chore(langchain): enable ruff docstring-code-format in langchain (#32858)

Author: cbornet

libs/langchain/langchain/agents/agent_toolkits/vectorstore/base.py

@@ -60,7 +60,8 @@ def create_vectorstore_agent(
 
             vector_store = InMemoryVectorStore.from_texts(
                 [
-                    "Dogs are great companions, known for their loyalty and friendliness.",
+                    "Dogs are great companions, "
+                    "known for their loyalty and friendliness.",
                     "Cats are independent pets that often enjoy their own space.",
                 ],
                 OpenAIEmbeddings(),
@@ -81,18 +82,20 @@ def create_vectorstore_agent(
                 step["messages"][-1].pretty_print()
 
     Args:
-        llm (BaseLanguageModel): LLM that will be used by the agent
-        toolkit (VectorStoreToolkit): Set of tools for the agent
-        callback_manager (Optional[BaseCallbackManager], optional): Object to handle the callback [ Defaults to None. ]
-        prefix (str, optional): The prefix prompt for the agent. If not provided uses default PREFIX.
-        verbose (bool, optional): If you want to see the content of the scratchpad. [ Defaults to False ]
-        agent_executor_kwargs (Optional[Dict[str, Any]], optional): If there is any other parameter you want to send to the agent. [ Defaults to None ]
+        llm: LLM that will be used by the agent
+        toolkit: Set of tools for the agent
+        callback_manager: Object to handle the callback [ Defaults to None. ]
+        prefix: The prefix prompt for the agent. If not provided uses default PREFIX.
+        verbose: If you want to see the content of the scratchpad. [ Defaults to False ]
+        agent_executor_kwargs: If there is any other parameter you want to send to the
+            agent. [ Defaults to None ]
         kwargs: Additional named parameters to pass to the ZeroShotAgent.
 
     Returns:
-        AgentExecutor: Returns a callable AgentExecutor object. Either you can call it or use run method with the query to get the response
+        Returns a callable AgentExecutor object.
+        Either you can call it or use run method with the query to get the response.
 
-    """  # noqa: E501
+    """
     tools = toolkit.get_tools()
     prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
     llm_chain = LLMChain(
@@ -155,7 +158,8 @@ def create_vectorstore_router_agent(
 
             pet_vector_store = InMemoryVectorStore.from_texts(
                 [
-                    "Dogs are great companions, known for their loyalty and friendliness.",
+                    "Dogs are great companions, "
+                    "known for their loyalty and friendliness.",
                     "Cats are independent pets that often enjoy their own space.",
                 ],
                 OpenAIEmbeddings(),
@@ -179,7 +183,7 @@ def create_vectorstore_router_agent(
                     food_vector_store.as_retriever(),
                     "food_information_retriever",
                     "Fetches information about food.",
-                )
+                ),
             ]
 
             agent = create_react_agent(llm, tools)
@@ -191,18 +195,22 @@ def create_vectorstore_router_agent(
                 step["messages"][-1].pretty_print()
 
     Args:
-        llm (BaseLanguageModel): LLM that will be used by the agent
-        toolkit (VectorStoreRouterToolkit): Set of tools for the agent which have routing capability with multiple vector stores
-        callback_manager (Optional[BaseCallbackManager], optional): Object to handle the callback [ Defaults to None. ]
-        prefix (str, optional): The prefix prompt for the router agent. If not provided uses default ROUTER_PREFIX.
-        verbose (bool, optional): If you want to see the content of the scratchpad. [ Defaults to False ]
-        agent_executor_kwargs (Optional[Dict[str, Any]], optional): If there is any other parameter you want to send to the agent. [ Defaults to None ]
+        llm: LLM that will be used by the agent
+        toolkit: Set of tools for the agent which have routing capability with multiple
+            vector stores
+        callback_manager: Object to handle the callback [ Defaults to None. ]
+        prefix: The prefix prompt for the router agent.
+            If not provided uses default ROUTER_PREFIX.
+        verbose: If you want to see the content of the scratchpad. [ Defaults to False ]
+        agent_executor_kwargs: If there is any other parameter you want to send to the
+            agent. [ Defaults to None ]
         kwargs: Additional named parameters to pass to the ZeroShotAgent.
 
     Returns:
-        AgentExecutor: Returns a callable AgentExecutor object. Either you can call it or use run method with the query to get the response.
+        Returns a callable AgentExecutor object.
+        Either you can call it or use run method with the query to get the response.
 
