Installation

From NPM

npm install @huggingface/inferencenpm install @huggingface/hubnpm install @huggingface/mcp-client

import{InferenceClient}from"@huggingface/inference";import{createRepo,commit,deleteRepo,listFiles}from"@huggingface/hub";import{McpClient}from"@huggingface/mcp-client";importtype{RepoId}from"@huggingface/hub";

From CDN or Static hosting

<scripttype="module">import{InferenceClient}from'https://cdn.jsdelivr.net/npm/@huggingface/inference@4.4.0/+esm';import{createRepo,commit,deleteRepo,listFiles}from"https://cdn.jsdelivr.net/npm/@huggingface/hub@2.4.0/+esm";</script>

Deno

// esm.shimport{InferenceClient}from"https://esm.sh/@huggingface/inference"import{createRepo,commit,deleteRepo,listFiles}from"https://esm.sh/@huggingface/hub"// or npm:import{InferenceClient}from"npm:@huggingface/inference"import{createRepo,commit,deleteRepo,listFiles}from"npm:@huggingface/hub"

Usage examples

@huggingface/inference examples

import{InferenceClient}from"@huggingface/inference";constHF_TOKEN="hf_...";constclient=newInferenceClient(HF_TOKEN);// Chat completion APIconstout=awaitclient.chatCompletion({model:"meta-llama/Llama-3.1-8B-Instruct",messages:[{role:"user",content:"Hello, nice to meet you!"}],max_tokens:512});console.log(out.choices[0].message);// Streaming chat completion APIforawait(constchunkofclient.chatCompletionStream({model:"meta-llama/Llama-3.1-8B-Instruct",messages:[{role:"user",content:"Hello, nice to meet you!"}],max_tokens:512})){console.log(chunk.choices[0].delta.content);}/// Using a third-party provider:awaitclient.chatCompletion({model:"meta-llama/Llama-3.1-8B-Instruct",messages:[{role:"user",content:"Hello, nice to meet you!"}],max_tokens:512,provider:"sambanova",// or together, fal-ai, replicate, cohere …})awaitclient.textToImage({model:"black-forest-labs/FLUX.1-dev",inputs:"a picture of a green bird",provider:"fal-ai",})// You can also omit "model" to use the recommended model for the taskawaitclient.translation({inputs:"My name is Wolfgang and I live in Amsterdam",parameters:{src_lang:"en",tgt_lang:"fr",},});// pass multimodal files or URLs as inputsawaitclient.imageToText({model:'nlpconnect/vit-gpt2-image-captioning',data:await(awaitfetch('https://picsum.photos/300/300')).blob(),})// Using your own dedicated inference endpoint: https://hf.co/docs/inference-endpoints/constgpt2Client=client.endpoint('https://xyz.eu-west-1.aws.endpoints.huggingface.cloud/gpt2');const{ generated_text}=awaitgpt2Client.textGeneration({inputs:'The answer to the universe is'});// Chat CompletionconstllamaEndpoint=client.endpoint("https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.1-8B-Instruct");constout=awaitllamaEndpoint.chatCompletion({model:"meta-llama/Llama-3.1-8B-Instruct",messages:[{role:"user",content:"Hello, nice to meet you!"}],max_tokens:512,});console.log(out.choices[0].message);

@huggingface/hub examples

import{createRepo,uploadFile,deleteFiles}from"@huggingface/hub";constHF_TOKEN="hf_...";awaitcreateRepo({repo:"my-user/nlp-model",// or { type: "model", name: "my-user/nlp-test" },accessToken:HF_TOKEN});awaituploadFile({repo:"my-user/nlp-model",accessToken:HF_TOKEN,// Can work with native File in browsersfile:{path:"pytorch_model.bin",content:newBlob(...)}});awaitdeleteFiles({repo:{type:"space",name:"my-user/my-space"},// or "spaces/my-user/my-space"accessToken:HF_TOKEN,paths:["README.md",".gitattributes"]});

@huggingface/mcp-client example

import{Agent}from'@huggingface/mcp-client';constHF_TOKEN="hf_...";constagent=newAgent({provider:"auto",model:"Qwen/Qwen2.5-72B-Instruct",apiKey:HF_TOKEN,servers:[{// Playwright MCPcommand:"npx",args:["@playwright/mcp@latest"],},],});awaitagent.loadTools();forawait(constchunkofagent.run("What are the top 5 trending models on Hugging Face?")){if("choices"inchunk){constdelta=chunk.choices[0]?.delta;if(delta.content){console.log(delta.content);}}}

Formatting & testing

sudo corepack enablepnpm installpnpm -r format:checkpnpm -r lint:checkpnpm -r test

Building

pnpm -r build