@ -60,6 +63,7 @@ class AsyncFinalIteratorCallbackHandler(AsyncIteratorCallbackHandler):
self.stream_prefix = stream_prefix
self.answer_reached = False
+ @override
async def on_llm_start(
self,
serialized: dict[str, Any],
@@ -70,10 +74,12 @@ class AsyncFinalIteratorCallbackHandler(AsyncIteratorCallbackHandler):
self.done.clear()
self.answer_reached = False
+ @override
async def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
if self.answer_reached:
self.done.set()
+ @override
async def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
# Remember the last n tokens, where n = len(answer_prefix_tokens)
self.append_to_last_tokens(token)
diff --git a/libs/langchain/langchain/callbacks/streaming_stdout_final_only.py b/libs/langchain/langchain/callbacks/streaming_stdout_final_only.py
index 5dbbf700e8..ddcfa1d456 100644
--- a/libs/langchain/langchain/callbacks/streaming_stdout_final_only.py
+++ b/libs/langchain/langchain/callbacks/streaming_stdout_final_only.py
@@ -16,6 +16,7 @@ class FinalStreamingStdOutCallbackHandler(StreamingStdOutCallbackHandler):
"""
def append_to_last_tokens(self, token: str) -> None:
+ """Append token to the last tokens."""
self.last_tokens.append(token)
self.last_tokens_stripped.append(token.strip())
if len(self.last_tokens) > len(self.answer_prefix_tokens):
@@ -23,6 +24,7 @@ class FinalStreamingStdOutCallbackHandler(StreamingStdOutCallbackHandler):
self.last_tokens_stripped.pop(0)
def check_if_answer_reached(self) -> bool:
+ """Check if the answer has been reached."""
if self.strip_tokens:
return self.last_tokens_stripped == self.answer_prefix_tokens_stripped
return self.last_tokens == self.answer_prefix_tokens
diff --git a/libs/langchain/langchain/callbacks/tracers/logging.py b/libs/langchain/langchain/callbacks/tracers/logging.py
index 35d075dd0d..94e42c8049 100644
--- a/libs/langchain/langchain/callbacks/tracers/logging.py
+++ b/libs/langchain/langchain/callbacks/tracers/logging.py
@@ -7,6 +7,7 @@ from uuid import UUID
from langchain_core.exceptions import TracerException
from langchain_core.tracers.stdout import FunctionCallbackHandler
from langchain_core.utils.input import get_bolded_text, get_colored_text
+from typing_extensions import override
class LoggingCallbackHandler(FunctionCallbackHandler):
@@ -21,6 +22,15 @@ class LoggingCallbackHandler(FunctionCallbackHandler):
extra: Optional[dict] = None,
**kwargs: Any,
) -> None:
+ """
+ Initialize the LoggingCallbackHandler.
+
+ Args:
+ logger: the logger to use for logging
+ log_level: the logging level (default: logging.INFO)
+ extra: the extra context to log (default: None)
+ **kwargs:
+ """
log_method = getattr(logger, logging.getLevelName(level=log_level).lower())
def callback(text: str) -> None:
@@ -28,6 +38,7 @@ class LoggingCallbackHandler(FunctionCallbackHandler):
super().__init__(function=callback, **kwargs)
+ @override
def on_text(
self,
text: str,
diff --git a/libs/langchain/langchain/chains/api/base.py b/libs/langchain/langchain/chains/api/base.py
index 454993c068..9a03f142ac 100644
--- a/libs/langchain/langchain/chains/api/base.py
+++ b/libs/langchain/langchain/chains/api/base.py
@@ -386,7 +386,10 @@ try:
except ImportError:
class APIChain: # type: ignore[no-redef]
+ """Raise an ImportError if APIChain is used without langchain_community."""
+
def __init__(self, *args: Any, **kwargs: Any) -> None:
+ """Raise an ImportError if APIChain is used without langchain_community."""
msg = (
"To use the APIChain, you must install the langchain_community package."
"pip install langchain_community"
diff --git a/libs/langchain/langchain/chains/base.py b/libs/langchain/langchain/chains/base.py
index ffba114e2c..11d7b7fb97 100644
--- a/libs/langchain/langchain/chains/base.py
+++ b/libs/langchain/langchain/chains/base.py
@@ -108,6 +108,7 @@ class Chain(RunnableSerializable[dict[str, Any], dict[str, Any]], ABC):
arbitrary_types_allowed=True,
)
+ @override
def get_input_schema(
self,
config: Optional[RunnableConfig] = None,
@@ -115,6 +116,7 @@ class Chain(RunnableSerializable[dict[str, Any], dict[str, Any]], ABC):
# This is correct, but pydantic typings/mypy don't think so.
return create_model("ChainInput", **dict.fromkeys(self.input_keys, (Any, None)))
+ @override
def get_output_schema(
self,
config: Optional[RunnableConfig] = None,
diff --git a/libs/langchain/langchain/chains/combine_documents/base.py b/libs/langchain/langchain/chains/combine_documents/base.py
index 5c24b64f1a..d0fc8ca77c 100644
--- a/libs/langchain/langchain/chains/combine_documents/base.py
+++ b/libs/langchain/langchain/chains/combine_documents/base.py
@@ -14,6 +14,7 @@ from langchain_core.runnables.config import RunnableConfig
from langchain_core.utils.pydantic import create_model
from langchain_text_splitters import RecursiveCharacterTextSplitter, TextSplitter
from pydantic import BaseModel, Field
+from typing_extensions import override
from langchain.chains.base import Chain
@@ -46,6 +47,7 @@ class BaseCombineDocumentsChain(Chain, ABC):
input_key: str = "input_documents" #: :meta private:
output_key: str = "output_text" #: :meta private:
+ @override
def get_input_schema(
self,
config: Optional[RunnableConfig] = None,
@@ -55,6 +57,7 @@ class BaseCombineDocumentsChain(Chain, ABC):
**{self.input_key: (list[Document], None)},
)
+ @override
def get_output_schema(
self,
config: Optional[RunnableConfig] = None,
@@ -253,6 +256,7 @@ class AnalyzeDocumentChain(Chain):
"""
return self.combine_docs_chain.output_keys
+ @override
def get_input_schema(
self,
config: Optional[RunnableConfig] = None,
@@ -262,6 +266,7 @@ class AnalyzeDocumentChain(Chain):
**{self.input_key: (str, None)},
)
+ @override
def get_output_schema(
self,
config: Optional[RunnableConfig] = None,
diff --git a/libs/langchain/langchain/chains/combine_documents/map_reduce.py b/libs/langchain/langchain/chains/combine_documents/map_reduce.py
index bab85195cd..0b1b4c1450 100644
--- a/libs/langchain/langchain/chains/combine_documents/map_reduce.py
+++ b/libs/langchain/langchain/chains/combine_documents/map_reduce.py
@@ -10,6 +10,7 @@ from langchain_core.documents import Document
from langchain_core.runnables.config import RunnableConfig
from langchain_core.utils.pydantic import create_model
from pydantic import BaseModel, ConfigDict, model_validator
+from typing_extensions import override
from langchain.chains.combine_documents.base import BaseCombineDocumentsChain
from langchain.chains.combine_documents.reduce import ReduceDocumentsChain
@@ -111,6 +112,7 @@ class MapReduceDocumentsChain(BaseCombineDocumentsChain):
return_intermediate_steps: bool = False
"""Return the results of the map steps in the output."""
+ @override
def get_output_schema(
self,
config: Optional[RunnableConfig] = None,
diff --git a/libs/langchain/langchain/chains/combine_documents/map_rerank.py b/libs/langchain/langchain/chains/combine_documents/map_rerank.py
index 743c2f7282..32323bf1e9 100644
--- a/libs/langchain/langchain/chains/combine_documents/map_rerank.py
+++ b/libs/langchain/langchain/chains/combine_documents/map_rerank.py
@@ -11,7 +11,7 @@ from langchain_core.documents import Document
from langchain_core.runnables.config import RunnableConfig
from langchain_core.utils.pydantic import create_model
from pydantic import BaseModel, ConfigDict, model_validator
-from typing_extensions import Self
+from typing_extensions import Self, override
from langchain.chains.combine_documents.base import BaseCombineDocumentsChain
from langchain.chains.llm import LLMChain
@@ -91,6 +91,7 @@ class MapRerankDocumentsChain(BaseCombineDocumentsChain):
extra="forbid",
)
+ @override
def get_output_schema(
self,
config: Optional[RunnableConfig] = None,
diff --git a/libs/langchain/langchain/chains/combine_documents/stuff.py b/libs/langchain/langchain/chains/combine_documents/stuff.py
index a4cefc8998..89b0674385 100644
--- a/libs/langchain/langchain/chains/combine_documents/stuff.py
+++ b/libs/langchain/langchain/chains/combine_documents/stuff.py
@@ -10,6 +10,7 @@ from langchain_core.output_parsers import BaseOutputParser, StrOutputParser
from langchain_core.prompts import BasePromptTemplate, format_document
from langchain_core.runnables import Runnable, RunnablePassthrough
from pydantic import ConfigDict, Field, model_validator
+from typing_extensions import override
from langchain.chains.combine_documents.base import (
DEFAULT_DOCUMENT_PROMPT,
@@ -189,6 +190,7 @@ class StuffDocumentsChain(BaseCombineDocumentsChain):
return values
@property
+ @override
def input_keys(self) -> list[str]:
extra_keys = [
k for k in self.llm_chain.input_keys if k != self.document_variable_name
diff --git a/libs/langchain/langchain/chains/constitutional_ai/base.py b/libs/langchain/langchain/chains/constitutional_ai/base.py
index bdaddaa7cb..cfe29606dc 100644
--- a/libs/langchain/langchain/chains/constitutional_ai/base.py
+++ b/libs/langchain/langchain/chains/constitutional_ai/base.py
@@ -200,6 +200,12 @@ class ConstitutionalChain(Chain):
cls,
names: Optional[list[str]] = None,
) -> list[ConstitutionalPrinciple]:
+ """Get constitutional principles by name.
+
+ Args:
+ names: List of names of constitutional principles to retrieve.
+ If None (default), all principles are returned.
+ """
if names is None:
return list(PRINCIPLES.values())
return [PRINCIPLES[name] for name in names]
diff --git a/libs/langchain/langchain/chains/conversation/base.py b/libs/langchain/langchain/chains/conversation/base.py
index fd7dea5d73..428031d278 100644
--- a/libs/langchain/langchain/chains/conversation/base.py
+++ b/libs/langchain/langchain/chains/conversation/base.py
@@ -4,7 +4,7 @@ from langchain_core._api import deprecated
from langchain_core.memory import BaseMemory
from langchain_core.prompts import BasePromptTemplate
from pydantic import ConfigDict, Field, model_validator
-from typing_extensions import Self
+from typing_extensions import Self, override
from langchain.chains.conversation.prompt import PROMPT
from langchain.chains.llm import LLMChain
@@ -112,6 +112,7 @@ class ConversationChain(LLMChain):
)
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
diff --git a/libs/langchain/langchain/chains/conversational_retrieval/base.py b/libs/langchain/langchain/chains/conversational_retrieval/base.py
index 8a7934472a..9fb89bd027 100644
--- a/libs/langchain/langchain/chains/conversational_retrieval/base.py
+++ b/libs/langchain/langchain/chains/conversational_retrieval/base.py
@@ -22,6 +22,7 @@ from langchain_core.retrievers import BaseRetriever
from langchain_core.runnables import RunnableConfig
from langchain_core.vectorstores import VectorStore
from pydantic import BaseModel, ConfigDict, Field, model_validator
+from typing_extensions import override
from langchain.chains.base import Chain
from langchain.chains.combine_documents.base import BaseCombineDocumentsChain
@@ -109,6 +110,7 @@ class BaseConversationalRetrievalChain(Chain):
"""Input keys."""
return ["question", "chat_history"]
+ @override
def get_input_schema(
self,
config: Optional[RunnableConfig] = None,
@@ -242,6 +244,7 @@ class BaseConversationalRetrievalChain(Chain):
output["generated_question"] = new_question
return output
+ @override
def save(self, file_path: Union[Path, str]) -> None:
if self.get_chat_history:
msg = "Chain not saveable when `get_chat_history` is not None."
