langchain 0.2.5__py3-none-any.whl → 0.2.7__py3-none-any.whl

langchain/agents/mrkl/base.py

@@ -1,4 +1,5 @@
 """Attempt to implement MRKL systems as described in arxiv.org/pdf/2205.00445.pdf."""
+
 from __future__ import annotations
 
 from typing import Any, Callable, List, NamedTuple, Optional, Sequence
@@ -20,9 +21,9 @@ from langchain.tools.render import render_text_description
 
 
 class ChainConfig(NamedTuple):
-    """Configuration for chain to use in MRKL system.
+    """Configuration for a chain to use in MRKL system.
 
-    Args:
+    Parameters:
         action_name: Name of the action.
         action: Action function to call.
         action_description: Description of the action.
@@ -35,7 +36,11 @@ class ChainConfig(NamedTuple):
 
 @deprecated("0.1.0", alternative="create_react_agent", removal="0.3.0")
 class ZeroShotAgent(Agent):
-    """Agent for the MRKL chain."""
+    """Agent for the MRKL chain.
+
+    Parameters:
+        output_parser: Output parser for the agent.
+    """
 
     output_parser: AgentOutputParser = Field(default_factory=MRKLOutputParser)
 
@@ -50,12 +55,20 @@ class ZeroShotAgent(Agent):
 
     @property
     def observation_prefix(self) -> str:
-        """Prefix to append the observation with."""
+        """Prefix to append the observation with.
+
+        Returns:
+            "Observation: "
+        """
         return "Observation: "
 
     @property
     def llm_prefix(self) -> str:
-        """Prefix to append the llm call with."""
+        """Prefix to append the llm call with.
+
+        Returns:
+            "Thought: "
+        """
         return "Thought:"
 
     @classmethod
@@ -72,9 +85,12 @@ class ZeroShotAgent(Agent):
         Args:
             tools: List of tools the agent will have access to, used to format the
                 prompt.
-            prefix: String to put before the list of tools.
-            suffix: String to put after the list of tools.
+            prefix: String to put before the list of tools. Defaults to PREFIX.
+            suffix: String to put after the list of tools. Defaults to SUFFIX.
+            format_instructions: Instructions on how to use the tools.
+                Defaults to FORMAT_INSTRUCTIONS
             input_variables: List of input variables the final prompt will expect.
+                Defaults to None.
 
         Returns:
             A PromptTemplate with the template assembled from the pieces here.
@@ -100,7 +116,20 @@ class ZeroShotAgent(Agent):
         input_variables: Optional[List[str]] = None,
         **kwargs: Any,
     ) -> Agent:
-        """Construct an agent from an LLM and tools."""
+        """Construct an agent from an LLM and tools.
+
+        Args:
+            llm: The LLM to use as the agent LLM.
+            tools: The tools to use.
+            callback_manager: The callback manager to use. Defaults to None.
+            output_parser: The output parser to use. Defaults to None.
+            prefix: The prefix to use. Defaults to PREFIX.
+            suffix: The suffix to use. Defaults to SUFFIX.
+            format_instructions: The format instructions to use.
+                Defaults to FORMAT_INSTRUCTIONS.
+            input_variables: The input variables to use. Defaults to None.
+            **kwargs: Additional parameters to pass to the agent.
+        """
         cls._validate_tools(tools)
         prompt = cls.create_prompt(
             tools,
@@ -141,13 +170,13 @@ class ZeroShotAgent(Agent):
 
 @deprecated("0.1.0", removal="0.3.0")
 class MRKLChain(AgentExecutor):
-    """[Deprecated] Chain that implements the MRKL system."""
+    """Chain that implements the MRKL system."""
 
     @classmethod
     def from_chains(
         cls, llm: BaseLanguageModel, chains: List[ChainConfig], **kwargs: Any
     ) -> AgentExecutor:
-        """User friendly way to initialize the MRKL chain.
+        """User-friendly way to initialize the MRKL chain.
 
