Function●Since v1.2

llmToolSelectorMiddleware

Middleware for selecting tools using an LLM-based strategy.

When an agent has many tools available, this middleware filters them down to only the most relevant ones for the user's query. This reduces token usage and helps the main model focus on the right tools.

llmToolSelectorMiddleware(
  options: __type
): AgentMiddleware<undefined, ZodObject<__type, "strip", ZodTypeAny, __type, __type>, __type, readonly ClientTool | ServerTool[]>

Parameters

Name	Type	Description
`options`*	`__type`	Configuration options for the middleware

Example 1

Limit to 3 tools:

import { llmToolSelectorMiddleware } from "langchain/agents/middleware";

const middleware = llmToolSelectorMiddleware({ maxTools: 3 });

const agent = createAgent({
  model: "openai:gpt-4o",
  tools: [tool1, tool2, tool3, tool4, tool5],
  middleware: [middleware],
});

Example 2

Use a smaller model for selection:

const middleware = llmToolSelectorMiddleware({
  model: "openai:gpt-4o-mini",
  maxTools: 2
});

View source on GitHub

llmToolSelectorMiddleware

Parameters

Example 1

Example 2

LangChain Assistant

Menu

llmToolSelectorMiddleware

Parameters

Example 1

Example 2

llmToolSelectorMiddleware

Used in Docs

Parameters

Example 1

Example 2

Menu

llmToolSelectorMiddleware

Used in Docs

Parameters

Example 1

Example 2