@@ -500,7 +503,7 @@ class ChatVectorDBChain(BaseConversationalRetrievalChain):
@model_validator(mode="before")
@classmethod
- def raise_deprecation(cls, values: dict) -> Any:
+ def _raise_deprecation(cls, values: dict) -> Any:
warnings.warn(
"`ChatVectorDBChain` is deprecated - "
"please use `from langchain.chains import ConversationalRetrievalChain`",
diff --git a/libs/langchain/langchain/chains/elasticsearch_database/base.py b/libs/langchain/langchain/chains/elasticsearch_database/base.py
index d57c97f1c6..632d5d2fbc 100644
--- a/libs/langchain/langchain/chains/elasticsearch_database/base.py
+++ b/libs/langchain/langchain/chains/elasticsearch_database/base.py
@@ -58,7 +58,7 @@ class ElasticsearchDatabaseChain(Chain):
)
@model_validator(mode="after")
- def validate_indices(self) -> Self:
+ def _validate_indices(self) -> Self:
if self.include_indices and self.ignore_indices:
msg = "Cannot specify both 'include_indices' and 'ignore_indices'."
raise ValueError(msg)
diff --git a/libs/langchain/langchain/chains/flare/base.py b/libs/langchain/langchain/chains/flare/base.py
index cb1d33e000..34a31b2a1e 100644
--- a/libs/langchain/langchain/chains/flare/base.py
+++ b/libs/langchain/langchain/chains/flare/base.py
@@ -15,6 +15,7 @@ from langchain_core.prompts import BasePromptTemplate
from langchain_core.retrievers import BaseRetriever
from langchain_core.runnables import Runnable
from pydantic import Field
+from typing_extensions import override
from langchain.chains.base import Chain
from langchain.chains.flare.prompts import (
@@ -44,6 +45,7 @@ class QuestionGeneratorChain(LLMChain):
"""Prompt template for the chain."""
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
diff --git a/libs/langchain/langchain/chains/flare/prompts.py b/libs/langchain/langchain/chains/flare/prompts.py
index 629badffc5..30efa0743c 100644
--- a/libs/langchain/langchain/chains/flare/prompts.py
+++ b/libs/langchain/langchain/chains/flare/prompts.py
@@ -1,5 +1,6 @@
from langchain_core.output_parsers import BaseOutputParser
from langchain_core.prompts import PromptTemplate
+from typing_extensions import override
class FinishedOutputParser(BaseOutputParser[tuple[str, bool]]):
@@ -8,6 +9,7 @@ class FinishedOutputParser(BaseOutputParser[tuple[str, bool]]):
finished_value: str = "FINISHED"
"""Value that indicates the output is finished."""
+ @override
def parse(self, text: str) -> tuple[str, bool]:
cleaned = text.strip()
finished = self.finished_value in cleaned
diff --git a/libs/langchain/langchain/chains/llm.py b/libs/langchain/langchain/chains/llm.py
index a5d8c3e47b..ca43d7a9e8 100644
--- a/libs/langchain/langchain/chains/llm.py
+++ b/libs/langchain/langchain/chains/llm.py
@@ -32,6 +32,7 @@ from langchain_core.runnables import (
from langchain_core.runnables.configurable import DynamicRunnable
from langchain_core.utils.input import get_colored_text
from pydantic import ConfigDict, Field
+from typing_extensions import override
from langchain.chains.base import Chain
@@ -76,6 +77,7 @@ class LLMChain(Chain):
"""
@classmethod
+ @override
def is_lc_serializable(self) -> bool:
return True
diff --git a/libs/langchain/langchain/chains/llm_checker/base.py b/libs/langchain/langchain/chains/llm_checker/base.py
index a8cbd11f29..66db6394b8 100644
--- a/libs/langchain/langchain/chains/llm_checker/base.py
+++ b/libs/langchain/langchain/chains/llm_checker/base.py
@@ -106,7 +106,7 @@ class LLMCheckerChain(Chain):
@model_validator(mode="before")
@classmethod
- def raise_deprecation(cls, values: dict) -> Any:
+ def _raise_deprecation(cls, values: dict) -> Any:
if "llm" in values:
warnings.warn(
"Directly instantiating an LLMCheckerChain with an llm is deprecated. "
@@ -179,6 +179,16 @@ class LLMCheckerChain(Chain):
revised_answer_prompt: PromptTemplate = REVISED_ANSWER_PROMPT,
**kwargs: Any,
) -> LLMCheckerChain:
+ """Create an LLMCheckerChain from a language model.
+
+ Args:
+ llm: a language model
+ create_draft_answer_prompt: prompt to create a draft answer
+ list_assertions_prompt: prompt to list assertions
+ check_assertions_prompt: prompt to check assertions
+ revised_answer_prompt: prompt to revise the answer
+ **kwargs: additional arguments
+ """
question_to_checked_assertions_chain = (
_load_question_to_checked_assertions_chain(
llm,
diff --git a/libs/langchain/langchain/chains/llm_math/base.py b/libs/langchain/langchain/chains/llm_math/base.py
index 58ea43c5af..d55d52c71a 100644
--- a/libs/langchain/langchain/chains/llm_math/base.py
+++ b/libs/langchain/langchain/chains/llm_math/base.py
@@ -163,7 +163,7 @@ class LLMMathChain(Chain):
@model_validator(mode="before")
@classmethod
- def raise_deprecation(cls, values: dict) -> Any:
+ def _raise_deprecation(cls, values: dict) -> Any:
try:
import numexpr # noqa: F401
except ImportError as e:
@@ -307,5 +307,12 @@ class LLMMathChain(Chain):
prompt: BasePromptTemplate = PROMPT,
**kwargs: Any,
) -> LLMMathChain:
+ """Create a LLMMathChain from a language model.
+
+ Args:
+ llm: a language model
+ prompt: a prompt template
+ **kwargs: additional arguments
+ """
llm_chain = LLMChain(llm=llm, prompt=prompt)
return cls(llm_chain=llm_chain, **kwargs)
diff --git a/libs/langchain/langchain/chains/llm_summarization_checker/base.py b/libs/langchain/langchain/chains/llm_summarization_checker/base.py
index 7b75b9917c..a4885b7701 100644
--- a/libs/langchain/langchain/chains/llm_summarization_checker/base.py
+++ b/libs/langchain/langchain/chains/llm_summarization_checker/base.py
@@ -112,7 +112,7 @@ class LLMSummarizationCheckerChain(Chain):
@model_validator(mode="before")
@classmethod
- def raise_deprecation(cls, values: dict) -> Any:
+ def _raise_deprecation(cls, values: dict) -> Any:
if "llm" in values:
warnings.warn(
"Directly instantiating an LLMSummarizationCheckerChain with an llm is "
@@ -194,6 +194,17 @@ class LLMSummarizationCheckerChain(Chain):
verbose: bool = False, # noqa: FBT001,FBT002
**kwargs: Any,
) -> LLMSummarizationCheckerChain:
+ """Create a LLMSummarizationCheckerChain from a language model.
+
+ Args:
+ llm: a language model
+ create_assertions_prompt: prompt to create assertions
+ check_assertions_prompt: prompt to check assertions
+ revised_summary_prompt: prompt to revise summary
+ are_all_true_prompt: prompt to check if all assertions are true
+ verbose: whether to print verbose output
+ **kwargs: additional arguments
+ """
chain = _load_sequential_chain(
llm,
create_assertions_prompt,
diff --git a/libs/langchain/langchain/chains/loading.py b/libs/langchain/langchain/chains/loading.py
index 5255dc6b42..a24365b808 100644
--- a/libs/langchain/langchain/chains/loading.py
+++ b/libs/langchain/langchain/chains/loading.py
@@ -40,6 +40,7 @@ try:
except ImportError:
def load_llm(*args: Any, **kwargs: Any) -> None:
+ """Import error for load_llm."""
msg = (
"To use this load_llm functionality you must install the "
"langchain_community package. "
@@ -48,6 +49,7 @@ except ImportError:
raise ImportError(msg)
def load_llm_from_config(*args: Any, **kwargs: Any) -> None:
+ """Import error for load_llm_from_config."""
msg = (
"To use this load_llm_from_config functionality you must install the "
"langchain_community package. "
diff --git a/libs/langchain/langchain/chains/natbot/base.py b/libs/langchain/langchain/chains/natbot/base.py
index f7ce4ca152..3d3303d286 100644
--- a/libs/langchain/langchain/chains/natbot/base.py
+++ b/libs/langchain/langchain/chains/natbot/base.py
@@ -66,7 +66,7 @@ class NatBotChain(Chain):
@model_validator(mode="before")
@classmethod
- def raise_deprecation(cls, values: dict) -> Any:
+ def _raise_deprecation(cls, values: dict) -> Any:
if "llm" in values:
warnings.warn(
"Directly instantiating an NatBotChain with an llm is deprecated. "
diff --git a/libs/langchain/langchain/chains/natbot/crawler.py b/libs/langchain/langchain/chains/natbot/crawler.py
index 00a5dd38a6..f42fc1c0e0 100644
--- a/libs/langchain/langchain/chains/natbot/crawler.py
+++ b/libs/langchain/langchain/chains/natbot/crawler.py
@@ -61,6 +61,7 @@ class Crawler:
"""
def __init__(self) -> None:
+ """Initialize the crawler."""
try:
from playwright.sync_api import sync_playwright
except ImportError as e:
@@ -78,11 +79,22 @@ class Crawler:
self.client: CDPSession
def go_to_page(self, url: str) -> None:
+ """Navigate to the given URL.
+
+ Args:
+ url: The URL to navigate to. If it does not contain a scheme, it will be
+ prefixed with "http://".
+ """
self.page.goto(url=url if "://" in url else "http://" + url)
self.client = self.page.context.new_cdp_session(self.page)
self.page_element_buffer = {}
def scroll(self, direction: str) -> None:
+ """Scroll the page in the given direction.
+
+ Args:
+ direction: The direction to scroll in, either "up" or "down".
+ """
if direction == "up":
self.page.evaluate(
"(document.scrollingElement || document.body).scrollTop = (document.scrollingElement || document.body).scrollTop - window.innerHeight;" # noqa: E501
@@ -93,6 +105,11 @@ class Crawler:
)
def click(self, id_: Union[str, int]) -> None:
+ """Click on an element with the given id.
+
+ Args:
+ id_: The id of the element to click on.
+ """
# Inject javascript into the page which removes the target= attribute from links
js = """
links = document.getElementsByTagName("a");
@@ -112,13 +129,25 @@ class Crawler:
print("Could not find element") # noqa: T201
def type(self, id_: Union[str, int], text: str) -> None:
+ """Type text into an element with the given id.
+
+ Args:
+ id_: The id of the element to type into.
+ text: The text to type into the element.
+ """
self.click(id_)
self.page.keyboard.type(text)
def enter(self) -> None:
+ """Press the Enter key."""
self.page.keyboard.press("Enter")
def crawl(self) -> list[str]:
+ """Crawl the current page.
+
+ Returns:
+ A list of the elements in the viewport.
+ """
page = self.page
page_element_buffer = self.page_element_buffer
start = time.time()
diff --git a/libs/langchain/langchain/chains/openai_functions/citation_fuzzy_match.py b/libs/langchain/langchain/chains/openai_functions/citation_fuzzy_match.py
index a940709664..30412dcc61 100644
--- a/libs/langchain/langchain/chains/openai_functions/citation_fuzzy_match.py
+++ b/libs/langchain/langchain/chains/openai_functions/citation_fuzzy_match.py
@@ -45,6 +45,14 @@ class FactWithEvidence(BaseModel):
yield from s.spans()
def get_spans(self, context: str) -> Iterator[str]:
+ """Get spans of the substring quote in the context.
+
+ Args:
+ context: The context in which to find the spans of the substring quote.
+
+ Returns:
+ An iterator over the spans of the substring quote in the context.
+ """
for quote in self.substring_quote:
yield from self._get_span(quote, context)
diff --git a/libs/langchain/langchain/chains/openai_functions/openapi.py b/libs/langchain/langchain/chains/openai_functions/openapi.py
index a981d9fddb..c42c30e6f8 100644
--- a/libs/langchain/langchain/chains/openai_functions/openapi.py
+++ b/libs/langchain/langchain/chains/openai_functions/openapi.py
@@ -13,6 +13,7 @@ from langchain_core.output_parsers.openai_functions import JsonOutputFunctionsPa
from langchain_core.prompts import BasePromptTemplate, ChatPromptTemplate
from langchain_core.utils.input import get_colored_text
from requests import Response
+from typing_extensions import override
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
@@ -202,10 +203,12 @@ class SimpleRequestChain(Chain):
"""Key to use for the input of the request."""
