Hugging Face hosts thousands of open models for NLP, vision, and other tasks. The Inference API (via Inference Providers) lets you call those models over HTTP. The @huggingface/inference package from huggingface.js is the Node.js client.

Prerequisites

• Hugging Face account
• Access token with permission to call Inference (create a token of type Read or Fine-grained with inference access)
• Node.js version 26
• @huggingface/inference installed (npm i @huggingface/inference)

Some models (especially image generation) are routed through Inference Providers. Enable providers and billing in account settings when a model requires it.

Client setup

Pass your token to InferenceClient. Read it from the environment in production.

import { InferenceClient } from '@huggingface/inference';
const client = new InferenceClient(process.env.HF_TOKEN);

Summarization

Shrink longer text into a short summary. Pick a model trained for summarization and respect its max input length.

const result = await client.summarization({
  model: 'facebook/bart-large-cnn',
  inputs: `The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was initially criticized by some artists and intellectuals, but it became a global cultural icon of France and one of the most recognizable structures in the world.`,
  parameters: {
    max_length: 80,
  },
});
console.log(result.summary_text);

Text classification

Assign labels with confidence scores. Common use case: sentiment analysis on short text.

const labels = await client.textClassification({
  model: 'distilbert-base-uncased-finetuned-sst-2-english',
  inputs: 'I really enjoyed this workshop.',
});
for (const { label, score } of labels) {
  console.log(label, score.toFixed(4));
}

Text to image

Generate an image from a text prompt. The client returns a Blob; write it to disk or serve it from your app.

import { writeFileSync } from 'node:fs';
const image = await client.textToImage({
  provider: 'hf-inference',
  model: 'black-forest-labs/FLUX.1-schnell',
  inputs: 'A watercolor painting of a fox in an autumn forest',
  parameters: {
    num_inference_steps: 4,
  },
});
const buffer = Buffer.from(await image.arrayBuffer());
writeFileSync('output.png', buffer);

With provider: 'hf-inference', use a model from the hf-inference catalog for that task (for example black-forest-labs/FLUX.1-schnell). Older Hub repos such as stabilityai/stable-diffusion-2-1 may no longer exist or lack provider mapping.

Image models are often slower and may incur provider usage charges.

Demo

Runnable scripts for each task live in the huggingface-inference-api-demo folder. Get access via code demos.

Large language models (LLMs) understand and generate text from prompts. OpenAI exposes models through the Responses API. The official openai npm package is the practical way to call it from Node.js. This post covers common patterns beyond a single prompt string.

For the Chat Completions API (messages, choices[0].message.content), see the dedicated post. For the same patterns with the Vercel AI SDK (generateText, streamText), see the dedicated post.

Prerequisites

• OpenAI account
• Generated API key
• Enabled billing
• Node.js version 26
• openai package installed (npm i openai)
• For Markdown output: marked, dompurify, and jsdom (npm i marked dompurify jsdom)

Client setup

Create a client with your API key (read from the environment in production).

import OpenAI from 'openai';
const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

The same SDK can target other hosts that implement a compatible API by setting baseURL and apiKey:

const client = new OpenAI({
  apiKey: process.env.LLM_API_KEY,
  baseURL: 'https://your-gateway.example/v1',
});

Azure OpenAI uses AzureOpenAI instead. Many third-party gateways support Chat Completions only; the examples below use client.responses.*, so confirm your provider supports the Responses API (especially for tools like web search).

Basic integration

Pass a string as input and read output_text from the response.

const response = await client.responses.create({
  model: 'gpt-5.5',
  input: 'Write a one-sentence bedtime story about a unicorn.',
});
console.log(response.output_text);

System prompt

Use top-level instructions for stable behavior (tone, format, role). They take precedence over casual wording in the user message.

const response = await client.responses.create({
  model: 'gpt-5.5',
  instructions: 'Reply in one short sentence. Use plain language.',
  input: 'Explain what an LLM is.',
});
console.log(response.output_text);

Few-shot prompting

Pass prior turns as an input array with user and assistant roles, then the new user message. Keep task rules in instructions.

const response = await client.responses.create({
  model: 'gpt-5.5',
  instructions:
    'Classify sentiment as exactly one word: positive, negative, or neutral.',
  input: [
    { role: 'user', content: 'I love this!' },
    { role: 'assistant', content: 'positive' },
    { role: 'user', content: 'This is awful.' },
    { role: 'assistant', content: 'negative' },
    { role: 'user', content: 'It is fine I guess.' },
  ],
});
console.log(response.output_text);

Streaming

Set stream: true and handle response.output_text.delta events for incremental text.

const stream = await client.responses.create({
  model: 'gpt-5.5',
  input: 'List three colors.',
  stream: true,
});
for await (const event of stream) {
  if (event.type === 'response.output_text.delta') {
    process.stdout.write(event.delta);
  }
}

Structured output with JSON schema

Constrain the model to JSON matching your schema via text.format. With strict: true, the output should match the schema.

const response = await client.responses.create({
  model: 'gpt-5.5',
  input: 'The film Inception was directed by Christopher Nolan.',
  text: {
    format: {
      type: 'json_schema',
      name: 'movie_summary',
      strict: true,
      schema: {
        type: 'object',
        properties: {
          title: { type: 'string' },
          director: { type: 'string' },
        },
        required: ['title', 'director'],
        additionalProperties: false,
      },
    },
  },
});
const data = JSON.parse(response.output_text);
console.log(data.title, data.director);

For typed parsing with Zod, you can use client.responses.parse() instead of JSON.parse.

