@typia/langchain

LangChain.js integration for typia.

Converts typia controllers to LangChain DynamicStructuredTool[] with automatic validation.

Setup

npm install @typia/langchain @langchain/core typia
npm install -D ttsc typescript@rc

Usage

From TypeScript class

import { ChainValues, Runnable } from "@langchain/core";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { ChatOpenAI } from "@langchain/openai";
import { toLangChainTools } from "@typia/langchain";
import { AgentExecutor, createToolCallingAgent } from "langchain/agents";
import typia from "typia";

const tools: DynamicStructuredTool[] = toLangChainTools(
  typia.llm.controller<Calculator>("Calculator", new Calculator()),
);

const agent: Runnable = createToolCallingAgent({
  llm: new ChatOpenAI({ model: "gpt-4o" }),
  tools,
  prompt: ChatPromptTemplate.fromMessages([
    ["system", "You are a helpful assistant."],
    ["human", "{input}"],
    ["placeholder", "{agent_scratchpad}"],
  ]),
});
const executor: AgentExecutor = new AgentExecutor({ agent, tools });
const result: ChainValues = await executor.invoke({ input: "What is 10 + 5?" });

From OpenAPI document

import { DynamicStructuredTool } from "@langchain/core/tools";
import { toLangChainTools } from "@typia/langchain";
import { HttpLlm } from "@typia/utils";

const tools: DynamicStructuredTool[] = toLangChainTools(
  HttpLlm.controller({
    name: "petStore",
    document: yourOpenApiDocument,
    connection: { host: "https://api.example.com" },
  }),
);

Structured Output

Use typia.llm.parameters<T>() with LangChain's withStructuredOutput() to generate structured output with validation:

import { ChatOpenAI } from "@langchain/openai";
import { dedent, LlmJson } from "@typia/utils";
import typia, { tags } from "typia";

interface IMember {
  email: string & tags.Format<"email">;
  name: string;
  age: number & tags.Minimum<0> & tags.Maximum<100>;
  hobbies: string[];
  joined_at: string & tags.Format<"date">;
}

const model = new ChatOpenAI({ model: "gpt-4o" }).withStructuredOutput(
  typia.llm.parameters<IMember>(),
);

const member: IMember = await model.invoke(dedent`
  I am a new member of the community.

  My name is John Doe, and I am 25 years old.
  I like playing basketball and reading books,
  and joined to this community at 2022-01-01.
`);

// Validate the result
const result = typia.validate<IMember>(member);
if (!result.success) {
  console.error(LlmJson.stringify(result));
}

Features

• No manual schema definition — generates everything from TypeScript types or OpenAPI
• Automatic argument validation with LLM-friendly error feedback
• Runtime tool errors are returned as { success: false, error } for model recovery
• Supports both class-based (typia.llm.controller) and HTTP-based (HttpLlm.controller) controllers