@property
+ @override
def input_keys(self) -> list[str]:
return [self.input_key]
@property
+ @override
def output_keys(self) -> list[str]:
return [self.output_key]
diff --git a/libs/langchain/langchain/chains/qa_generation/base.py b/libs/langchain/langchain/chains/qa_generation/base.py
index 75eaf791d8..f203bd49c4 100644
--- a/libs/langchain/langchain/chains/qa_generation/base.py
+++ b/libs/langchain/langchain/chains/qa_generation/base.py
@@ -9,6 +9,7 @@ from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import BasePromptTemplate
from langchain_text_splitters import RecursiveCharacterTextSplitter, TextSplitter
from pydantic import Field
+from typing_extensions import override
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
@@ -103,10 +104,12 @@ class QAGenerationChain(Chain):
raise NotImplementedError
@property
+ @override
def input_keys(self) -> list[str]:
return [self.input_key]
@property
+ @override
def output_keys(self) -> list[str]:
return [self.output_key]
diff --git a/libs/langchain/langchain/chains/qa_with_sources/vector_db.py b/libs/langchain/langchain/chains/qa_with_sources/vector_db.py
index 26091871e4..e758bc87b1 100644
--- a/libs/langchain/langchain/chains/qa_with_sources/vector_db.py
+++ b/libs/langchain/langchain/chains/qa_with_sources/vector_db.py
@@ -73,7 +73,7 @@ class VectorDBQAWithSourcesChain(BaseQAWithSourcesChain):
@model_validator(mode="before")
@classmethod
- def raise_deprecation(cls, values: dict) -> Any:
+ def _raise_deprecation(cls, values: dict) -> Any:
warnings.warn(
"`VectorDBQAWithSourcesChain` is deprecated - "
"please use `from langchain.chains import RetrievalQAWithSourcesChain`",
diff --git a/libs/langchain/langchain/chains/query_constructor/base.py b/libs/langchain/langchain/chains/query_constructor/base.py
index ad7053678c..7d27376fc1 100644
--- a/libs/langchain/langchain/chains/query_constructor/base.py
+++ b/libs/langchain/langchain/chains/query_constructor/base.py
@@ -22,6 +22,7 @@ from langchain_core.structured_query import (
Operator,
StructuredQuery,
)
+from typing_extensions import override
from langchain.chains.llm import LLMChain
from langchain.chains.query_constructor.parser import get_parser
@@ -46,6 +47,7 @@ class StructuredQueryOutputParser(BaseOutputParser[StructuredQuery]):
ast_parse: Callable
"""Callable that parses dict into internal representation of query language."""
+ @override
def parse(self, text: str) -> StructuredQuery:
try:
expected_keys = ["query", "filter"]
diff --git a/libs/langchain/langchain/chains/query_constructor/parser.py b/libs/langchain/langchain/chains/query_constructor/parser.py
index 3929969706..e03a26efe1 100644
--- a/libs/langchain/langchain/chains/query_constructor/parser.py
+++ b/libs/langchain/langchain/chains/query_constructor/parser.py
@@ -83,15 +83,35 @@ class QueryTransformer(Transformer):
allowed_attributes: Optional[Sequence[str]] = None,
**kwargs: Any,
):
+ """Initialize the QueryTransformer.
+
+ Args:
+ allowed_comparators: Optional sequence of allowed comparators.
+ allowed_operators: Optional sequence of allowed operators.
+ allowed_attributes: Optional sequence of allowed attributes for comparators.
+ **kwargs: Additional keyword arguments.
+ """
super().__init__(*args, **kwargs)
self.allowed_comparators = allowed_comparators
self.allowed_operators = allowed_operators
self.allowed_attributes = allowed_attributes
def program(self, *items: Any) -> tuple:
+ """Transform the items into a tuple."""
return items
def func_call(self, func_name: Any, args: list) -> FilterDirective:
+ """Transform a function name and args into a FilterDirective.
+
+ Args:
+ func_name: The name of the function.
+ args: The arguments passed to the function.
+ Returns:
+ FilterDirective: The filter directive.
+ Raises:
+ ValueError: If the function is a comparator and the first arg is not in the
+ allowed attributes.
+ """
func = self._match_func_name(str(func_name))
if isinstance(func, Comparator):
if self.allowed_attributes and args[0] not in self.allowed_attributes:
@@ -135,26 +155,55 @@ class QueryTransformer(Transformer):
raise ValueError(msg)
def args(self, *items: Any) -> tuple:
+ """Transforms items into a tuple.
+
+ Args:
+ items: The items to transform.
+ """
return items
def false(self) -> bool:
+ """Returns false."""
return False
def true(self) -> bool:
+ """Returns true."""
return True
def list(self, item: Any) -> list:
+ """Transforms an item into a list.
+
+ Args:
+ item: The item to transform.
+ """
if item is None:
return []
return list(item)
def int(self, item: Any) -> int:
+ """Transforms an item into an int.
+
+ Args:
+ item: The item to transform.
+ """
return int(item)
def float(self, item: Any) -> float:
+ """Transforms an item into a float.
+
+ Args:
+ item: The item to transform.
+ """
return float(item)
def date(self, item: Any) -> ISO8601Date:
+ """Transforms an item into a ISO8601Date object.
+
+ Args:
+ item: The item to transform.
+ Raises:
+ ValueError: If the item is not in ISO 8601 date format.
+ """
item = str(item).strip("\"'")
try:
datetime.datetime.strptime(item, "%Y-%m-%d") # noqa: DTZ007
@@ -167,6 +216,13 @@ class QueryTransformer(Transformer):
return {"date": item, "type": "date"}
def datetime(self, item: Any) -> ISO8601DateTime:
+ """Transforms an item into a ISO8601DateTime object.
+
+ Args:
+ item: The item to transform.
+ Raises:
+ ValueError: If the item is not in ISO 8601 datetime format.
+ """
item = str(item).strip("\"'")
try:
# Parse full ISO 8601 datetime format
@@ -180,7 +236,13 @@ class QueryTransformer(Transformer):
return {"datetime": item, "type": "datetime"}
def string(self, item: Any) -> str:
- # Remove escaped quotes
+ """Transforms an item into a string.
+
+ Removes escaped quotes.
+
+ Args:
+ item: The item to transform.
+ """
return str(item).strip("\"'")
diff --git a/libs/langchain/langchain/chains/router/base.py b/libs/langchain/langchain/chains/router/base.py
index ce280b7502..c7d351be63 100644
--- a/libs/langchain/langchain/chains/router/base.py
+++ b/libs/langchain/langchain/chains/router/base.py
@@ -12,11 +12,14 @@ from langchain_core.callbacks import (
Callbacks,
)
from pydantic import ConfigDict
+from typing_extensions import override
from langchain.chains.base import Chain
class Route(NamedTuple):
+ """A route to a destination chain."""
+
destination: Optional[str]
next_inputs: dict[str, Any]
@@ -25,12 +28,12 @@ class RouterChain(Chain, ABC):
"""Chain that outputs the name of a destination chain and the inputs to it."""
@property
+ @override
def output_keys(self) -> list[str]:
return ["destination", "next_inputs"]
def route(self, inputs: dict[str, Any], callbacks: Callbacks = None) -> Route:
- """
- Route inputs to a destination chain.
+ """Route inputs to a destination chain.
Args:
inputs: inputs to the chain
@@ -47,6 +50,15 @@ class RouterChain(Chain, ABC):
inputs: dict[str, Any],
callbacks: Callbacks = None,
) -> Route:
+ """Route inputs to a destination chain.
+
+ Args:
+ inputs: inputs to the chain
+ callbacks: callbacks to use for the chain
+
+ Returns:
+ a Route object
+ """
result = await self.acall(inputs, callbacks=callbacks)
return Route(result["destination"], result["next_inputs"])
diff --git a/libs/langchain/langchain/chains/router/llm_router.py b/libs/langchain/langchain/chains/router/llm_router.py
index 33731c63b0..fe9a2554c0 100644
--- a/libs/langchain/langchain/chains/router/llm_router.py
+++ b/libs/langchain/langchain/chains/router/llm_router.py
@@ -15,7 +15,7 @@ from langchain_core.output_parsers import BaseOutputParser
from langchain_core.prompts import BasePromptTemplate
from langchain_core.utils.json import parse_and_check_json_markdown
from pydantic import model_validator
-from typing_extensions import Self
+from typing_extensions import Self, override
from langchain.chains import LLMChain
from langchain.chains.router.base import RouterChain
@@ -102,7 +102,7 @@ class LLMRouterChain(RouterChain):
"""LLM chain used to perform routing"""
@model_validator(mode="after")
- def validate_prompt(self) -> Self:
+ def _validate_prompt(self) -> Self:
prompt = self.llm_chain.prompt
if prompt.output_parser is None:
msg = (
@@ -172,6 +172,7 @@ class RouterOutputParser(BaseOutputParser[dict[str, str]]):
next_inputs_type: type = str
next_inputs_inner_key: str = "input"
+ @override
def parse(self, text: str) -> dict[str, Any]:
try:
expected_keys = ["destination", "next_inputs"]
diff --git a/libs/langchain/langchain/chains/router/multi_prompt.py b/libs/langchain/langchain/chains/router/multi_prompt.py
index c0b85a1c6c..2bfe1c42bd 100644
--- a/libs/langchain/langchain/chains/router/multi_prompt.py
+++ b/libs/langchain/langchain/chains/router/multi_prompt.py
@@ -7,6 +7,7 @@ from typing import Any, Optional
from langchain_core._api import deprecated
from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import PromptTemplate
+from typing_extensions import override
from langchain.chains import ConversationChain
from langchain.chains.base import Chain
@@ -142,6 +143,7 @@ class MultiPromptChain(MultiRouteChain):
""" # noqa: E501
@property
+ @override
def output_keys(self) -> list[str]:
return ["text"]
diff --git a/libs/langchain/langchain/chains/router/multi_retrieval_qa.py b/libs/langchain/langchain/chains/router/multi_retrieval_qa.py
index 8745b48a58..aa3bd23f9c 100644
--- a/libs/langchain/langchain/chains/router/multi_retrieval_qa.py
+++ b/libs/langchain/langchain/chains/router/multi_retrieval_qa.py
@@ -8,6 +8,7 @@ from typing import Any, Optional
from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import PromptTemplate
from langchain_core.retrievers import BaseRetriever
+from typing_extensions import override
from langchain.chains import ConversationChain
from langchain.chains.base import Chain
@@ -32,6 +33,7 @@ class MultiRetrievalQAChain(MultiRouteChain):
"""Default chain to use when router doesn't map input to one of the destinations."""
@property
+ @override
def output_keys(self) -> list[str]:
return ["result"]
@@ -47,6 +49,22 @@ class MultiRetrievalQAChain(MultiRouteChain):
default_chain_llm: Optional[BaseLanguageModel] = None,
**kwargs: Any,
) -> MultiRetrievalQAChain:
+ """Create a multi retrieval qa chain from an LLM and a default chain.
+
+ Args:
+ llm: The language model to use.
+ retriever_infos: Dictionaries containing retriever information.
+ default_retriever: Optional default retriever to use if no default chain
+ is provided.
+ default_prompt: Optional prompt template to use for the default retriever.
+ default_chain: Optional default chain to use when router doesn't map input
+ to one of the destinations.
+ default_chain_llm: Optional language model to use if no default chain and
+ no default retriever are provided.
+ **kwargs: Additional keyword arguments to pass to the chain.
+ Returns:
+ An instance of the multi retrieval qa chain.
+ """
if default_prompt and not default_retriever:
msg = (
"`default_retriever` must be specified if `default_prompt` is "
diff --git a/libs/langchain/langchain/evaluation/comparison/eval_chain.py b/libs/langchain/langchain/evaluation/comparison/eval_chain.py
index 6d1d03a465..e430e48166 100644
--- a/libs/langchain/langchain/evaluation/comparison/eval_chain.py
+++ b/libs/langchain/langchain/evaluation/comparison/eval_chain.py
@@ -191,6 +191,7 @@ class PairwiseStringEvalChain(PairwiseStringEvaluator, LLMEvalChain, LLMChain):
)
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
diff --git a/libs/langchain/langchain/evaluation/criteria/eval_chain.py b/libs/langchain/langchain/evaluation/criteria/eval_chain.py
index 1f72c73c56..943a342e87 100644
--- a/libs/langchain/langchain/evaluation/criteria/eval_chain.py
+++ b/libs/langchain/langchain/evaluation/criteria/eval_chain.py
@@ -236,6 +236,7 @@ class CriteriaEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
output_key: str = "results" #: :meta private:
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
@@ -249,6 +250,7 @@ class CriteriaEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
return False
@property
+ @override
def requires_input(self) -> bool:
return True
@@ -520,6 +522,7 @@ class LabeledCriteriaEvalChain(CriteriaEvalChain):
"""Criteria evaluation chain that requires references."""
