base on Utilities to use the Hugging Face Hub API <p align="center">
<br/>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/datasets/huggingface/documentation-images/raw/main/huggingfacejs-dark.svg">
<source media="(prefers-color-scheme: light)" srcset="https://huggingface.co/datasets/huggingface/documentation-images/raw/main/huggingfacejs-light.svg">
<img alt="huggingface javascript library logo" src="https://huggingface.co/datasets/huggingface/documentation-images/raw/main/huggingfacejs-light.svg" width="376" height="59" style="max-width: 100%;">
</picture>
<br/>
<br/>
</p>
```ts
// Programatically interact with the Hub
await createRepo({
repo: {type: "model", name: "my-user/nlp-model"},
accessToken: HF_TOKEN
});
await uploadFile({
repo: "my-user/nlp-model",
accessToken: HF_TOKEN,
// Can work with native File in browsers
file: {
path: "pytorch_model.bin",
content: new Blob(...)
}
});
// Use Inference API
await inference.chatCompletion({
model: "meta-llama/Llama-3.1-8B-Instruct",
messages: [
{
role: "user",
content: "Hello, nice to meet you!",
},
],
max_tokens: 512,
temperature: 0.5,
});
await inference.textToImage({
model: "black-forest-labs/FLUX.1-dev",
inputs: "a picture of a green bird",
});
// and much more…
```
# Hugging Face JS libraries
This is a collection of JS libraries to interact with the Hugging Face API, with TS types included.
- [@huggingface/inference](packages/inference/README.md): Use Inference Endpoints (dedicated) and Inference API (serverless) to make calls to 100,000+ Machine Learning models
- [@huggingface/hub](packages/hub/README.md): Interact with huggingface.co to create or delete repos and commit / download files
- [@huggingface/agents](packages/agents/README.md): Interact with HF models through a natural language interface
- [@huggingface/gguf](packages/gguf/README.md): A GGUF parser that works on remotely hosted files.
- [@huggingface/tasks](packages/tasks/README.md): The definition files and source-of-truth for the Hub's main primitives like pipeline tasks, model libraries, etc.
- [@huggingface/space-header](packages/space-header/README.md): Use the Space `mini_header` outside Hugging Face
We use modern features to avoid polyfills and dependencies, so the libraries will only work on modern browsers / Node.js >= 18 / Bun / Deno.
The libraries are still very young, please help us by opening issues!
## Installation
### From NPM
To install via NPM, you can download the libraries as needed:
```bash
npm install @huggingface/inference
npm install @huggingface/hub
npm install @huggingface/agents
```
Then import the libraries in your code:
```ts
import { HfInference } from "@huggingface/inference";
import { HfAgent } from "@huggingface/agents";
import { createRepo, commit, deleteRepo, listFiles } from "@huggingface/hub";
import type { RepoId } from "@huggingface/hub";
```
### From CDN or Static hosting
You can run our packages with vanilla JS, without any bundler, by using a CDN or static hosting. Using [ES modules](https://hacks.mozilla.org/2018/03/es-modules-a-cartoon-deep-dive/), i.e. `<script type="module">`, you can import the libraries in your code:
```html
<script type="module">
import { HfInference } from 'https://cdn.jsdelivr.net/npm/@huggingface/
[email protected]/+esm';
import { createRepo, commit, deleteRepo, listFiles } from "https://cdn.jsdelivr.net/npm/@huggingface/
[email protected]/+esm";
</script>
```
### Deno
```ts
// esm.sh
import { HfInference } from "https://esm.sh/@huggingface/inference"
import { HfAgent } from "https://esm.sh/@huggingface/agents";
import { createRepo, commit, deleteRepo, listFiles } from "https://esm.sh/@huggingface/hub"
// or npm:
import { HfInference } from "npm:@huggingface/inference"
import { HfAgent } from "npm:@huggingface/agents";
import { createRepo, commit, deleteRepo, listFiles } from "npm:@huggingface/hub"
```
## Usage examples
Get your HF access token in your [account settings](https://huggingface.co/settings/tokens).
### @huggingface/inference examples
```ts
import { HfInference } from "@huggingface/inference";
const HF_TOKEN = "hf_...";
const inference = new HfInference(HF_TOKEN);
// Chat completion API
const out = await inference.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 API
for await (const chunk of inference.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);
}
// You can also omit "model" to use the recommended model for the task
await inference.translation({
inputs: "My name is Wolfgang and I live in Amsterdam",
parameters: {
src_lang: "en",
tgt_lang: "fr",
},
});
await inference.textToImage({
model: 'black-forest-labs/FLUX.1-dev',
inputs: 'a picture of a green bird',
})
await inference.imageToText({
data: await (await fetch('https://picsum.photos/300/300')).blob(),
model: 'nlpconnect/vit-gpt2-image-captioning',
})
// Using your own dedicated inference endpoint: https://hf.co/docs/inference-endpoints/
const gpt2 = inference.endpoint('https://xyz.eu-west-1.aws.endpoints.huggingface.cloud/gpt2');
const { generated_text } = await gpt2.textGeneration({inputs: 'The answer to the universe is'});
//Chat Completion
const llamaEndpoint = inference.endpoint(
"https://api-inference.huggingface.co/models/meta-llama/Llama-3.1-8B-Instruct"
);
const out = await llamaEndpoint.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
```ts
import { createRepo, uploadFile, deleteFiles } from "@huggingface/hub";
const HF_TOKEN = "hf_...";
await createRepo({
repo: "my-user/nlp-model", // or {type: "model", name: "my-user/nlp-test"},
accessToken: HF_TOKEN
});
await uploadFile({
repo: "my-user/nlp-model",
accessToken: HF_TOKEN,
// Can work with native File in browsers
file: {
path: "pytorch_model.bin",
content: new Blob(...)
}
});
await deleteFiles({
repo: {type: "space", name: "my-user/my-space"}, // or "spaces/my-user/my-space"
accessToken: HF_TOKEN,
paths: ["README.md", ".gitattributes"]
});
```
### @huggingface/agents example
```ts
import {HfAgent, LLMFromHub, defaultTools} from '@huggingface/agents';
const HF_TOKEN = "hf_...";
const agent = new HfAgent(
HF_TOKEN,
LLMFromHub(HF_TOKEN),
[...defaultTools]
);
// you can generate the code, inspect it and then run it
const code = await agent.generateCode("Draw a picture of a cat wearing a top hat. Then caption the picture and read it out loud.");
console.log(code);
const messages = await agent.evaluateCode(code)
console.log(messages); // contains the data
// or you can run the code directly, however you can't check that the code is safe to execute this way, use at your own risk.
const messages = await agent.run("Draw a picture of a cat wearing a top hat. Then caption the picture and read it out loud.")
console.log(messages);
```
There are more features of course, check each library's README!
## Formatting & testing
```console
sudo corepack enable
pnpm install
pnpm -r format:check
pnpm -r lint:check
pnpm -r test
```
## Building
```
pnpm -r build
```
This will generate ESM and CJS javascript files in `packages/*/dist`, eg `packages/inference/dist/index.mjs`.
", Assign "at most 3 tags" to the expected json: {"id":"10335","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"