`LanguageModelV1Middleware`

Language model middleware is an experimental feature.

Language model middleware provides a way to enhance the behavior of language models by intercepting and modifying the calls to the language model. It can be used to add features like guardrails, RAG, caching, and logging in a language model agnostic way.

See Language Model Middleware for more information.

Import

import { LanguageModelV1Middleware } from "ai"

API Signature

transformParams:

({ type: "generate" | "stream", params: LanguageModelV1CallOptions }) => Promise<LanguageModelV1CallOptions>

wrapGenerate:

({ doGenerate: DoGenerateFunction, params: LanguageModelV1CallOptions, model: LanguageModelV1 }) => Promise<DoGenerateResult>

wrapStream:

({ doStream: DoStreamFunction, params: LanguageModelV1CallOptions, model: LanguageModelV1 }) => Promise<DoStreamResult>