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
diff --git a/libs/langchain/langchain/evaluation/embedding_distance/base.py b/libs/langchain/langchain/evaluation/embedding_distance/base.py
index 0844074c1c..53a67962a5 100644
--- a/libs/langchain/langchain/evaluation/embedding_distance/base.py
+++ b/libs/langchain/langchain/evaluation/embedding_distance/base.py
@@ -14,6 +14,7 @@ from langchain_core.callbacks.manager import (
from langchain_core.embeddings import Embeddings
from langchain_core.utils import pre_init
from pydantic import ConfigDict, Field
+from typing_extensions import override
from langchain.chains.base import Chain
from langchain.evaluation.schema import PairwiseStringEvaluator, StringEvaluator
@@ -317,6 +318,7 @@ class EmbeddingDistanceEvalChain(_EmbeddingDistanceChainMixin, StringEvaluator):
return True
@property
+ @override
def evaluation_name(self) -> str:
return f"embedding_{self.distance_metric.value}_distance"
@@ -473,6 +475,7 @@ class PairwiseEmbeddingDistanceEvalChain(
@property
def evaluation_name(self) -> str:
+ """Return the evaluation name."""
return f"pairwise_embedding_{self.distance_metric.value}_distance"
def _call(
diff --git a/libs/langchain/langchain/evaluation/exact_match/base.py b/libs/langchain/langchain/evaluation/exact_match/base.py
index 818f5661cb..4ee092b64f 100644
--- a/libs/langchain/langchain/evaluation/exact_match/base.py
+++ b/libs/langchain/langchain/evaluation/exact_match/base.py
@@ -27,8 +27,18 @@ class ExactMatchStringEvaluator(StringEvaluator):
ignore_case: bool = False,
ignore_punctuation: bool = False,
ignore_numbers: bool = False,
- **kwargs: Any,
+ **_: Any,
):
+ """Initialize the ExactMatchStringEvaluator.
+
+ Args:
+ ignore_case: Whether to ignore case when comparing strings.
+ Defaults to False.
+ ignore_punctuation: Whether to ignore punctuation when comparing strings.
+ Defaults to False.
+ ignore_numbers: Whether to ignore numbers when comparing strings.
+ Defaults to False.
+ """
super().__init__()
self.ignore_case = ignore_case
self.ignore_punctuation = ignore_punctuation
diff --git a/libs/langchain/langchain/evaluation/parsing/base.py b/libs/langchain/langchain/evaluation/parsing/base.py
index d14ef851cf..aeeda41a05 100644
--- a/libs/langchain/langchain/evaluation/parsing/base.py
+++ b/libs/langchain/langchain/evaluation/parsing/base.py
@@ -35,18 +35,22 @@ class JsonValidityEvaluator(StringEvaluator):
{'score': 0, 'reasoning': 'Expecting property name enclosed in double quotes'}
"""
- def __init__(self, **kwargs: Any) -> None:
+ def __init__(self, **_: Any) -> None:
+ """Initialize the JsonValidityEvaluator."""
super().__init__()
@property
+ @override
def requires_input(self) -> bool:
return False
@property
+ @override
def requires_reference(self) -> bool:
return False
@property
+ @override
def evaluation_name(self) -> str:
return "json_validity"
@@ -110,19 +114,28 @@ class JsonEqualityEvaluator(StringEvaluator):
"""
- def __init__(self, operator: Optional[Callable] = None, **kwargs: Any) -> None:
+ def __init__(self, operator: Optional[Callable] = None, **_: Any) -> None:
+ """Initialize the JsonEqualityEvaluator.
+
+ Args:
+ operator: A custom operator to compare the parsed JSON objects.
+ Defaults to equality (`eq`).
+ """
super().__init__()
self.operator = operator or eq
@property
+ @override
def requires_input(self) -> bool:
return False
@property
+ @override
def requires_reference(self) -> bool:
return True
@property
+ @override
def evaluation_name(self) -> str:
return "json_equality"
diff --git a/libs/langchain/langchain/evaluation/parsing/json_distance.py b/libs/langchain/langchain/evaluation/parsing/json_distance.py
index ca3970c598..954f545a66 100644
--- a/libs/langchain/langchain/evaluation/parsing/json_distance.py
+++ b/libs/langchain/langchain/evaluation/parsing/json_distance.py
@@ -15,13 +15,6 @@ class JsonEditDistanceEvaluator(StringEvaluator):
after parsing them and converting them to a canonical format (i.e., whitespace and key order are normalized).
It can be customized with alternative distance and canonicalization functions.
- Args:
- string_distance (Optional[Callable[[str, str], float]]): A callable that computes the distance between two strings.
- If not provided, a Damerau-Levenshtein distance from the `rapidfuzz` package will be used.
- canonicalize (Optional[Callable[[Any], Any]]): A callable that converts a parsed JSON object into its canonical string form.
- If not provided, the default behavior is to serialize the JSON with sorted keys and no extra whitespace.
- **kwargs (Any): Additional keyword arguments.
-
Attributes:
_string_distance (Callable[[str, str], float]): The internal distance computation function.
_canonicalize (Callable[[Any], Any]): The internal canonicalization function.
@@ -40,8 +33,23 @@ class JsonEditDistanceEvaluator(StringEvaluator):
self,
string_distance: Optional[Callable[[str, str], float]] = None,
canonicalize: Optional[Callable[[Any], Any]] = None,
- **kwargs: Any,
+ **_: Any,
) -> None:
+ """Initialize the JsonEditDistanceEvaluator.
+
+ Args:
+ string_distance: A callable that computes the distance between two strings.
+ If not provided, a Damerau-Levenshtein distance from the `rapidfuzz`
+ package will be used.
+ canonicalize: A callable that converts a parsed JSON object into its
+ canonical string form.
+ If not provided, the default behavior is to serialize the JSON with
+ sorted keys and no extra whitespace.
+
+ Raises:
+ ImportError: If the `rapidfuzz` package is not installed and no
+ `string_distance` function is provided.
+ """
super().__init__()
if string_distance is not None:
self._string_distance = string_distance
@@ -67,14 +75,17 @@ class JsonEditDistanceEvaluator(StringEvaluator):
)
@property
+ @override
def requires_input(self) -> bool:
return False
@property
+ @override
def requires_reference(self) -> bool:
return True
@property
+ @override
def evaluation_name(self) -> str:
return "json_edit_distance"
diff --git a/libs/langchain/langchain/evaluation/qa/eval_chain.py b/libs/langchain/langchain/evaluation/qa/eval_chain.py
index fcf8571fd2..0ad0eddc40 100644
--- a/libs/langchain/langchain/evaluation/qa/eval_chain.py
+++ b/libs/langchain/langchain/evaluation/qa/eval_chain.py
@@ -80,18 +80,22 @@ class QAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
)
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
@property
+ @override
def evaluation_name(self) -> str:
return "correctness"
@property
+ @override
def requires_reference(self) -> bool:
return True
@property
+ @override
def requires_input(self) -> bool:
return True
@@ -214,6 +218,7 @@ class ContextQAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
"""LLM Chain for evaluating QA w/o GT based on context"""
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
@@ -242,6 +247,7 @@ class ContextQAEvalChain(LLMChain, StringEvaluator, LLMEvalChain):
raise ValueError(msg)
@property
+ @override
def evaluation_name(self) -> str:
return "Contextual Accuracy"
@@ -344,10 +350,12 @@ class CotQAEvalChain(ContextQAEvalChain):
"""LLM Chain for evaluating QA using chain of thought reasoning."""
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
@property
+ @override
def evaluation_name(self) -> str:
return "COT Contextual Accuracy"
diff --git a/libs/langchain/langchain/evaluation/qa/generate_chain.py b/libs/langchain/langchain/evaluation/qa/generate_chain.py
index 41ad4a6ed5..8ee561b22c 100644
--- a/libs/langchain/langchain/evaluation/qa/generate_chain.py
+++ b/libs/langchain/langchain/evaluation/qa/generate_chain.py
@@ -7,6 +7,7 @@ from typing import Any
from langchain_core.language_models import BaseLanguageModel
from langchain_core.output_parsers import BaseLLMOutputParser
from pydantic import Field
+from typing_extensions import override
from langchain.chains.llm import LLMChain
from langchain.evaluation.qa.generate_prompt import PROMPT
@@ -25,6 +26,7 @@ class QAGenerateChain(LLMChain):
output_key: str = "qa_pairs"
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
diff --git a/libs/langchain/langchain/evaluation/regex_match/base.py b/libs/langchain/langchain/evaluation/regex_match/base.py
index 71b9c9e574..d86eb45a23 100644
--- a/libs/langchain/langchain/evaluation/regex_match/base.py
+++ b/libs/langchain/langchain/evaluation/regex_match/base.py
@@ -27,7 +27,12 @@ class RegexMatchStringEvaluator(StringEvaluator):
) # This will return {'score': 1.0} as the prediction matches the second pattern in the union
""" # noqa: E501
- def __init__(self, *, flags: int = 0, **kwargs: Any): # Default is no flags
+ def __init__(self, *, flags: int = 0, **_: Any): # Default is no flags
+ """Initialize the RegexMatchStringEvaluator.
+
+ Args:
+ flags: Flags to use for the regex match. Defaults to 0 (no flags).
+ """
super().__init__()
self.flags = flags
diff --git a/libs/langchain/langchain/evaluation/scoring/eval_chain.py b/libs/langchain/langchain/evaluation/scoring/eval_chain.py
index d998f4da90..1ab9b2102a 100644
--- a/libs/langchain/langchain/evaluation/scoring/eval_chain.py
+++ b/libs/langchain/langchain/evaluation/scoring/eval_chain.py
@@ -187,6 +187,7 @@ class ScoreStringEvalChain(StringEvaluator, LLMEvalChain, LLMChain):
)
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return False
diff --git a/libs/langchain/langchain/memory/buffer.py b/libs/langchain/langchain/memory/buffer.py
index a3bd947e59..9beffa87d9 100644
--- a/libs/langchain/langchain/memory/buffer.py
+++ b/libs/langchain/langchain/memory/buffer.py
@@ -4,6 +4,7 @@ from langchain_core._api import deprecated
from langchain_core.memory import BaseMemory
from langchain_core.messages import BaseMessage, get_buffer_string
from langchain_core.utils import pre_init
+from typing_extensions import override
from langchain.memory.chat_memory import BaseChatMemory
from langchain.memory.utils import get_prompt_input_key
@@ -169,5 +170,6 @@ class ConversationStringBufferMemory(BaseMemory):
"""Clear memory contents."""
self.buffer = ""
+ @override
async def aclear(self) -> None:
self.clear()
diff --git a/libs/langchain/langchain/memory/combined.py b/libs/langchain/langchain/memory/combined.py
index eb25197ec8..aaca8849fc 100644
--- a/libs/langchain/langchain/memory/combined.py
+++ b/libs/langchain/langchain/memory/combined.py
@@ -15,7 +15,7 @@ class CombinedMemory(BaseMemory):
@field_validator("memories")
@classmethod
- def check_repeated_memory_variable(
+ def _check_repeated_memory_variable(
cls,
value: list[BaseMemory],
) -> list[BaseMemory]:
diff --git a/libs/langchain/langchain/memory/entity.py b/libs/langchain/langchain/memory/entity.py
index e66a60a473..726abed4f8 100644
--- a/libs/langchain/langchain/memory/entity.py
+++ b/libs/langchain/langchain/memory/entity.py
@@ -11,6 +11,7 @@ from langchain_core.language_models import BaseLanguageModel
from langchain_core.messages import BaseMessage, get_buffer_string
from langchain_core.prompts import BasePromptTemplate
from pydantic import BaseModel, ConfigDict, Field
+from typing_extensions import override
from langchain.chains.llm import LLMChain
from langchain.memory.chat_memory import BaseChatMemory
@@ -71,18 +72,23 @@ class InMemoryEntityStore(BaseEntityStore):
store: dict[str, Optional[str]] = {}
+ @override
def get(self, key: str, default: Optional[str] = None) -> Optional[str]:
return self.store.get(key, default)
+ @override
def set(self, key: str, value: Optional[str]) -> None:
self.store[key] = value
+ @override
def delete(self, key: str) -> None:
del self.store[key]
+ @override
def exists(self, key: str) -> bool:
return key in self.store
+ @override
def clear(self) -> None:
return self.store.clear()
@@ -113,6 +119,16 @@ class UpstashRedisEntityStore(BaseEntityStore):
*args: Any,
**kwargs: Any,
):
+ """Initializes the RedisEntityStore.
+
+ Args:
+ session_id: Unique identifier for the session.
+ url: URL of the Redis server.
+ token: Authentication token for the Redis server.
+ key_prefix: Prefix for keys in the Redis store.