-    """  # noqa: E501
+    """
     tools = toolkit.get_tools()
     prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
     llm_chain = LLMChain(

libs/langchain/langchain/agents/chat/base.py

@@ -108,7 +108,12 @@ def create_prompt(
         tool_strings = "\n".join([f"{tool.name}: {tool.description}" for tool in tools])
         tool_names = ", ".join([tool.name for tool in tools])
         format_instructions = format_instructions.format(tool_names=tool_names)
-        template = f"{system_message_prefix}\n\n{tool_strings}\n\n{format_instructions}\n\n{system_message_suffix}"  # noqa: E501
+        template = (
+            f"{system_message_prefix}\n\n"
+            f"{tool_strings}\n\n"
+            f"{format_instructions}\n\n"
+            f"{system_message_suffix}"
+        )
         messages = [
             SystemMessagePromptTemplate.from_template(template),
             HumanMessagePromptTemplate.from_template(human_message),

libs/langchain/langchain/agents/json_chat/base.py

@@ -35,8 +35,8 @@ def create_json_chat_agent(
             does not support stop sequences.
         tools_renderer: This controls how the tools are converted into a string and
             then passed into the LLM. Default is `render_text_description`.
-        template_tool_response: Template prompt that uses the tool response (observation)
-            to make the LLM generate the next action to take.
+        template_tool_response: Template prompt that uses the tool response
+            (observation) to make the LLM generate the next action to take.
             Default is TEMPLATE_TOOL_RESPONSE.
 
     Returns:
@@ -68,6 +68,7 @@ def create_json_chat_agent(
 
             # Using with chat history
             from langchain_core.messages import AIMessage, HumanMessage
+
             agent_executor.invoke(
                 {
                     "input": "what's my name?",
@@ -83,7 +84,8 @@ def create_json_chat_agent(
         The prompt must have input keys:
             * `tools`: contains descriptions and arguments for each tool.
             * `tool_names`: contains all tool names.
-            * `agent_scratchpad`: must be a MessagesPlaceholder. Contains previous agent actions and tool outputs as messages.
+            * `agent_scratchpad`: must be a MessagesPlaceholder. Contains previous
+              agent actions and tool outputs as messages.
 
         Here's an example:
 

libs/langchain/langchain/agents/openai_assistant/base.py

@@ -149,11 +149,14 @@ class OpenAIAssistantRunnable(RunnableSerializable[dict, OutputType]):
 
             interpreter_assistant = OpenAIAssistantRunnable.create_assistant(
                 name="langchain assistant",
-                instructions="You are a personal math tutor. Write and run code to answer math questions.",
+                instructions="You are a personal math tutor. "
+                "Write and run code to answer math questions.",
                 tools=[{"type": "code_interpreter"}],
-                model="gpt-4-1106-preview"
+                model="gpt-4-1106-preview",
+            )
+            output = interpreter_assistant.invoke(
+                {"content": "What's 10 - 4 raised to the 2.7"}
             )
-            output = interpreter_assistant.invoke({"content": "What's 10 - 4 raised to the 2.7"})
 
     Example using custom tools and AgentExecutor:
         .. code-block:: python
@@ -166,10 +169,11 @@ class OpenAIAssistantRunnable(RunnableSerializable[dict, OutputType]):
             tools = [E2BDataAnalysisTool(api_key="...")]
             agent = OpenAIAssistantRunnable.create_assistant(
                 name="langchain assistant e2b tool",
-                instructions="You are a personal math tutor. Write and run code to answer math questions.",
+                instructions="You are a personal math tutor. "
+                "Write and run code to answer math questions.",
                 tools=tools,
                 model="gpt-4-1106-preview",
-                as_agent=True
+                as_agent=True,
             )
 
             agent_executor = AgentExecutor(agent=agent, tools=tools)
@@ -188,34 +192,45 @@ class OpenAIAssistantRunnable(RunnableSerializable[dict, OutputType]):
             tools = [E2BDataAnalysisTool(api_key="...")]
             agent = OpenAIAssistantRunnable.create_assistant(
                 name="langchain assistant e2b tool",
-                instructions="You are a personal math tutor. Write and run code to answer math questions.",
+                instructions="You are a personal math tutor. "
+                "Write and run code to answer math questions.",
                 tools=tools,
                 model="gpt-4-1106-preview",
-                as_agent=True
+                as_agent=True,
             )
 
