This page contains a curated list of examples, tutorials, blogs about WebLLM usecases. Please send a pull request if you find things that belong here.

Note that all examples below run in-browser and use WebGPU as a backend.

• get-started: minimum get started example with chat completion.

  

• simple-chat-js: a mininum and complete chat bot app in vanilla JavaScript.

  

• simple-chat-ts: a mininum and complete chat bot app in TypeScript.

• get-started-web-worker: same as get-started, but using web worker.

• next-simple-chat: a mininum and complete chat bot app with Next.js.

• subgroups-usage: capability-based routing between baseline and subgroup WebGPU WASM builds.

• multi-round-chat: while APIs are functional, we internally optimize so that multi round chat usage can reuse KV cache

• text-completion: demonstrates API engine.completions.create(), which is pure text completion with no conversation, as opposed to engine.chat.completions.create()

• embeddings: demonstrates API engine.embeddings.create(), integration with EmbeddingsInterface and MemoryVectorStore of Langchain.js, and RAG with Langchain.js using WebLLM for both LLM and Embedding in a single engine

• multi-models: demonstrates loading multiple models in a single engine concurrently

These examples demonstrate various capabilities via WebLLM's OpenAI-like API.

• streaming: return output as chunks in real-time in the form of an AsyncGenerator
• json-mode: efficiently ensure output is in json format, see OpenAI Reference for more.
• json-schema: besides guaranteeing output to be in JSON, ensure output to adhere to a specific JSON schema specified the user
• seed-to-reproduce: use seeding to ensure reproducible output with fields seed.
• function-calling (WIP): function calling with fields tools and tool_choice (with preliminary support).
• vision-model: process request with image input using Vision Language Model (e.g. Phi3.5-vision)

• chrome-extension: chrome extension that does not have a persistent background
• chrome-extension-webgpu-service-worker: chrome extension using service worker, hence having a persistent background

• logit-processor: while logit_bias is supported, we additionally support stateful logit processing where users can specify their own rules. We also expose low-level API forwardTokensAndSample().
• cache-usage: demonstrates how WebLLM supports multiple cache backends. Choose between the Cache API, IndexedDB cache, OPFS, or the experimental Chrome Cross-Origin Storage extension via appConfig.cacheBackend. Also demonstrates various cache utils such as checking whether a model is cached, deleting a model's weights from cache, deleting a model library wasm from cache, etc. Note: cross-origin backend currently does not support programmatic tensor-cache deletion.
• simple-chat-upload: demonstrates how to upload local models to WebLLM instead of downloading via a URL link

• web-llm-embed: document chat prototype using react-llm with transformers.js embeddings
• DeVinci: AI chat app based on WebLLM and hosted on decentralized cloud platform