+ ttl: Time-to-live for keys in seconds (default 1 day).
+ recall_ttl: Time-to-live extension for keys when recalled (default 3 days).
+ """
try:
from upstash_redis import Redis
except ImportError as e:
@@ -138,8 +154,10 @@ class UpstashRedisEntityStore(BaseEntityStore):
@property
def full_key_prefix(self) -> str:
+ """Returns the full key prefix with session ID."""
return f"{self.key_prefix}:{self.session_id}"
+ @override
def get(self, key: str, default: Optional[str] = None) -> Optional[str]:
res = (
self.redis_client.getex(f"{self.full_key_prefix}:{key}", ex=self.recall_ttl)
@@ -151,6 +169,7 @@ class UpstashRedisEntityStore(BaseEntityStore):
)
return res
+ @override
def set(self, key: str, value: Optional[str]) -> None:
if not value:
return self.delete(key)
@@ -164,12 +183,15 @@ class UpstashRedisEntityStore(BaseEntityStore):
)
return None
+ @override
def delete(self, key: str) -> None:
self.redis_client.delete(f"{self.full_key_prefix}:{key}")
+ @override
def exists(self, key: str) -> bool:
return self.redis_client.exists(f"{self.full_key_prefix}:{key}") == 1
+ @override
def clear(self) -> None:
def scan_and_delete(cursor: int) -> int:
cursor, keys_to_delete = self.redis_client.scan(
@@ -215,6 +237,16 @@ class RedisEntityStore(BaseEntityStore):
*args: Any,
**kwargs: Any,
):
+ """Initializes the RedisEntityStore.
+
+ Args:
+ session_id: Unique identifier for the session.
+ url: URL of the Redis server.
+ key_prefix: Prefix for keys in the Redis store.
+ ttl: Time-to-live for keys in seconds (default 1 day).
+ recall_ttl: Time-to-live extension for keys when recalled (default 3 days).
+ """
+
try:
import redis
except ImportError as e:
@@ -247,8 +279,10 @@ class RedisEntityStore(BaseEntityStore):
@property
def full_key_prefix(self) -> str:
+ """Returns the full key prefix with session ID."""
return f"{self.key_prefix}:{self.session_id}"
+ @override
def get(self, key: str, default: Optional[str] = None) -> Optional[str]:
res = (
self.redis_client.getex(f"{self.full_key_prefix}:{key}", ex=self.recall_ttl)
@@ -258,6 +292,7 @@ class RedisEntityStore(BaseEntityStore):
logger.debug("REDIS MEM get '%s:%s': '%s'", self.full_key_prefix, key, res)
return res
+ @override
def set(self, key: str, value: Optional[str]) -> None:
if not value:
return self.delete(key)
@@ -271,12 +306,15 @@ class RedisEntityStore(BaseEntityStore):
)
return None
+ @override
def delete(self, key: str) -> None:
self.redis_client.delete(f"{self.full_key_prefix}:{key}")
+ @override
def exists(self, key: str) -> bool:
return self.redis_client.exists(f"{self.full_key_prefix}:{key}") == 1
+ @override
def clear(self) -> None:
# iterate a list in batches of size batch_size
def batched(iterable: Iterable[Any], batch_size: int) -> Iterable[Any]:
@@ -318,6 +356,13 @@ class SQLiteEntityStore(BaseEntityStore):
*args: Any,
**kwargs: Any,
):
+ """Initializes the SQLiteEntityStore.
+
+ Args:
+ session_id: Unique identifier for the session.
+ db_file: Path to the SQLite database file.
+ table_name: Name of the table to store entities.
+ """
super().__init__(*args, **kwargs)
try:
import sqlite3
@@ -341,6 +386,7 @@ class SQLiteEntityStore(BaseEntityStore):
@property
def full_table_name(self) -> str:
+ """Returns the full table name with session ID."""
return f"{self.table_name}_{self.session_id}"
def _execute_query(self, query: str, params: tuple = ()) -> "sqlite3.Cursor":
@@ -393,6 +439,7 @@ class SQLiteEntityStore(BaseEntityStore):
cursor = self._execute_query(query, (key,))
return cursor.fetchone() is not None
+ @override
def clear(self) -> None:
# Ignore S608 since we validate for malicious table/session names in `__init__`
query = f"""
diff --git a/libs/langchain/langchain/memory/simple.py b/libs/langchain/langchain/memory/simple.py
index c9b1e90ab5..466a3bf1cd 100644
--- a/libs/langchain/langchain/memory/simple.py
+++ b/libs/langchain/langchain/memory/simple.py
@@ -1,6 +1,7 @@
from typing import Any
from langchain_core.memory import BaseMemory
+from typing_extensions import override
class SimpleMemory(BaseMemory):
@@ -11,9 +12,11 @@ class SimpleMemory(BaseMemory):
memories: dict[str, Any] = {}
@property
+ @override
def memory_variables(self) -> list[str]:
return list(self.memories.keys())
+ @override
def load_memory_variables(self, inputs: dict[str, Any]) -> dict[str, str]:
return self.memories
diff --git a/libs/langchain/langchain/memory/summary.py b/libs/langchain/langchain/memory/summary.py
index 6097258d29..31dc478516 100644
--- a/libs/langchain/langchain/memory/summary.py
+++ b/libs/langchain/langchain/memory/summary.py
@@ -37,6 +37,15 @@ class SummarizerMixin(BaseModel):
messages: list[BaseMessage],
existing_summary: str,
) -> str:
+ """Predict a new summary based on the messages and existing summary.
+
+ Args:
+ messages: List of messages to summarize.
+ existing_summary: Existing summary to build upon.
+
+ Returns:
+ A new summary string.
+ """
new_lines = get_buffer_string(
messages,
human_prefix=self.human_prefix,
@@ -51,6 +60,15 @@ class SummarizerMixin(BaseModel):
messages: list[BaseMessage],
existing_summary: str,
) -> str:
+ """Predict a new summary based on the messages and existing summary.
+
+ Args:
+ messages: List of messages to summarize.
+ existing_summary: Existing summary to build upon.
+
+ Returns:
+ A new summary string.
+ """
new_lines = get_buffer_string(
messages,
human_prefix=self.human_prefix,
@@ -89,6 +107,16 @@ class ConversationSummaryMemory(BaseChatMemory, SummarizerMixin):
summarize_step: int = 2,
**kwargs: Any,
) -> ConversationSummaryMemory:
+ """Create a ConversationSummaryMemory from a list of messages.
+
+ Args:
+ llm: The language model to use for summarization.
+ chat_memory: The chat history to summarize.
+ summarize_step: Number of messages to summarize at a time.
+ **kwargs: Additional keyword arguments to pass to the class.
+ Returns:
+ An instance of ConversationSummaryMemory with the summarized history.
+ """
obj = cls(llm=llm, chat_memory=chat_memory, **kwargs)
for i in range(0, len(obj.chat_memory.messages), summarize_step):
obj.buffer = obj.predict_new_summary(
diff --git a/libs/langchain/langchain/output_parsers/combining.py b/libs/langchain/langchain/output_parsers/combining.py
index 2db7628be1..555bf00e67 100644
--- a/libs/langchain/langchain/output_parsers/combining.py
+++ b/libs/langchain/langchain/output_parsers/combining.py
@@ -4,6 +4,7 @@ from typing import Any
from langchain_core.output_parsers import BaseOutputParser
from langchain_core.utils import pre_init
+from typing_extensions import override
_MIN_PARSERS = 2
@@ -14,6 +15,7 @@ class CombiningOutputParser(BaseOutputParser[dict[str, Any]]):
parsers: list[BaseOutputParser]
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return True
diff --git a/libs/langchain/langchain/output_parsers/enum.py b/libs/langchain/langchain/output_parsers/enum.py
index 9a838db730..a96185a6b9 100644
--- a/libs/langchain/langchain/output_parsers/enum.py
+++ b/libs/langchain/langchain/output_parsers/enum.py
@@ -3,6 +3,7 @@ from enum import Enum
from langchain_core.exceptions import OutputParserException
from langchain_core.output_parsers import BaseOutputParser
from langchain_core.utils import pre_init
+from typing_extensions import override
class EnumOutputParser(BaseOutputParser[Enum]):
@@ -12,7 +13,7 @@ class EnumOutputParser(BaseOutputParser[Enum]):
"""The enum to parse. Its values must be strings."""
@pre_init
- def raise_deprecation(cls, values: dict) -> dict:
+ def _raise_deprecation(cls, values: dict) -> dict:
enum = values["enum"]
if not all(isinstance(e.value, str) for e in enum):
msg = "Enum values must be strings"
@@ -23,6 +24,7 @@ class EnumOutputParser(BaseOutputParser[Enum]):
def _valid_values(self) -> list[str]:
return [e.value for e in self.enum]
+ @override
def parse(self, response: str) -> Enum:
try:
return self.enum(response.strip())
@@ -33,9 +35,11 @@ class EnumOutputParser(BaseOutputParser[Enum]):
)
raise OutputParserException(msg) from e
+ @override
def get_format_instructions(self) -> str:
return f"Select one of the following options: {', '.join(self._valid_values)}"
@property
+ @override
def OutputType(self) -> type[Enum]:
return self.enum
diff --git a/libs/langchain/langchain/output_parsers/fix.py b/libs/langchain/langchain/output_parsers/fix.py
index c556a0d729..6dd4439e78 100644
--- a/libs/langchain/langchain/output_parsers/fix.py
+++ b/libs/langchain/langchain/output_parsers/fix.py
@@ -7,7 +7,7 @@ from langchain_core.output_parsers import BaseOutputParser, StrOutputParser
from langchain_core.prompts import BasePromptTemplate
from langchain_core.runnables import Runnable, RunnableSerializable
from pydantic import SkipValidation
-from typing_extensions import TypedDict
+from typing_extensions import TypedDict, override
from langchain.output_parsers.prompts import NAIVE_FIX_PROMPT
@@ -15,6 +15,8 @@ T = TypeVar("T")
class OutputFixingParserRetryChainInput(TypedDict, total=False):
+ """Input for the retry chain of the OutputFixingParser."""
+
instructions: str
completion: str
error: str
@@ -24,6 +26,7 @@ class OutputFixingParser(BaseOutputParser[T]):
"""Wrap a parser and try to fix parsing errors."""
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return True
@@ -62,6 +65,7 @@ class OutputFixingParser(BaseOutputParser[T]):
chain = prompt | llm | StrOutputParser()
return cls(parser=parser, retry_chain=chain, max_retries=max_retries)
+ @override
def parse(self, completion: str) -> T:
retries = 0
@@ -99,6 +103,7 @@ class OutputFixingParser(BaseOutputParser[T]):
msg = "Failed to parse"
raise OutputParserException(msg)
+ @override
async def aparse(self, completion: str) -> T:
retries = 0
@@ -136,6 +141,7 @@ class OutputFixingParser(BaseOutputParser[T]):
msg = "Failed to parse"
raise OutputParserException(msg)
+ @override
def get_format_instructions(self) -> str:
return self.parser.get_format_instructions()
@@ -144,5 +150,6 @@ class OutputFixingParser(BaseOutputParser[T]):
return "output_fixing"
@property
+ @override
def OutputType(self) -> type[T]:
return self.parser.OutputType
diff --git a/libs/langchain/langchain/output_parsers/pandas_dataframe.py b/libs/langchain/langchain/output_parsers/pandas_dataframe.py
index d360865e32..96d1849316 100644
--- a/libs/langchain/langchain/output_parsers/pandas_dataframe.py
+++ b/libs/langchain/langchain/output_parsers/pandas_dataframe.py
@@ -4,6 +4,7 @@ from typing import Any, Union
from langchain_core.exceptions import OutputParserException
from langchain_core.output_parsers.base import BaseOutputParser
from pydantic import field_validator
+from typing_extensions import override
from langchain.output_parsers.format_instructions import (
PANDAS_DATAFRAME_FORMAT_INSTRUCTIONS,
@@ -18,7 +19,7 @@ class PandasDataFrameOutputParser(BaseOutputParser[dict[str, Any]]):
@field_validator("dataframe")
@classmethod
- def validate_dataframe(cls, val: Any) -> Any:
+ def _validate_dataframe(cls, val: Any) -> Any:
import pandas as pd
if issubclass(type(val), pd.DataFrame):
@@ -36,6 +37,18 @@ class PandasDataFrameOutputParser(BaseOutputParser[dict[str, Any]]):
array: str,
original_request_params: str,
) -> tuple[list[Union[int, str]], str]:
+ """Parse the array from the request parameters.
+
+ Args:
+ array: The array string to parse.
+ original_request_params: The original request parameters string.