+
             def execute_agent(agent, tools, input):
                 tool_map = {tool.name: tool for tool in tools}
                 response = agent.invoke(input)
                 while not isinstance(response, AgentFinish):
                     tool_outputs = []
                     for action in response:
                         tool_output = tool_map[action.tool].invoke(action.tool_input)
-                        tool_outputs.append({"output": tool_output, "tool_call_id": action.tool_call_id})
+                        tool_outputs.append(
+                            {"output": tool_output, "tool_call_id": action.tool_call_id}
+                        )
                     response = agent.invoke(
                         {
                             "tool_outputs": tool_outputs,
                             "run_id": action.run_id,
-                            "thread_id": action.thread_id
+                            "thread_id": action.thread_id,
                         }
                     )
 
                 return response
 
-            response = execute_agent(agent, tools, {"content": "What's 10 - 4 raised to the 2.7"})
-            next_response = execute_agent(agent, tools, {"content": "now add 17.241", "thread_id": response.thread_id})
 
-    """  # noqa: E501
+            response = execute_agent(
+                agent, tools, {"content": "What's 10 - 4 raised to the 2.7"}
+            )
+            next_response = execute_agent(
+                agent,
+                tools,
+                {"content": "now add 17.241", "thread_id": response.thread_id},
+            )
+
+    """
 
     client: Any = Field(default_factory=_get_openai_client)
     """OpenAI or AzureOpenAI client."""

libs/langchain/langchain/agents/openai_functions_agent/base.py

@@ -327,6 +327,7 @@ def create_openai_functions_agent(
 
             # Using with chat history
             from langchain_core.messages import AIMessage, HumanMessage
+
             agent_executor.invoke(
                 {
                     "input": "what's my name?",

libs/langchain/langchain/agents/openai_tools/base.py

@@ -55,6 +55,7 @@ def create_openai_tools_agent(
 
             # Using with chat history
             from langchain_core.messages import AIMessage, HumanMessage
+
             agent_executor.invoke(
                 {
                     "input": "what's my name?",

libs/langchain/langchain/agents/output_parsers/json.py

@@ -23,21 +23,15 @@ class JSONAgentOutputParser(AgentOutputParser):
     being returned.
 
     ```
-    {
-      "action": "search",
-      "action_input": "2+2"
-    }
+    {"action": "search", "action_input": "2+2"}
     ```
 
     If the output signals that a final answer should be given,
     should be in the below format. This will result in an AgentFinish
     being returned.
 
     ```
-    {
-      "action": "Final Answer",
-      "action_input": "4"
-    }
+    {"action": "Final Answer", "action_input": "4"}
     ```
     """
 

libs/langchain/langchain/agents/react/agent.py

@@ -29,9 +29,12 @@ def create_react_agent(
     (https://arxiv.org/abs/2210.03629)
 
     .. warning::
-       This implementation is based on the foundational ReAct paper but is older and not well-suited for production applications.
-       For a more robust and feature-rich implementation, we recommend using the `create_react_agent` function from the LangGraph library.
-       See the [reference doc](https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent)
+       This implementation is based on the foundational ReAct paper but is older and
+       not well-suited for production applications.
+       For a more robust and feature-rich implementation, we recommend using the
+       `create_react_agent` function from the LangGraph library.
+       See the
+       `reference doc <https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent>`__
        for more information.
 
     Args:
@@ -73,6 +76,7 @@ def create_react_agent(
 
             # Use with chat history
             from langchain_core.messages import AIMessage, HumanMessage
+
             agent_executor.invoke(
                 {
                     "input": "what's my name?",
@@ -87,7 +91,8 @@ def create_react_agent(
         The prompt must have input keys:
             * `tools`: contains descriptions and arguments for each tool.
             * `tool_names`: contains all tool names.
-            * `agent_scratchpad`: contains previous agent actions and tool outputs as a string.
+            * `agent_scratchpad`: contains previous agent actions and tool outputs as a
+               string.
 
         Here's an example:
 

libs/langchain/langchain/agents/self_ask_with_search/base.py

@@ -122,7 +122,8 @@ def create_self_ask_with_search_agent(
             from langchain import hub
             from langchain_community.chat_models import ChatAnthropic
             from langchain.agents import (
-                AgentExecutor, create_self_ask_with_search_agent
+                AgentExecutor,
+                create_self_ask_with_search_agent,
             )
 
             prompt = hub.pull("hwchase17/self-ask-with-search")

libs/langchain/langchain/agents/structured_chat/base.py

@@ -207,6 +207,7 @@ def create_structured_chat_agent(
 
             # Using with chat history
             from langchain_core.messages import AIMessage, HumanMessage
+
             agent_executor.invoke(
                 {
                     "input": "what's my name?",
@@ -222,7 +223,8 @@ def create_structured_chat_agent(
         The prompt must have input keys:
             * `tools`: contains descriptions and arguments for each tool.
             * `tool_names`: contains all tool names.
-            * `agent_scratchpad`: contains previous agent actions and tool outputs as a string.
+            * `agent_scratchpad`: contains previous agent actions and tool outputs as a
+              string.
 
         Here's an example: