wehub-resource-sync
54 lines
3.1 KiB
Plaintext
54 lines
3.1 KiB
Plaintext
---
|
|
title: "Next.js Batch LLM Evaluator"
|
|
sidebarTitle: "Batch LLM Evaluator"
|
|
description: "This example Next.js project evaluates multiple LLM models using the Vercel AI SDK and streams updates to the frontend using Trigger.dev Realtime."
|
|
---
|
|
|
|
import RealtimeLearnMore from "/snippets/realtime-learn-more.mdx";
|
|
|
|
## Overview
|
|
|
|
This demo is a full stack example that uses the following:
|
|
|
|
- A [Next.js](https://nextjs.org/) app with [Prisma](https://www.prisma.io/) for the database.
|
|
- Trigger.dev [Realtime](https://trigger.dev/launchweek/0/realtime) to stream updates to the frontend.
|
|
- Work with multiple LLM models using the Vercel [AI SDK](https://sdk.vercel.ai/docs/introduction). (OpenAI, Anthropic, XAI)
|
|
- Distribute tasks across multiple tasks using the new [`batch.triggerByTaskAndWait`](https://trigger.dev/docs/triggering#batch-triggerbytaskandwait) method.
|
|
|
|
## GitHub repo
|
|
|
|
<Card
|
|
title="View the Batch LLM Evaluator repo"
|
|
icon="GitHub"
|
|
href="https://github.com/triggerdotdev/examples/tree/main/batch-llm-evaluator"
|
|
>
|
|
Click here to view the full code for this project in our examples repository on GitHub. You can
|
|
fork it and use it as a starting point for your own project.
|
|
</Card>
|
|
|
|
## Video
|
|
|
|
<video
|
|
controls
|
|
className="w-full aspect-video"
|
|
src="https://content.trigger.dev/batch-llm-evaluator.mp4"
|
|
></video>
|
|
|
|
## Relevant code
|
|
|
|
- View the Trigger.dev task code in the [src/trigger/batch.ts](https://github.com/triggerdotdev/examples/blob/main/batch-llm-evaluator/src/trigger/batch.ts) file.
|
|
- The `evaluateModels` task uses the `batch.triggerByTaskAndWait` method to distribute the task to the different LLM models.
|
|
- It then passes the results through to a `summarizeEvals` task that calculates some dummy "tags" for each LLM response.
|
|
- We use a [useRealtimeRunsWithTag](/realtime/react-hooks/subscribe#userealtimerunswithtag) hook to subscribe to the different evaluation tasks runs in the [src/components/llm-evaluator.tsx](https://github.com/triggerdotdev/examples/blob/main/batch-llm-evaluator/src/components/llm-evaluator.tsx) file.
|
|
- We then pass the relevant run down into three different components for the different models:
|
|
- The `AnthropicEval` component: [src/components/evals/Anthropic.tsx](https://github.com/triggerdotdev/examples/blob/main/batch-llm-evaluator/src/components/evals/Anthropic.tsx)
|
|
- The `XAIEval` component: [src/components/evals/XAI.tsx](https://github.com/triggerdotdev/examples/blob/main/batch-llm-evaluator/src/components/evals/XAI.tsx)
|
|
- The `OpenAIEval` component: [src/components/evals/OpenAI.tsx](https://github.com/triggerdotdev/examples/blob/main/batch-llm-evaluator/src/components/evals/OpenAI.tsx)
|
|
- Each of these components then uses [useRealtimeRunWithStreams](/realtime/react-hooks/streams#userealtimerunwithstreams) to subscribe to the different LLM responses.
|
|
|
|
<Note>
|
|
This example uses the older `useRealtimeRunWithStreams` hook. For new projects, consider using the new [`useRealtimeStream`](/realtime/react-hooks/streams#userealtimestream-recommended) hook (SDK 4.1.0+) for a simpler API and better type safety with defined streams.
|
|
</Note>
|
|
|
|
<RealtimeLearnMore />
|