+
+ Returns:
+ A tuple containing the parsed array and the stripped request parameters.
+
+ Raises:
+ OutputParserException: If the array format is invalid or cannot be parsed.
+ """
parsed_array: list[Union[int, str]] = []
# Check if the format is [1,3,5]
@@ -76,6 +89,7 @@ class PandasDataFrameOutputParser(BaseOutputParser[dict[str, Any]]):
return parsed_array, original_request_params.split("[")[0]
+ @override
def parse(self, request: str) -> dict[str, Any]:
stripped_request_params = None
splitted_request = request.strip().split(":")
@@ -150,6 +164,7 @@ class PandasDataFrameOutputParser(BaseOutputParser[dict[str, Any]]):
return result
+ @override
def get_format_instructions(self) -> str:
return PANDAS_DATAFRAME_FORMAT_INSTRUCTIONS.format(
columns=", ".join(self.dataframe.columns),
diff --git a/libs/langchain/langchain/output_parsers/regex.py b/libs/langchain/langchain/output_parsers/regex.py
index b3b33909a8..9b3657e4bf 100644
--- a/libs/langchain/langchain/output_parsers/regex.py
+++ b/libs/langchain/langchain/output_parsers/regex.py
@@ -4,12 +4,14 @@ import re
from typing import Optional
from langchain_core.output_parsers import BaseOutputParser
+from typing_extensions import override
class RegexParser(BaseOutputParser[dict[str, str]]):
"""Parse the output of an LLM call using a regex."""
@classmethod
+ @override
def is_lc_serializable(cls) -> bool:
return True
diff --git a/libs/langchain/langchain/output_parsers/retry.py b/libs/langchain/langchain/output_parsers/retry.py
index 91ad9fda59..3f0ad084be 100644
--- a/libs/langchain/langchain/output_parsers/retry.py
+++ b/libs/langchain/langchain/output_parsers/retry.py
@@ -9,7 +9,7 @@ from langchain_core.prompt_values import PromptValue
from langchain_core.prompts import BasePromptTemplate, PromptTemplate
from langchain_core.runnables import RunnableSerializable
from pydantic import SkipValidation
-from typing_extensions import TypedDict
+from typing_extensions import TypedDict, override
NAIVE_COMPLETION_RETRY = """Prompt:
{prompt}
@@ -37,11 +37,15 @@ T = TypeVar("T")
class RetryOutputParserRetryChainInput(TypedDict):
+ """Retry chain input for RetryOutputParser."""
+
prompt: str
completion: str
class RetryWithErrorOutputParserRetryChainInput(TypedDict):
+ """Retry chain input for RetryWithErrorOutputParser."""
+
prompt: str
completion: str
error: str
@@ -160,10 +164,12 @@ class RetryOutputParser(BaseOutputParser[T]):
msg = "Failed to parse"
raise OutputParserException(msg)
+ @override
def parse(self, completion: str) -> T:
msg = "This OutputParser can only be called by the `parse_with_prompt` method."
raise NotImplementedError(msg)
+ @override
def get_format_instructions(self) -> str:
return self.parser.get_format_instructions()
@@ -172,6 +178,7 @@ class RetryOutputParser(BaseOutputParser[T]):
return "retry"
@property
+ @override
def OutputType(self) -> type[T]:
return self.parser.OutputType
@@ -224,6 +231,7 @@ class RetryWithErrorOutputParser(BaseOutputParser[T]):
chain = prompt | llm | StrOutputParser()
return cls(parser=parser, retry_chain=chain, max_retries=max_retries)
+ @override
def parse_with_prompt(self, completion: str, prompt_value: PromptValue) -> T:
retries = 0
@@ -253,6 +261,15 @@ class RetryWithErrorOutputParser(BaseOutputParser[T]):
raise OutputParserException(msg)
async def aparse_with_prompt(self, completion: str, prompt_value: PromptValue) -> T:
+ """Parse the output of an LLM call using a wrapped parser.
+
+ Args:
+ completion: The chain completion to parse.
+ prompt_value: The prompt to use to parse the completion.
+
+ Returns:
+ The parsed completion.
+ """
retries = 0
while retries <= self.max_retries:
@@ -280,10 +297,12 @@ class RetryWithErrorOutputParser(BaseOutputParser[T]):
msg = "Failed to parse"
raise OutputParserException(msg)
+ @override
def parse(self, completion: str) -> T:
msg = "This OutputParser can only be called by the `parse_with_prompt` method."
raise NotImplementedError(msg)
+ @override
def get_format_instructions(self) -> str:
return self.parser.get_format_instructions()
@@ -292,5 +311,6 @@ class RetryWithErrorOutputParser(BaseOutputParser[T]):
return "retry_with_error"
@property
+ @override
def OutputType(self) -> type[T]:
return self.parser.OutputType
diff --git a/libs/langchain/langchain/output_parsers/structured.py b/libs/langchain/langchain/output_parsers/structured.py
index 5210a8bb4d..07952c091b 100644
--- a/libs/langchain/langchain/output_parsers/structured.py
+++ b/libs/langchain/langchain/output_parsers/structured.py
@@ -5,6 +5,7 @@ from typing import Any
from langchain_core.output_parsers import BaseOutputParser
from langchain_core.output_parsers.json import parse_and_check_json_markdown
from pydantic import BaseModel
+from typing_extensions import override
from langchain.output_parsers.format_instructions import (
STRUCTURED_FORMAT_INSTRUCTIONS,
@@ -44,6 +45,14 @@ class StructuredOutputParser(BaseOutputParser[dict[str, Any]]):
cls,
response_schemas: list[ResponseSchema],
) -> StructuredOutputParser:
+ """Create a StructuredOutputParser from a list of ResponseSchema.
+
+ Args:
+ response_schemas: The schemas for the response.
+
+ Returns:
+ An instance of StructuredOutputParser.
+ """
return cls(response_schemas=response_schemas)
def get_format_instructions(
@@ -97,6 +106,7 @@ class StructuredOutputParser(BaseOutputParser[dict[str, Any]]):
return STRUCTURED_FORMAT_SIMPLE_INSTRUCTIONS.format(format=schema_str)
return STRUCTURED_FORMAT_INSTRUCTIONS.format(format=schema_str)
+ @override
def parse(self, text: str) -> dict[str, Any]:
expected_keys = [rs.name for rs in self.response_schemas]
return parse_and_check_json_markdown(text, expected_keys)
diff --git a/libs/langchain/langchain/output_parsers/yaml.py b/libs/langchain/langchain/output_parsers/yaml.py
index 88476c78bc..297a244988 100644
--- a/libs/langchain/langchain/output_parsers/yaml.py
+++ b/libs/langchain/langchain/output_parsers/yaml.py
@@ -6,6 +6,7 @@ import yaml
from langchain_core.exceptions import OutputParserException
from langchain_core.output_parsers import BaseOutputParser
from pydantic import BaseModel, ValidationError
+from typing_extensions import override
from langchain.output_parsers.format_instructions import YAML_FORMAT_INSTRUCTIONS
@@ -24,6 +25,7 @@ class YamlOutputParser(BaseOutputParser[T]):
"""Regex pattern to match yaml code blocks
within triple backticks with optional yaml or yml prefix."""
+ @override
def parse(self, text: str) -> T:
try:
# Greedy search for 1st yaml candidate.
@@ -41,6 +43,7 @@ class YamlOutputParser(BaseOutputParser[T]):
msg = f"Failed to parse {name} from completion {text}. Got: {e}"
raise OutputParserException(msg, llm_output=text) from e
+ @override
def get_format_instructions(self) -> str:
# Copy schema to avoid altering original Pydantic schema.
if hasattr(self.pydantic_object, "model_json_schema"):
@@ -69,5 +72,6 @@ class YamlOutputParser(BaseOutputParser[T]):
return "yaml"
@property
+ @override
def OutputType(self) -> type[T]:
return self.pydantic_object
diff --git a/libs/langchain/langchain/retrievers/document_compressors/chain_extract.py b/libs/langchain/langchain/retrievers/document_compressors/chain_extract.py
index cc156007e0..14fe23cd49 100644
--- a/libs/langchain/langchain/retrievers/document_compressors/chain_extract.py
+++ b/libs/langchain/langchain/retrievers/document_compressors/chain_extract.py
@@ -12,6 +12,7 @@ from langchain_core.output_parsers import BaseOutputParser, StrOutputParser
from langchain_core.prompts import PromptTemplate
from langchain_core.runnables import Runnable
from pydantic import ConfigDict
+from typing_extensions import override
from langchain.chains.llm import LLMChain
from langchain.retrievers.document_compressors.chain_extract_prompt import (
@@ -29,6 +30,7 @@ class NoOutputParser(BaseOutputParser[str]):
no_output_str: str = "NO_OUTPUT"
+ @override
def parse(self, text: str) -> str:
cleaned_text = text.strip()
if cleaned_text == self.no_output_str:
diff --git a/libs/langchain/langchain/retrievers/ensemble.py b/libs/langchain/langchain/retrievers/ensemble.py
index 2357d4b2ff..8392680284 100644
--- a/libs/langchain/langchain/retrievers/ensemble.py
+++ b/libs/langchain/langchain/retrievers/ensemble.py
@@ -81,7 +81,7 @@ class EnsembleRetriever(BaseRetriever):
@model_validator(mode="before")
@classmethod
- def set_weights(cls, values: dict[str, Any]) -> Any:
+ def _set_weights(cls, values: dict[str, Any]) -> Any:
if not values.get("weights"):
n_retrievers = len(values["retrievers"])
values["weights"] = [1 / n_retrievers] * n_retrievers
diff --git a/libs/langchain/langchain/retrievers/multi_query.py b/libs/langchain/langchain/retrievers/multi_query.py
index bbb116ce38..cb7f734348 100644
--- a/libs/langchain/langchain/retrievers/multi_query.py
+++ b/libs/langchain/langchain/retrievers/multi_query.py
@@ -14,6 +14,7 @@ from langchain_core.prompts import BasePromptTemplate
from langchain_core.prompts.prompt import PromptTemplate
from langchain_core.retrievers import BaseRetriever
from langchain_core.runnables import Runnable
+from typing_extensions import override
from langchain.chains.llm import LLMChain
@@ -23,6 +24,7 @@ logger = logging.getLogger(__name__)
class LineListOutputParser(BaseOutputParser[list[str]]):
"""Output parser for a list of lines."""
+ @override
def parse(self, text: str) -> list[str]:
lines = text.strip().split("\n")
return list(filter(None, lines)) # Remove empty lines
diff --git a/libs/langchain/langchain/retrievers/multi_vector.py b/libs/langchain/langchain/retrievers/multi_vector.py
index ad9f90befc..94e80cbe4d 100644
--- a/libs/langchain/langchain/retrievers/multi_vector.py
+++ b/libs/langchain/langchain/retrievers/multi_vector.py
@@ -43,7 +43,7 @@ class MultiVectorRetriever(BaseRetriever):
@model_validator(mode="before")
@classmethod
- def shim_docstore(cls, values: dict) -> Any:
+ def _shim_docstore(cls, values: dict) -> Any:
byte_store = values.get("byte_store")
docstore = values.get("docstore")
if byte_store is not None:
diff --git a/libs/langchain/langchain/retrievers/parent_document_retriever.py b/libs/langchain/langchain/retrievers/parent_document_retriever.py
index 85ca11b97b..b1a70c423f 100644
--- a/libs/langchain/langchain/retrievers/parent_document_retriever.py
+++ b/libs/langchain/langchain/retrievers/parent_document_retriever.py
@@ -147,6 +147,20 @@ class ParentDocumentRetriever(MultiVectorRetriever):
add_to_docstore: bool = True, # noqa: FBT001,FBT002
**kwargs: Any,
) -> None:
+ """Adds documents to the docstore and vectorstores.
+
+ Args:
+ documents: List of documents to add
+ ids: Optional list of ids for documents. If provided should be the same
+ length as the list of documents. Can be provided if parent documents
+ are already in the document store and you don't want to re-add
+ to the docstore. If not provided, random UUIDs will be used as
+ ids.
+ add_to_docstore: Boolean of whether to add documents to docstore.
+ This can be false if and only if `ids` are provided. You may want
+ to set this to False if the documents are already in the docstore
+ and you don't want to re-add them.
+ """
docs, full_docs = self._split_docs_for_adding(
documents,
ids,
diff --git a/libs/langchain/langchain/retrievers/self_query/base.py b/libs/langchain/langchain/retrievers/self_query/base.py
index 5a53203f2e..ba15288307 100644
--- a/libs/langchain/langchain/retrievers/self_query/base.py
+++ b/libs/langchain/langchain/retrievers/self_query/base.py
@@ -360,6 +360,25 @@ class SelfQueryRetriever(BaseRetriever):
use_original_query: bool = False, # noqa: FBT001,FBT002
**kwargs: Any,
) -> "SelfQueryRetriever":
+ """Create a SelfQueryRetriever from an LLM and a vector store.
