OpenAI integrations | LangChain 한국어

LangChain integrates with OpenAI and Azure OpenAI through the @langchain/openai package.

OpenAI is American artificial intelligence (AI) research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership. OpenAI conducts AI research with the declared intention of promoting and developing a friendly AI. OpenAI systems run on an Azure-based supercomputing platform from Microsoft.

The OpenAI API is powered by a diverse set of models with different capabilities and price points.
ChatGPT is the Artificial Intelligence (AI) chatbot developed by OpenAI.

Installation and setup

Get an OpenAI api key and set it as an environment variable (OPENAI_API_KEY)

Chat model

See a usage example.

import { ChatOpenAI } from "@langchain/openai";

LLM

See a usage example.

Tip

See this section for general instructions on installing LangChain packages.

npm install @langchain/openai @langchain/core

import { OpenAI } from "@langchain/openai";

Text embedding model

See a usage example

import { OpenAIEmbeddings } from "@langchain/openai";

Chain

import { OpenAIModerationChain } from "@langchain/classic/chains";

Middleware

Middleware specifically designed for OpenAI models. Learn more about middleware.

Middleware	Description
Content moderation	Moderate agent traffic using OpenAI's moderation endpoint

Content moderation

Moderate agent traffic (user input, model output, and tool results) using OpenAI's moderation endpoint to detect and handle unsafe content. Content moderation is useful for the following:

Applications requiring content safety and compliance
Filtering harmful, hateful, or inappropriate content
Customer-facing agents that need safety guardrails
Meeting platform moderation requirements

Info

Learn more about OpenAI's moderation models and categories.

API reference: openAIModerationMiddleware

import { createAgent, openAIModerationMiddleware } from "langchain";

const agent = createAgent({
  model: "openai:gpt-5.5",
  tools: [searchTool, databaseTool],
  middleware: [
    openAIModerationMiddleware({
      model: "openai:gpt-5.5",
      moderationModel: "omni-moderation-latest",
      checkInput: true,
      checkOutput: true,
      exitBehavior: "end",
    }),
  ],
});

The middleware integrates OpenAI's moderation endpoint to check content at different stages:

Moderation stages:

checkInput - User messages before model call
checkOutput - AI messages after model call
checkToolResults - Tool outputs before model call

Exit behaviors:

'end' (default) - Stop execution with violation message
'error' - Throw exception for application handling
'replace' - Replace flagged content and continue

import { createAgent, openAIModerationMiddleware } from "langchain";

// Basic moderation
const agent = createAgent({
  model: "openai:gpt-5.5",
  tools: [searchTool, customerDataTool],
  middleware: [
    openAIModerationMiddleware({
      model: "openai:gpt-5.5",
      moderationModel: "omni-moderation-latest",
      checkInput: true,
      checkOutput: true,
    }),
  ],
});

// Strict moderation with custom message
const agentStrict = createAgent({
  model: "openai:gpt-5.5",
  tools: [searchTool, customerDataTool],
  middleware: [
    openAIModerationMiddleware({
      model: "openai:gpt-5.5",
      moderationModel: "omni-moderation-latest",
      checkInput: true,
      checkOutput: true,
      checkToolResults: true,
      exitBehavior: "error",
      violationMessage:
        "Content policy violation detected: {categories}. " +
        "Please rephrase your request.",
    }),
  ],
});

// Moderation with replacement behavior
const agentReplace = createAgent({
  model: "openai:gpt-5.5",
  tools: [searchTool],
  middleware: [
    openAIModerationMiddleware({
      model: "openai:gpt-5.5",
      checkInput: true,
      exitBehavior: "replace",
      violationMessage: "[Content removed due to safety policies]",
    }),
  ],
});

Configuration options

Full example

The middleware integrates OpenAI's moderation endpoint to check content at different stages:

Moderation stages:

checkInput - User messages before model call
checkOutput - AI messages after model call
checkToolResults - Tool outputs before model call

Exit behaviors:

'end' (default) - Stop execution with violation message
'error' - Throw exception for application handling
'replace' - Replace flagged content and continue

import { createAgent, openAIModerationMiddleware } from "langchain";

// Basic moderation
const agent = createAgent({
  model: "openai:gpt-5.5",
  tools: [searchTool, customerDataTool],
  middleware: [
    openAIModerationMiddleware({
      model: "openai:gpt-5.5",
      moderationModel: "omni-moderation-latest",
      checkInput: true,
      checkOutput: true,
    }),
  ],
});

// Strict moderation with custom message
const agentStrict = createAgent({
  model: "openai:gpt-5.5",
  tools: [searchTool, customerDataTool],
  middleware: [
    openAIModerationMiddleware({
      model: "openai:gpt-5.5",
      moderationModel: "omni-moderation-latest",
      checkInput: true,
      checkOutput: true,
      checkToolResults: true,
      exitBehavior: "error",
      violationMessage:
        "Content policy violation detected: {categories}. " +
        "Please rephrase your request.",
    }),
  ],
});

// Moderation with replacement behavior
const agentReplace = createAgent({
  model: "openai:gpt-5.5",
  tools: [searchTool],
  middleware: [
    openAIModerationMiddleware({
      model: "openai:gpt-5.5",
      checkInput: true,
      exitBehavior: "replace",
      violationMessage: "[Content removed due to safety policies]",
    }),
  ],
});