@langinsight/langchain

LangInsight callback handler for LangChain. Sends input/output traces to LangInsight in parallel on each LLM end and supports feedback (thumbs up/down) via score().

Usage

Basic usage

import { ChatOllama } from "@langchain/ollama";
import { LangInsight } from "@langinsight/langchain";

const model = new ChatOllama({ model: "gpt-oss:20b" });

const { LANGINSIGHT_ENDPOINT, LANGINSIGHT_API_KEY } = process.env;

await model.invoke("hi!", {
  callbacks: [
    new LangInsight.CallbackHandler({
      apiKey: LANGINSIGHT_API_KEY,
      endpoint: LANGINSIGHT_ENDPOINT,
      metadata: { userId: "admin", sessionId: "admin" },
      onSuccess: (input, output) => console.log("Trace sent:", output.id),
      onFailure: (err) => console.error("Trace failed:", err),
    }),
  ],
});

With LangGraph

import { Annotation, END, START, StateGraph } from "@langchain/langgraph";
import { ChatOllama } from "@langchain/ollama";
import { LangInsight } from "@langinsight/langchain";

const model = new ChatOllama({ model: "gpt-oss:20b" });

const callbacks = [
  new LangInsight.CallbackHandler({
    apiKey: process.env.LANGINSIGHT_API_KEY,
    endpoint: process.env.LANGINSIGHT_ENDPOINT,
    metadata: { userId: "admin", sessionId: "langgraph-example" },
  }),
];

const GraphState = Annotation.Root({
  input: Annotation<string>,
  response: Annotation<string>,
});

async function processInput(state: typeof GraphState.State) {
  const response = await model.invoke(state.input, { callbacks });
  return {
    response: response.content as string,
  };
}

const workflow = new StateGraph(GraphState)
  .addNode("process", processInput)
  .addEdge(START, "process")
  .addEdge("process", END);

const app = workflow.compile();

const result = await app.invoke(
  { input: "What is LangGraph?" },
  { callbacks }
);

Feedback (score)

Trace ID は handler.result で取得し、その output.id を score() に渡してフィードバックを送信する。DB 永続化などは onSuccess コールバックでも行える。

const handler = new LangInsight.CallbackHandler({
  apiKey: LANGINSIGHT_API_KEY,
  endpoint: LANGINSIGHT_ENDPOINT,
  metadata: { userId: "admin", sessionId: "admin" },
});

await model.invoke("hi!", { callbacks: [handler] });

const { input, output } = await handler.result;
await handler.score({ traceId: output.id, value: 1 });  // 👍
await handler.score({ traceId: output.id, value: -1 }); // 👎

Options

| Option | Type | Required | Description | | ----------- | -------------------------- | -------- | ----------------------------------------------------------------------- | | apiKey | string | Yes | LangInsight API key | | endpoint | string | Yes | LangInsight API endpoint (e.g. https://api.langinsight.example.com) | | metadata | object | Yes | Metadata attached to traces | | metadata.userId | string | Yes | User ID | | metadata.sessionId| string | Yes | Session ID (e.g. conversation id) | | metadata.modelName| string | No | Model name (defaults to run metadata when not set) | | metadata.* | any | No | Additional key-value pairs | | onSuccess | (input: Trace, output: Trace) => void | No | Callback invoked with both input and output traces when trace submission succeeds. Use output.id to get traceId and persist to DB. | | onFailure | (error: Error) => void | No | Callback invoked with the error when trace submission fails |

API

• score({ traceId, value }) — Submits feedback (1 = thumbs up, -1 = thumbs down) for the given trace. Use (await handler.result).output.id as traceId.
• result — A promise that resolves with { input: Trace, output: Trace } when traces are sent successfully.