         This is intended to be an easy way to get up and running with the
         MRKL chain.

langchain/agents/mrkl/output_parser.py

@@ -30,6 +30,18 @@ class MRKLOutputParser(AgentOutputParser):
         return self.format_instructions
 
     def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
+        """Parse the output from the agent into
+        an AgentAction or AgentFinish object.
+
+        Args:
+            text: The text to parse.
+
+        Returns:
+            An AgentAction or AgentFinish object.
+
+        Raises:
+            OutputParserException: If the output could not be parsed.
+        """
         includes_answer = FINAL_ANSWER_ACTION in text
         regex = (
             r"Action\s*\d*\s*:[\s]*(.*?)[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)"

langchain/agents/openai_assistant/base.py

@@ -33,18 +33,34 @@ if TYPE_CHECKING:
 
 
 class OpenAIAssistantFinish(AgentFinish):
-    """AgentFinish with run and thread metadata."""
+    """AgentFinish with run and thread metadata.
+
+    Parameters:
+        run_id: Run id.
+        thread_id: Thread id.
+    """
 
     run_id: str
     thread_id: str
 
     @classmethod
     def is_lc_serializable(cls) -> bool:
+        """Check if the class is serializable by LangChain.
+
+        Returns:
+            False
+        """
         return False
 
 
 class OpenAIAssistantAction(AgentAction):
-    """AgentAction with info needed to submit custom tool output to existing run."""
+    """AgentAction with info needed to submit custom tool output to existing run.
+
+    Parameters:
+        tool_call_id: Tool call id.
+        run_id: Run id.
+        thread_id: Thread id
+    """
 
     tool_call_id: str
     run_id: str
@@ -52,6 +68,11 @@ class OpenAIAssistantAction(AgentAction):
 
     @classmethod
     def is_lc_serializable(cls) -> bool:
+        """Check if the class is serializable by LangChain.
+
+        Returns:
+            False
+        """
         return False
 
 
@@ -210,7 +231,7 @@ class OpenAIAssistantRunnable(RunnableSerializable[Dict, OutputType]):
     as_agent: bool = False
     """Use as a LangChain agent, compatible with the AgentExecutor."""
 
-    @root_validator()
+    @root_validator(pre=False, skip_on_failure=True)
     def validate_async_client(cls, values: dict) -> dict:
         if values["async_client"] is None:
             import openai
@@ -238,7 +259,8 @@ class OpenAIAssistantRunnable(RunnableSerializable[Dict, OutputType]):
             tools: Assistant tools. Can be passed in OpenAI format or as BaseTools.
             model: Assistant model to use.
             client: OpenAI or AzureOpenAI client.
-                Will create default OpenAI client if not specified.
+                Will create a default OpenAI client if not specified.
+            **kwargs: Additional arguments.
 
         Returns:
             OpenAIAssistantRunnable configured to run using the created assistant.
@@ -272,12 +294,12 @@ class OpenAIAssistantRunnable(RunnableSerializable[Dict, OutputType]):
                 model: Override Assistant model for this run.
                 tools: Override Assistant tools for this run.
                 run_metadata: Metadata to associate with new run.
-            config: Runnable config:
+            config: Runnable config. Defaults to None.
 
         Return:
             If self.as_agent, will return
-                Union[List[OpenAIAssistantAction], OpenAIAssistantFinish]. Otherwise,
-                will return OpenAI types
+                Union[List[OpenAIAssistantAction], OpenAIAssistantFinish].
+                Otherwise, will return OpenAI types
                 Union[List[ThreadMessage], List[RequiredActionFunctionToolCall]].
         """
 
@@ -351,7 +373,7 @@ class OpenAIAssistantRunnable(RunnableSerializable[Dict, OutputType]):
         ] = None,
         **kwargs: Any,
     ) -> OpenAIAssistantRunnable:
-        """Create an AsyncOpenAI Assistant and instantiate the Runnable.
+        """Async create an AsyncOpenAI Assistant and instantiate the Runnable.
 
         Args:
             name: Assistant name.
@@ -359,7 +381,7 @@ class OpenAIAssistantRunnable(RunnableSerializable[Dict, OutputType]):
             tools: Assistant tools. Can be passed in OpenAI format or as BaseTools.
             model: Assistant model to use.
             async_client: AsyncOpenAI client.
-            Will create default async_client if not specified.
+                Will create default async_client if not specified.
 