+
+ Args:
+ llm: The language model to use for generating queries.
+ vectorstore: The vector store to use for retrieving documents.
+ document_contents: Description of the page contents of the document to be
+ queried.
+ metadata_field_info: Metadata field information for the documents.
+ structured_query_translator: Optional translator for turning internal query
+ language into vectorstore search params.
+ chain_kwargs: Additional keyword arguments for the query constructor.
+ enable_limit: Whether to enable the limit operator.
+ use_original_query: Whether to use the original query instead of the revised
+ query from the LLM.
+ **kwargs: Additional keyword arguments for the SelfQueryRetriever.
+
+ Returns:
+ An instance of SelfQueryRetriever.
+ """
if structured_query_translator is None:
structured_query_translator = _get_builtin_translator(vectorstore)
chain_kwargs = chain_kwargs or {}
diff --git a/libs/langchain/langchain/runnables/hub.py b/libs/langchain/langchain/runnables/hub.py
index a6b93add4f..92a5037441 100644
--- a/libs/langchain/langchain/runnables/hub.py
+++ b/libs/langchain/langchain/runnables/hub.py
@@ -19,6 +19,18 @@ class HubRunnable(RunnableBindingBase[Input, Output]):
api_key: Optional[str] = None,
**kwargs: Any,
) -> None:
+ """Initialize the HubRunnable.
+
+ Args:
+ owner_repo_commit: The full name of the prompt to pull from in the format of
+ `owner/prompt_name:commit_hash` or `owner/prompt_name`
+ or just `prompt_name` if it's your own prompt.
+ api_url: The URL of the LangChain Hub API.
+ Defaults to the hosted API service if you have an api key set,
+ or a localhost instance if not.
+ api_key: The API key to use to authenticate with the LangChain Hub API.
+ **kwargs: Additional keyword arguments to pass to the parent class.
+ """
from langchain.hub import pull
pulled = pull(owner_repo_commit, api_url=api_url, api_key=api_key)
diff --git a/libs/langchain/langchain/runnables/openai_functions.py b/libs/langchain/langchain/runnables/openai_functions.py
index c381ff10c1..e6c0111c8e 100644
--- a/libs/langchain/langchain/runnables/openai_functions.py
+++ b/libs/langchain/langchain/runnables/openai_functions.py
@@ -36,6 +36,12 @@ class OpenAIFunctionsRouter(RunnableBindingBase[BaseMessage, Any]):
],
functions: Optional[list[OpenAIFunction]] = None,
):
+ """Initialize the OpenAIFunctionsRouter.
+
+ Args:
+ runnables: A mapping of function names to runnables.
+ functions: Optional list of functions to check against the runnables.
+ """
if functions is not None:
if len(functions) != len(runnables):
msg = "The number of functions does not match the number of runnables."
diff --git a/libs/langchain/langchain/smith/evaluation/config.py b/libs/langchain/langchain/smith/evaluation/config.py
index d8752c80c8..a6fef4259e 100644
--- a/libs/langchain/langchain/smith/evaluation/config.py
+++ b/libs/langchain/langchain/smith/evaluation/config.py
@@ -10,6 +10,7 @@ from langsmith import RunEvaluator
from langsmith.evaluation.evaluator import EvaluationResult, EvaluationResults
from langsmith.schemas import Example, Run
from pydantic import BaseModel, ConfigDict, Field
+from typing_extensions import override
from langchain.evaluation.criteria.eval_chain import CRITERIA_TYPE
from langchain.evaluation.embedding_distance.base import (
@@ -78,6 +79,7 @@ class SingleKeyEvalConfig(EvalConfig):
"""The key from the traced run's inputs dictionary to use to represent the
input. If not provided, it will be inferred automatically."""
+ @override
def get_kwargs(self) -> dict[str, Any]:
kwargs = super().get_kwargs()
# Filer out the keys that are not needed for the evaluator.
@@ -176,13 +178,6 @@ class RunEvalConfig(BaseModel):
llm: Optional[BaseLanguageModel] = None
evaluator_type: EvaluatorType = EvaluatorType.CRITERIA
- def __init__(
- self,
- criteria: Optional[CRITERIA_TYPE] = None,
- **kwargs: Any,
- ) -> None:
- super().__init__(criteria=criteria, **kwargs) # type: ignore[call-arg]
-
class LabeledCriteria(SingleKeyEvalConfig):
"""Configuration for a labeled (with references) criteria evaluator.
@@ -198,13 +193,6 @@ class RunEvalConfig(BaseModel):
llm: Optional[BaseLanguageModel] = None
evaluator_type: EvaluatorType = EvaluatorType.LABELED_CRITERIA
- def __init__(
- self,
- criteria: Optional[CRITERIA_TYPE] = None,
- **kwargs: Any,
- ) -> None:
- super().__init__(criteria=criteria, **kwargs) # type: ignore[call-arg]
-
class EmbeddingDistance(SingleKeyEvalConfig):
"""Configuration for an embedding distance evaluator.
@@ -345,6 +333,7 @@ class RunEvalConfig(BaseModel):
class ScoreString(SingleKeyEvalConfig):
"""Configuration for a score string evaluator.
+
This is like the criteria evaluator but it is configured by
default to return a score on the scale from 1-10.
@@ -370,13 +359,7 @@ class RunEvalConfig(BaseModel):
normalize_by: Optional[float] = None
prompt: Optional[BasePromptTemplate] = None
- def __init__(
- self,
- criteria: Optional[CRITERIA_TYPE] = None,
- normalize_by: Optional[float] = None,
- **kwargs: Any,
- ) -> None:
- super().__init__(criteria=criteria, normalize_by=normalize_by, **kwargs) # type: ignore[call-arg]
-
class LabeledScoreString(ScoreString):
+ """ "Configuration for a labeled score string evaluator."""
+
evaluator_type: EvaluatorType = EvaluatorType.LABELED_SCORE_STRING
diff --git a/libs/langchain/langchain/smith/evaluation/progress.py b/libs/langchain/langchain/smith/evaluation/progress.py
index 7f7ba5f981..613a4f6307 100644
--- a/libs/langchain/langchain/smith/evaluation/progress.py
+++ b/libs/langchain/langchain/smith/evaluation/progress.py
@@ -8,6 +8,7 @@ from uuid import UUID
from langchain_core.callbacks import base as base_callbacks
from langchain_core.documents import Document
from langchain_core.outputs import LLMResult
+from typing_extensions import override
class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
@@ -48,6 +49,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
end = "" if self.counter < self.total else self.end_with
print(f"\r[{arrow + spaces}] {self.counter}/{self.total}", end=end) # noqa: T201
+ @override
def on_chain_error(
self,
error: BaseException,
@@ -59,6 +61,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
if parent_run_id is None:
self.increment()
+ @override
def on_chain_end(
self,
outputs: dict[str, Any],
@@ -70,6 +73,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
if parent_run_id is None:
self.increment()
+ @override
def on_retriever_error(
self,
error: BaseException,
@@ -81,6 +85,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
if parent_run_id is None:
self.increment()
+ @override
def on_retriever_end(
self,
documents: Sequence[Document],
@@ -92,6 +97,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
if parent_run_id is None:
self.increment()
+ @override
def on_llm_error(
self,
error: BaseException,
@@ -103,6 +109,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
if parent_run_id is None:
self.increment()
+ @override
def on_llm_end(
self,
response: LLMResult,
@@ -114,6 +121,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
if parent_run_id is None:
self.increment()
+ @override
def on_tool_error(
self,
error: BaseException,
@@ -125,6 +133,7 @@ class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
if parent_run_id is None:
self.increment()
+ @override
def on_tool_end(
self,
output: str,
diff --git a/libs/langchain/langchain/smith/evaluation/runner_utils.py b/libs/langchain/langchain/smith/evaluation/runner_utils.py
index 6ca7656d15..89096c0179 100644
--- a/libs/langchain/langchain/smith/evaluation/runner_utils.py
+++ b/libs/langchain/langchain/smith/evaluation/runner_utils.py
@@ -155,9 +155,24 @@ class EvalError(dict):
"""Your architecture raised an error."""
def __init__(self, Error: BaseException, **kwargs: Any) -> None:
+ """Initialize the EvalError with an error and additional attributes.
+
+ Args:
+ Error: The error that occurred.
+ **kwargs: Additional attributes to include in the error.
+ """
super().__init__(Error=Error, **kwargs)
def __getattr__(self, name: str) -> Any:
+ """Get an attribute from the EvalError.
+
+ Args:
+ name: The name of the attribute to get.
+ Returns:
+ The value of the attribute.
+ Raises:
+ AttributeError: If the attribute does not exist.
+ """
try:
return self[name]
except KeyError as e:
@@ -1330,6 +1345,113 @@ async def arun_on_dataset(
revision_id: Optional[str] = None,
**kwargs: Any,
) -> dict[str, Any]:
+ """Run on dataset.
+
+ Run the Chain or language model on a dataset and store traces
+ to the specified project name.
+
+ For the (usually faster) async version of this function,
+ see :func:`arun_on_dataset`.
+
+ Args:
+ dataset_name: Name of the dataset to run the chain on.
+ llm_or_chain_factory: Language model or Chain constructor to run
+ over the dataset. The Chain constructor is used to permit
+ independent calls on each example without carrying over state.
+ evaluation: Configuration for evaluators to run on the
+ results of the chain
+ concurrency_level: The number of async tasks to run concurrently.
+ project_name: Name of the project to store the traces in.
+ Defaults to {dataset_name}-{chain class name}-{datetime}.
+ project_metadata: Optional metadata to add to the project.
+ Useful for storing information the test variant.
+ (prompt version, model version, etc.)
+ client: LangSmith client to use to access the dataset and to
+ log feedback and run traces.
+ verbose: Whether to print progress.
+ tags: Tags to add to each run in the project.
+ revision_id: Optional revision identifier to assign this test run to
+ track the performance of different versions of your system.
+ Returns:
+ A dictionary containing the run's project name and the resulting model outputs.
+
+ Examples:
+
+ .. code-block:: python
+
+ from langsmith import Client
+ from langchain_openai import ChatOpenAI
+ from langchain.chains import LLMChain
+ from langchain.smith import smith_eval.RunEvalConfig, run_on_dataset
+
+ # Chains may have memory. Passing in a constructor function lets the
+ # evaluation framework avoid cross-contamination between runs.
+ def construct_chain():
+ llm = ChatOpenAI(temperature=0)
+ chain = LLMChain.from_string(
+ llm,
+ "What's the answer to {your_input_key}"
+ )
+ return chain
+
+ # Load off-the-shelf evaluators via config or the EvaluatorType (string or enum)
+ evaluation_config = smith_eval.RunEvalConfig(
+ evaluators=[
+ "qa", # "Correctness" against a reference answer
+ "embedding_distance",
+ smith_eval.RunEvalConfig.Criteria("helpfulness"),
+ smith_eval.RunEvalConfig.Criteria({
+ "fifth-grader-score": "Do you have to be smarter than a fifth grader to answer this question?"
+ }),
+ ]
+ )
+
+ client = Client()
+ await arun_on_dataset(
+ client,
+ dataset_name="<my_dataset_name>",
+ llm_or_chain_factory=construct_chain,
+ evaluation=evaluation_config,
+ )
+
+ You can also create custom evaluators by subclassing the
+ :class:`StringEvaluator <langchain.evaluation.schema.StringEvaluator>`
+ or LangSmith's `RunEvaluator` classes.
+
+ .. code-block:: python
+
+ from typing import Optional
+ from langchain.evaluation import StringEvaluator
+
+ class MyStringEvaluator(StringEvaluator):
+
+ @property
+ def requires_input(self) -> bool:
+ return False
+
+ @property
+ def requires_reference(self) -> bool:
+ return True
+
+ @property
+ def evaluation_name(self) -> str:
+ return "exact_match"
+
+ def _evaluate_strings(self, prediction, reference=None, input=None, **kwargs) -> dict:
+ return {"score": prediction == reference}
+
+
+ evaluation_config = smith_eval.RunEvalConfig(
+ custom_evaluators = [MyStringEvaluator()],
+ )
+
+ await arun_on_dataset(
+ client,
+ dataset_name="<my_dataset_name>",
+ llm_or_chain_factory=construct_chain,
+ evaluation=evaluation_config,
+ )
+ """ # noqa: E501
input_mapper = kwargs.pop("input_mapper", None)
if input_mapper:
warn_deprecated("0.0.305", message=_INPUT_MAPPER_DEP_WARNING, pending=True)
@@ -1395,6 +1517,113 @@ def run_on_dataset(
revision_id: Optional[str] = None,
**kwargs: Any,
) -> dict[str, Any]:
+ """Run on dataset.
