From db03dccb2b6f71ef5af35978108067b8fe9a0182 Mon Sep 17 00:00:00 2001 From: Eugene Yurtsev Date: Tue, 24 Jun 2025 09:56:19 -0400 Subject: [PATCH] x --- docs/docs/concepts/tools.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/docs/concepts/tools.md b/docs/docs/concepts/tools.md index ef463536b..c12509e75 100644 --- a/docs/docs/concepts/tools.md +++ b/docs/docs/concepts/tools.md @@ -12,13 +12,13 @@ Tool calling is typically **conditional**. Based on the user input and available ```python llm_with_tools.invoke("What is 2 multiplied by 3?") -# → AIMessage(tool_calls=[{'name': 'multiply', 'args': {'a': 2, 'b': 3}, ...}]) +# -> AIMessage(tool_calls=[{'name': 'multiply', 'args': {'a': 2, 'b': 3}, ...}]) ``` If the input is unrelated to any tool, the model returns only a natural language message: ```python -llm_with_tools.invoke("Hello world!") # → AIMessage(content="Hello!") +llm_with_tools.invoke("Hello world!") # -> AIMessage(content="Hello!") ``` Importantly, the model does not execute the tool—it only generates a request. A separate executor (such as a runtime or agent) is responsible for handling the tool call and returning the result.