         Returns:
             AsyncOpenAIAssistantRunnable configured to run using the created assistant.
@@ -387,19 +409,20 @@ class OpenAIAssistantRunnable(RunnableSerializable[Dict, OutputType]):
                 run_id: Existing run to use. Should only be supplied when providing
                     the tool output for a required action after an initial invocation.
                 file_ids: File ids to include in new run. Used for retrieval.
-                message_metadata: Metadata to associate with new message.
+                message_metadata: Metadata to associate with a new message.
                 thread_metadata: Metadata to associate with new thread. Only relevant
-                    when new thread being created.
+                    when a new thread is created.
                 instructions: Additional run instructions.
                 model: Override Assistant model for this run.
                 tools: Override Assistant tools for this run.
                 run_metadata: Metadata to associate with new run.
-            config: Runnable config:
+            config: Runnable config. Defaults to None.
+            **kwargs: Additional arguments.
 
         Return:
             If self.as_agent, will return
-                Union[List[OpenAIAssistantAction], OpenAIAssistantFinish]. Otherwise,
-                will return OpenAI types
+                Union[List[OpenAIAssistantAction], OpenAIAssistantFinish].
+                Otherwise, will return OpenAI types
                 Union[List[ThreadMessage], List[RequiredActionFunctionToolCall]].
         """
 

langchain/agents/openai_functions_agent/agent_token_buffer_memory.py

@@ -1,4 +1,5 @@
 """Memory used to save agent output AND intermediate steps."""
+
 from typing import Any, Dict, List
 
 from langchain_core.language_models import BaseLanguageModel
@@ -12,7 +13,22 @@ from langchain.memory.chat_memory import BaseChatMemory
 
 
 class AgentTokenBufferMemory(BaseChatMemory):
-    """Memory used to save agent output AND intermediate steps."""
+    """Memory used to save agent output AND intermediate steps.
+
+    Parameters:
+        human_prefix: Prefix for human messages. Default is "Human".
+        ai_prefix: Prefix for AI messages. Default is "AI".
+        llm: Language model.
+        memory_key: Key to save memory under. Default is "history".
+        max_token_limit: Maximum number of tokens to keep in the buffer.
+            Once the buffer exceeds this many tokens, the oldest
+            messages will be pruned. Default is 12000.
+        return_messages: Whether to return messages. Default is True.
+        output_key: Key to save output under. Default is "output".
+        intermediate_steps_key: Key to save intermediate steps under.
+            Default is "intermediate_steps".
+        format_as_tools: Whether to format as tools. Default is False.
+    """
 
     human_prefix: str = "Human"
     ai_prefix: str = "AI"
@@ -33,14 +49,21 @@ class AgentTokenBufferMemory(BaseChatMemory):
 
     @property
     def memory_variables(self) -> List[str]:
-        """Will always return list of memory variables.
+        """Always return list of memory variables.
 
         :meta private:
         """
         return [self.memory_key]
 
     def load_memory_variables(self, inputs: Dict[str, Any]) -> Dict[str, Any]:
-        """Return history buffer."""
+        """Return history buffer.
+
+        Args:
+            inputs: Inputs to the agent.
+
+        Returns:
+            A dictionary with the history buffer.
+        """
         if self.return_messages:
             final_buffer: Any = self.buffer
         else:
@@ -52,7 +75,12 @@ class AgentTokenBufferMemory(BaseChatMemory):
         return {self.memory_key: final_buffer}
 
     def save_context(self, inputs: Dict[str, Any], outputs: Dict[str, Any]) -> None:
-        """Save context from this conversation to buffer. Pruned."""
+        """Save context from this conversation to buffer. Pruned.
+
+        Args:
+            inputs: Inputs to the agent.
+            outputs: Outputs from the agent.
+        """
         input_str, output_str = self._get_input_output(inputs, outputs)
         self.chat_memory.add_user_message(input_str)
         format_to_messages = (

langchain/agents/openai_functions_agent/base.py

@@ -1,4 +1,5 @@
 """Module implements an agent that uses OpenAI's APIs function enabled API."""
+
 from typing import Any, List, Optional, Sequence, Tuple, Type, Union
 