+
+ Run the Chain or language model on a dataset and store traces
+ to the specified project name.
+
+ For the (usually faster) async version of this function,
+ see :func:`arun_on_dataset`.
+
+ Args:
+ dataset_name: Name of the dataset to run the chain on.
+ llm_or_chain_factory: Language model or Chain constructor to run
+ over the dataset. The Chain constructor is used to permit
+ independent calls on each example without carrying over state.
+ evaluation: Configuration for evaluators to run on the
+ results of the chain
+ concurrency_level: The number of async tasks to run concurrently.
+ project_name: Name of the project to store the traces in.
+ Defaults to {dataset_name}-{chain class name}-{datetime}.
+ project_metadata: Optional metadata to add to the project.
+ Useful for storing information the test variant.
+ (prompt version, model version, etc.)
+ client: LangSmith client to use to access the dataset and to
+ log feedback and run traces.
+ verbose: Whether to print progress.
+ tags: Tags to add to each run in the project.
+ revision_id: Optional revision identifier to assign this test run to
+ track the performance of different versions of your system.
+ Returns:
+ A dictionary containing the run's project name and the resulting model outputs.
+
+ Examples:
+
+ .. code-block:: python
+
+ from langsmith import Client
+ from langchain_openai import ChatOpenAI
+ from langchain.chains import LLMChain
+ from langchain.smith import smith_eval.RunEvalConfig, run_on_dataset
+
+ # Chains may have memory. Passing in a constructor function lets the
+ # evaluation framework avoid cross-contamination between runs.
+ def construct_chain():
+ llm = ChatOpenAI(temperature=0)
+ chain = LLMChain.from_string(
+ llm,
+ "What's the answer to {your_input_key}"
+ )
+ return chain
+
+ # Load off-the-shelf evaluators via config or the EvaluatorType (string or enum)
+ evaluation_config = smith_eval.RunEvalConfig(
+ evaluators=[
+ "qa", # "Correctness" against a reference answer
+ "embedding_distance",
+ smith_eval.RunEvalConfig.Criteria("helpfulness"),
+ smith_eval.RunEvalConfig.Criteria({
+ "fifth-grader-score": "Do you have to be smarter than a fifth grader to answer this question?"
+ }),
+ ]
+ )
+
+ client = Client()
+ run_on_dataset(
+ client,
+ dataset_name="<my_dataset_name>",
+ llm_or_chain_factory=construct_chain,
+ evaluation=evaluation_config,
+ )
+
+ You can also create custom evaluators by subclassing the
+ :class:`StringEvaluator <langchain.evaluation.schema.StringEvaluator>`
+ or LangSmith's `RunEvaluator` classes.
+
+ .. code-block:: python
+
+ from typing import Optional
+ from langchain.evaluation import StringEvaluator
+
+ class MyStringEvaluator(StringEvaluator):
+
+ @property
+ def requires_input(self) -> bool:
+ return False
+
+ @property
+ def requires_reference(self) -> bool:
+ return True
+
+ @property
+ def evaluation_name(self) -> str:
+ return "exact_match"
+
+ def _evaluate_strings(self, prediction, reference=None, input=None, **kwargs) -> dict:
+ return {"score": prediction == reference}
+
+
+ evaluation_config = smith_eval.RunEvalConfig(
+ custom_evaluators = [MyStringEvaluator()],
+ )
+
+ run_on_dataset(
+ client,
+ dataset_name="<my_dataset_name>",
+ llm_or_chain_factory=construct_chain,
+ evaluation=evaluation_config,
+ )
+ """ # noqa: E501
input_mapper = kwargs.pop("input_mapper", None)
if input_mapper:
warn_deprecated("0.0.305", message=_INPUT_MAPPER_DEP_WARNING, pending=True)
@@ -1456,117 +1685,3 @@ def run_on_dataset(
)
return container.finish(batch_results, verbose=verbose)
-
-
-_RUN_ON_DATASET_DOCSTRING = """
-Run the Chain or language model on a dataset and store traces
-to the specified project name.
-
-Args:
- dataset_name: Name of the dataset to run the chain on.
- llm_or_chain_factory: Language model or Chain constructor to run
- over the dataset. The Chain constructor is used to permit
- independent calls on each example without carrying over state.
- evaluation: Configuration for evaluators to run on the
- results of the chain
- concurrency_level: The number of async tasks to run concurrently.
- project_name: Name of the project to store the traces in.
- Defaults to {dataset_name}-{chain class name}-{datetime}.
- project_metadata: Optional metadata to add to the project.
- Useful for storing information the test variant.
- (prompt version, model version, etc.)
- client: LangSmith client to use to access the dataset and to
- log feedback and run traces.
- verbose: Whether to print progress.
- tags: Tags to add to each run in the project.
- revision_id: Optional revision identifier to assign this test run to
- track the performance of different versions of your system.
-Returns:
- A dictionary containing the run's project name and the resulting model outputs.
-
-
-For the (usually faster) async version of this function, see :func:`arun_on_dataset`.
-
-Examples
---------
-
-.. code-block:: python
-
- from langsmith import Client
- from langchain_openai import ChatOpenAI
- from langchain.chains import LLMChain
- from langchain.smith import smith_eval.RunEvalConfig, run_on_dataset
-
- # Chains may have memory. Passing in a constructor function lets the
- # evaluation framework avoid cross-contamination between runs.
- def construct_chain():
- llm = ChatOpenAI(temperature=0)
- chain = LLMChain.from_string(
- llm,
- "What's the answer to {your_input_key}"
- )
- return chain
-
- # Load off-the-shelf evaluators via config or the EvaluatorType (string or enum)
- evaluation_config = smith_eval.RunEvalConfig(
- evaluators=[
- "qa", # "Correctness" against a reference answer
- "embedding_distance",
- smith_eval.RunEvalConfig.Criteria("helpfulness"),
- smith_eval.RunEvalConfig.Criteria({
- "fifth-grader-score": "Do you have to be smarter than a fifth grader to answer this question?"
- }),
- ]
- )
-
- client = Client()
- run_on_dataset(
- client,
- dataset_name="<my_dataset_name>",
- llm_or_chain_factory=construct_chain,
- evaluation=evaluation_config,
- )
-
-You can also create custom evaluators by subclassing the
-:class:`StringEvaluator <langchain.evaluation.schema.StringEvaluator>`
-or LangSmith's `RunEvaluator` classes.
-
-.. code-block:: python
-
- from typing import Optional
- from langchain.evaluation import StringEvaluator
-
- class MyStringEvaluator(StringEvaluator):
-
- @property
- def requires_input(self) -> bool:
- return False
-
- @property
- def requires_reference(self) -> bool:
- return True
-
- @property
- def evaluation_name(self) -> str:
- return "exact_match"
-
- def _evaluate_strings(self, prediction, reference=None, input=None, **kwargs) -> dict:
- return {"score": prediction == reference}
-
-
- evaluation_config = smith_eval.RunEvalConfig(
- custom_evaluators = [MyStringEvaluator()],
- )
-
- run_on_dataset(
- client,
- dataset_name="<my_dataset_name>",
- llm_or_chain_factory=construct_chain,
- evaluation=evaluation_config,
- )
-""" # noqa: E501
-run_on_dataset.__doc__ = _RUN_ON_DATASET_DOCSTRING
-arun_on_dataset.__doc__ = _RUN_ON_DATASET_DOCSTRING.replace(
- "run_on_dataset(",
- "await arun_on_dataset(",
-)
diff --git a/libs/langchain/langchain/smith/evaluation/string_run_evaluator.py b/libs/langchain/langchain/smith/evaluation/string_run_evaluator.py
index 614eb82eba..b481c2a3fb 100644
--- a/libs/langchain/langchain/smith/evaluation/string_run_evaluator.py
+++ b/libs/langchain/langchain/smith/evaluation/string_run_evaluator.py
@@ -16,6 +16,7 @@ from langchain_core.load.serializable import Serializable
from langchain_core.messages import BaseMessage, get_buffer_string, messages_from_dict
from langsmith import EvaluationResult, RunEvaluator
from langsmith.schemas import DataType, Example, Run
+from typing_extensions import override
from langchain.chains.base import Chain
from langchain.evaluation.schema import StringEvaluator
@@ -70,6 +71,15 @@ class LLMStringRunMapper(StringRunMapper):
raise ValueError(msg)
def serialize_inputs(self, inputs: dict) -> str:
+ """Serialize inputs.
+
+ Args:
+ inputs: The inputs from the run, expected to contain prompts or messages.
+ Returns:
+ The serialized input text from the prompts or messages.
+ Raises:
+ ValueError: If neither prompts nor messages are found in the inputs.
+ """
if "prompts" in inputs: # Should we even accept this?
input_ = "\n\n".join(inputs["prompts"])
elif "prompt" in inputs:
@@ -82,6 +92,18 @@ class LLMStringRunMapper(StringRunMapper):
return input_
def serialize_outputs(self, outputs: dict) -> str:
+ """Serialize outputs.
+
+ Args:
+ outputs: The outputs from the run, expected to contain generations.
+
+ Returns:
+ The serialized output text from the first generation.
+
+ Raises:
+ ValueError: If no generations are found in the outputs,
+ or if the generations are empty.
+ """
if not outputs.get("generations"):
msg = "Cannot evaluate LLM Run without generations."
raise ValueError(msg)
@@ -185,6 +207,7 @@ class ChainStringRunMapper(StringRunMapper):
class ToolStringRunMapper(StringRunMapper):
"""Map an input to the tool."""
+ @override
def map(self, run: Run) -> dict[str, str]:
if not run.outputs:
msg = f"Run {run.id} has no outputs to evaluate."
@@ -256,10 +279,12 @@ class StringRunEvaluatorChain(Chain, RunEvaluator):
"""The evaluation chain."""
@property
+ @override
def input_keys(self) -> list[str]:
return ["run", "example"]
@property
+ @override
def output_keys(self) -> list[str]:
return ["feedback"]
diff --git a/libs/langchain/langchain/smith/evaluation/utils.py b/libs/langchain/langchain/smith/evaluation/utils.py
deleted file mode 100644
index e69de29bb2..0000000000
diff --git a/libs/langchain/pyproject.toml b/libs/langchain/pyproject.toml
index 135c1b15bf..f558488669 100644
--- a/libs/langchain/pyproject.toml
+++ b/libs/langchain/pyproject.toml
@@ -149,7 +149,7 @@ select = [
"ASYNC", # flake8-async
"C4", # flake8-comprehensions
"COM", # flake8-commas
- "D", # pydocstyle
+ "D1", # pydocstyle: missing docstring
"DTZ", # flake8-datetimez
"E", # pycodestyle error
"EM", # flake8-errmsg
@@ -186,14 +186,6 @@ select = [
"YTT", # flake8-2020
]
ignore = [
- "D100", # pydocstyle: Missing docstring in public module
- "D101", # pydocstyle: Missing docstring in public class
- "D102", # pydocstyle: Missing docstring in public method
- "D103", # pydocstyle: Missing docstring in public function
- "D104", # pydocstyle: Missing docstring in public package
- "D105", # pydocstyle: Missing docstring in magic method
- "D107", # pydocstyle: Missing docstring in __init__
- "D407", # pydocstyle: Missing-dashed-underline-after-section
"COM812", # Messes with the formatter
"ISC001", # Messes with the formatter
"PERF203", # Rarely useful
@@ -203,6 +195,8 @@ ignore = [
"UP007", # pyupgrade: non-pep604-annotation-union
# TODO rules
+ "D100", # pydocstyle: missing docstring in public module
+ "D104", # pydocstyle: missing docstring in public package
"PLC0415", # pylint: import-outside-top-level
"TRY301", # tryceratops: raise-within-try
]
@@ -211,12 +205,9 @@ unfixable = ["B028"] # People should intentionally tune the stacklevel
pydocstyle.convention = "google"
pyupgrade.keep-runtime-typing = true
-[tool.ruff.lint.per-file-ignores]
-"tests/*" = ["D"]
-"!langchain/indexes/vectorstore.py" = ["D"]
-
[tool.ruff.lint.extend-per-file-ignores]
"tests/**/*.py" = [
+ "D1", # Docstrings not mandatory in tests
"S101", # Tests need assertions
"S311", # Standard pseudo-random generators are not suitable for cryptographic purposes
"SLF001", # Private member access in tests