diff --git a/v4/examples/langchain-langsmith.mdx b/v4/examples/langchain-langsmith.mdx index d0531fc..452bb8c 100644 --- a/v4/examples/langchain-langsmith.mdx +++ b/v4/examples/langchain-langsmith.mdx @@ -15,7 +15,7 @@ A tool refers to any framework, utility, or system with defined functionality fo Key LangChain concepts: -1. `ChatModel.bind_tools()`: Attaches tool definitions to model calls. While providers have different tool definition formats, LangChain provides a standard interface for versatility. Accepts tool definitions as dictionaries, Pydantic classes, LangChain tools, or functions, telling the LLM how to use each tool. +`ChatModel.bind_tools()`: Attaches tool definitions to model calls. While providers have different tool definition formats, LangChain provides a standard interface for versatility. Accepts tool definitions as dictionaries, Pydantic classes, LangChain tools, or functions, telling the LLM how to use each tool. ```python @tool @@ -24,7 +24,7 @@ def exponentiate(x: float, y: float) -> float: return x**y ``` -2. `AIMessage.tool_calls`: An attribute on AIMessage that provides easy access to model-initiated tool calls, specifying invocations in the bind_tools format: +`AIMessage.tool_calls`: An attribute on AIMessage that provides easy access to model-initiated tool calls, specifying invocations in the bind_tools format: ```python # -> AIMessage( @@ -36,7 +36,7 @@ def exponentiate(x: float, y: float) -> float: # ) ``` -3. `create_tool_calling_agent()`: Unifies the above concepts to work across different provider formats, enabling easy model switching. +`create_tool_calling_agent()`: Unifies the above concepts to work across different provider formats, enabling easy model switching. ```python agent = create_tool_calling_agent(llm, tools, prompt)