 from langchain_core._api import deprecated
@@ -41,21 +42,35 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
         prompt: The prompt for this agent, should support agent_scratchpad as one
             of the variables. For an easy way to construct this prompt, use
             `OpenAIFunctionsAgent.create_prompt(...)`
+        output_parser: The output parser for this agent. Should be an instance of
+            OpenAIFunctionsAgentOutputParser.
+            Defaults to OpenAIFunctionsAgentOutputParser.
     """
 
     llm: BaseLanguageModel
     tools: Sequence[BaseTool]
     prompt: BasePromptTemplate
-    output_parser: Type[
+    output_parser: Type[OpenAIFunctionsAgentOutputParser] = (
         OpenAIFunctionsAgentOutputParser
-    ] = OpenAIFunctionsAgentOutputParser
+    )
 
     def get_allowed_tools(self) -> List[str]:
         """Get allowed tools."""
         return [t.name for t in self.tools]
 
-    @root_validator
+    @root_validator(pre=False, skip_on_failure=True)
     def validate_prompt(cls, values: dict) -> dict:
+        """Validate prompt.
+
+        Args:
+            values: Values to validate.
+
+        Returns:
+            Validated values.
+
+        Raises:
+            ValueError: If `agent_scratchpad` is not in the prompt.
+        """
         prompt: BasePromptTemplate = values["prompt"]
         if "agent_scratchpad" not in prompt.input_variables:
             raise ValueError(
@@ -71,6 +86,8 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
 
     @property
     def functions(self) -> List[dict]:
+        """Get functions."""
+
         return [dict(convert_to_openai_function(t)) for t in self.tools]
 
     def plan(
@@ -83,11 +100,16 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
         """Given input, decided what to do.
 
         Args:
-            intermediate_steps: Steps the LLM has taken to date, along with observations
+            intermediate_steps: Steps the LLM has taken to date,
+                along with observations.
+            callbacks: Callbacks to use. Defaults to None.
+            with_functions: Whether to use functions. Defaults to True.
             **kwargs: User inputs.
 
         Returns:
             Action specifying what tool to use.
+            If the agent is finished, returns an AgentFinish.
+            If the agent is not finished, returns an AgentAction.
         """
         agent_scratchpad = format_to_openai_function_messages(intermediate_steps)
         selected_inputs = {
@@ -116,15 +138,18 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
         callbacks: Callbacks = None,
         **kwargs: Any,
     ) -> Union[AgentAction, AgentFinish]:
-        """Given input, decided what to do.
+        """Async given input, decided what to do.
 
         Args:
             intermediate_steps: Steps the LLM has taken to date,
-                along with observations
+                along with observations.
+            callbacks: Callbacks to use. Defaults to None.
             **kwargs: User inputs.
 
         Returns:
             Action specifying what tool to use.
+            If the agent is finished, returns an AgentFinish.
+            If the agent is not finished, returns an AgentAction.
         """
         agent_scratchpad = format_to_openai_function_messages(intermediate_steps)
         selected_inputs = {
@@ -145,7 +170,20 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
         intermediate_steps: List[Tuple[AgentAction, str]],
         **kwargs: Any,
     ) -> AgentFinish:
-        """Return response when agent has been stopped due to max iterations."""
+        """Return response when agent has been stopped due to max iterations.
+
+        Args:
+            early_stopping_method: The early stopping method to use.
+            intermediate_steps: Intermediate steps.
+            **kwargs: User inputs.
+
+        Returns:
+            AgentFinish.
+
+        Raises:
+            ValueError: If `early_stopping_method` is not `force` or `generate`.
+            ValueError: If `agent_decision` is not an AgentAction.
+        """
         if early_stopping_method == "force":
             # `force` just returns a constant string
             return AgentFinish(
@@ -215,7 +253,17 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
         ),
         **kwargs: Any,
     ) -> BaseSingleActionAgent:
-        """Construct an agent from an LLM and tools."""
+        """Construct an agent from an LLM and tools.
+
+        Args:
+            llm: The LLM to use as the agent.
+            tools: The tools to use.
+            callback_manager: The callback manager to use. Defaults to None.
+            extra_prompt_messages: Extra prompt messages to use. Defaults to None.
+            system_message: The system message to use.
+                Defaults to a default system message.
+            **kwargs: Additional parameters to pass to the agent.
+        """
         prompt = cls.create_prompt(
             extra_prompt_messages=extra_prompt_messages,
             system_message=system_message,
@@ -243,8 +291,11 @@ def create_openai_functions_agent(
 
     Returns:
         A Runnable sequence representing an agent. It takes as input all the same input
-        variables as the prompt passed in does. It returns as output either an
-        AgentAction or AgentFinish.
+            variables as the prompt passed in does. It returns as output either an
+            AgentAction or AgentFinish.
+
+    Raises:
+        ValueError: If `agent_scratchpad` is not in the prompt.
 
     Example:
 

langchain/agents/openai_functions_multi_agent/base.py

@@ -1,4 +1,5 @@
 """Module implements an agent that uses OpenAI's APIs function enabled API."""
+
 import json
 from json import JSONDecodeError
 from typing import Any, List, Optional, Sequence, Tuple, Union
@@ -95,7 +96,7 @@ def _parse_ai_message(message: BaseMessage) -> Union[List[AgentAction], AgentFin
 
 @deprecated("0.1.0", alternative="create_openai_tools_agent", removal="0.3.0")
 class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
-    """An Agent driven by OpenAIs function powered API.
+    """Agent driven by OpenAIs function powered API.
 
     Args:
         llm: This should be an instance of ChatOpenAI, specifically a model
@@ -114,7 +115,7 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
         """Get allowed tools."""
         return [t.name for t in self.tools]
 
-    @root_validator
+    @root_validator(pre=False, skip_on_failure=True)
     def validate_prompt(cls, values: dict) -> dict:
         prompt: BasePromptTemplate = values["prompt"]
         if "agent_scratchpad" not in prompt.input_variables:
@@ -131,6 +132,7 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
 
     @property
     def functions(self) -> List[dict]:
+        """Get the functions for the agent."""
         enum_vals = [t.name for t in self.tools]
         tool_selection = {
             # OpenAI functions returns a single tool invocation
@@ -198,7 +200,9 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
         """Given input, decided what to do.
 
         Args:
-            intermediate_steps: Steps the LLM has taken to date, along with observations
+            intermediate_steps: Steps the LLM has taken to date,
+                along with observations.
+            callbacks: Callbacks to use. Default is None.
             **kwargs: User inputs.
 
         Returns:
@@ -223,11 +227,12 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
         callbacks: Callbacks = None,
         **kwargs: Any,
     ) -> Union[List[AgentAction], AgentFinish]:
-        """Given input, decided what to do.
+        """Async given input, decided what to do.
 
         Args:
             intermediate_steps: Steps the LLM has taken to date,
-                along with observations
+                along with observations.
+            callbacks: Callbacks to use. Default is None.
             **kwargs: User inputs.
 
         Returns:
@@ -260,7 +265,7 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
             system_message: Message to use as the system message that will be the
                 first in the prompt.
             extra_prompt_messages: Prompt messages that will be placed between the
-                system message and the new human input.
+                system message and the new human input. Default is None.
 
         Returns:
             A prompt template to pass into this agent.
@@ -293,7 +298,17 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
         ),
         **kwargs: Any,
     ) -> BaseMultiActionAgent:
-        """Construct an agent from an LLM and tools."""
+        """Construct an agent from an LLM and tools.
+
+        Args:
+            llm: The language model to use.
+            tools: A list of tools to use.
+            callback_manager: The callback manager to use. Default is None.
+            extra_prompt_messages: Extra prompt messages to use. Default is None.
+            system_message: The system message to use.
+                Default is a default system message.
+            **kwargs: Additional arguments.
+        """
         prompt = cls.create_prompt(
             extra_prompt_messages=extra_prompt_messages,
             system_message=system_message,

langchain/agents/openai_tools/base.py

@@ -28,6 +28,9 @@ def create_openai_tools_agent(
         variables as the prompt passed in does. It returns as output either an
         AgentAction or AgentFinish.
 
+    Raises:
+        ValueError: If the prompt is missing required variables.
+
     Example:
 
         .. code-block:: python

langchain/agents/output_parsers/__init__.py

@@ -9,6 +9,7 @@ This contains a `return_values` dictionary. This usually contains a
 single `output` key, but can be extended to contain more.
 This also contains a `log` variable (which contains a log of the agent's thinking).
 """
+
 from langchain.agents.output_parsers.json import JSONAgentOutputParser
 from langchain.agents.output_parsers.openai_functions import (
     OpenAIFunctionsAgentOutputParser,

langchain/agents/react/base.py

@@ -1,4 +1,5 @@
 """Chain that implements the ReAct paper from https://arxiv.org/pdf/2210.03629.pdf."""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any, List, Optional, Sequence

langchain/agents/self_ask_with_search/base.py

@@ -1,4 +1,5 @@
 """Chain that does self-ask with search."""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any, Sequence, Union

langchain/agents/structured_chat/output_parser.py

@@ -69,9 +69,9 @@ class StructuredChatOutputParserWithRetries(AgentOutputParser):
     def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
         try:
             if self.output_fixing_parser is not None:
-                parsed_obj: Union[
-                    AgentAction, AgentFinish
-                ] = self.output_fixing_parser.parse(text)
+                parsed_obj: Union[AgentAction, AgentFinish] = (
+                    self.output_fixing_parser.parse(text)
+                )
             else:
                 parsed_obj = self.base_parser.parse(text)
             return parsed_obj

langchain/agents/tool_calling_agent/base.py

@@ -1,6 +1,8 @@
-from typing import Sequence
+from typing import Callable, List, Sequence, Tuple
 
+from langchain_core.agents import AgentAction
 from langchain_core.language_models import BaseLanguageModel
+from langchain_core.messages import BaseMessage
 from langchain_core.prompts.chat import ChatPromptTemplate
 from langchain_core.runnables import Runnable, RunnablePassthrough
 from langchain_core.tools import BaseTool
@@ -10,9 +12,15 @@ from langchain.agents.format_scratchpad.tools import (
 )
 from langchain.agents.output_parsers.tools import ToolsAgentOutputParser
 
+MessageFormatter = Callable[[Sequence[Tuple[AgentAction, str]]], List[BaseMessage]]
+
 
 def create_tool_calling_agent(
-    llm: BaseLanguageModel, tools: Sequence[BaseTool], prompt: ChatPromptTemplate
+    llm: BaseLanguageModel,
+    tools: Sequence[BaseTool],
+    prompt: ChatPromptTemplate,
+    *,
+    message_formatter: MessageFormatter = format_to_tool_messages,
 ) -> Runnable:
     """Create an agent that uses tools.
 
@@ -21,6 +29,8 @@ def create_tool_calling_agent(
         tools: Tools this agent has access to.
         prompt: The prompt to use. See Prompt section below for more on the expected
             input variables.
+        message_formatter: Formatter function to convert (AgentAction, tool output)
+            tuples into FunctionMessages.
 
     Returns:
         A Runnable sequence representing an agent. It takes as input all the same input
@@ -89,7 +99,7 @@ def create_tool_calling_agent(
 
     agent = (
         RunnablePassthrough.assign(
-            agent_scratchpad=lambda x: format_to_tool_messages(x["intermediate_steps"])
+            agent_scratchpad=lambda x: message_formatter(x["intermediate_steps"])
         )
         | prompt
         | llm_with_tools

langchain/agents/tools.py

@@ -1,4 +1,5 @@
 """Interface for tools."""
+
 from typing import List, Optional
 
 from langchain_core.callbacks import (
@@ -12,7 +13,9 @@ class InvalidTool(BaseTool):
     """Tool that is run when invalid tool name is encountered by agent."""
 
     name: str = "invalid_tool"
+    """Name of the tool."""
     description: str = "Called when tool name is invalid. Suggests valid tool names."
+    """Description of the tool."""
 
     def _run(
         self,

langchain/agents/utils.py

@@ -4,7 +4,15 @@ from langchain_core.tools import BaseTool
 
 
 def validate_tools_single_input(class_name: str, tools: Sequence[BaseTool]) -> None:
-    """Validate tools for single input."""
+    """Validate tools for single input.
+
+    Args:
+        class_name: Name of the class.
+        tools: List of tools to validate.
+
+    Raises:
+        ValueError: If a multi-input tool is found in tools.
+    """
     for tool in tools:
         if not tool.is_single_input:
             raise ValueError(