Markdown output to HTML

Ask for Markdown in instructions, then convert output_text to HTML and sanitize before rendering (for example with innerHTML in the browser or when storing HTML).

import { marked } from 'marked';
import { JSDOM } from 'jsdom';
import DOMPurify from 'dompurify';
const purify = DOMPurify(new JSDOM('').window);
const response = await client.responses.create({
  model: 'gpt-5.5',
  instructions: 'Reply in Markdown only. Use a heading and a short bullet list.',
  input: 'Explain what an LLM is in three bullet points.',
});
const markdown = response.output_text;
const html = marked.parse(markdown);
const safeHtml = purify.sanitize(html);

Always run DOMPurify.sanitize on model-generated HTML. The model can emit unsafe markup; sanitization strips scripts and other dangerous content.

Web search tool

Enable the built-in web search tool when the answer should use current information from the web.

const response = await client.responses.create({
  model: 'gpt-5.5',
  tools: [{ type: 'web_search' }],
  include: ['web_search_call.action.sources'],
  input: 'What was a major tech headline this week? Cite sources briefly.',
});
console.log(response.output_text);

Web search adds latency and tool usage cost. Use a model that supports tools.

Demo

Runnable scripts for each section live in the openai-responses-api-demo folder. Get access via code demos.

Setting up a timeout for HTTP requests can prevent the connection from hanging forever, waiting for the response. It can be set on the client side to improve user experience, and on the server side to improve inter-service communication.

axios package provides a timeout parameter for this functionality.

const HTTP_TIMEOUT = 3000;
const URL = 'https://www.google.com:81';
(async () => {
  try {
    await axios(URL, {
      timeout: HTTP_TIMEOUT
    });
  } catch (error) {
    console.error('Request timed out', error.cause);
  }
})();

Use this snippet also to simulate aborted requests.

GitHub provides GraphQL API to create integrations, retrieve data, and automate workflows.

Prerequisites

• GitHub token (Settings → Developer Settings → Personal access tokens)

Integration

Below is an example of retrieving sponsorable users by location.

export async function getUsersBy(location) {
  return fetch('https://api.github.com/graphql', {
    method: 'POST',
    body: JSON.stringify({
      query: `query {
        search(type: USER, query: "location:${location} is:sponsorable", first: 100) {
          edges {
            node {
              ... on User {
                bio
                login
                viewerCanSponsor
              }
            }
          }
          userCount
        }
      }`
    }),
    headers: {
      ContentType: 'application/json',
      Authorization: `Bearer ${process.env.GITHUB_TOKEN}`
    }
  })
    .then((response) => response.json())
    .then((response) => response.data?.search?.edges || []);
}

Gumroad allows verifying license keys via API calls to limit the usage of the keys. It can be helpful to prevent the redistribution of products like desktop apps.

Allow generating a unique license key per sale in product settings, and the product ID will be shown there. Below is the code snippet for verification.

try {
  const requestBody = new URLSearchParams();
  requestBody.append('product_id', process.env.PRODUCT_ID);
  requestBody.append('license_key', process.env.LICENSE_KEY);
  requestBody.append('increment_uses_count', true);
  const response = await fetch('https://api.gumroad.com/v2/licenses/verify', {
    method: 'POST',
    body: requestBody
  });
  const data = await response.json();
  if (data.purchase?.test) {
    console.log('Skipping verification for test purchase');
    return;
  }
  const verificationLimit = Number(process.env.VERIFICATION_LIMIT);
  if (data.uses >= verificationLimit + 1) {
    throw new Error('Verification limit exceeded');
  }
  if (!data.success) {
    throw new Error(data.message);
  }
} catch (error) {
  if (error?.response?.status === 404) {
    console.log("License key doesn't exist");
    return;
  }
  console.log('Verifying license key failed', error);
}

Notion is a versatile workspace tool combining note-taking, task management, databases, and collaboration features into a single platform.

It also supports integration with Notion content, facilitating tasks such as creating pages, retrieving a block, and filtering database entries via API.

Prerequisites

• Notion account
• Generated Integration token (Settings & Members → Connections → Develop or manage integrations → New integration)
• Notion database ID (open database as full page, extract database ID from the URL (https://notion.so/<USERNAME>/<DATABASE_ID>?v=v))
• Added Notion connection (three dots (...) menu → Add Connections → choose created integration)
• @notionhq/client package installed

Integration

Below is an example of interacting with Notion API to create the page (within the chosen database) with icon, cover, properties, and child blocks.

const { Client } = require('@notionhq/client');
const notion = new Client({ auth: process.env.NOTION_INTEGRATION_TOKEN });
const response = await notion.pages.create({
  parent: {
    type: 'database_id',
    database_id: process.env.NOTION_DATABASE_ID
  },
  icon: {
    type: 'emoji',
    emoji: '🆗'
  },
  cover: {
    type: 'external',
    external: {
      url: 'https://cover.com'
    }
  },
  properties: {
    Name: {
      title: [
        {
          type: 'text',
          text: {
            content: 'Some name'
          }
        }
      ]
    },
    Score: {
      number: 42
    },
    Tags: {
      multi_select: [
        {
          name: 'A'
        },
        {
          name: 'B'
        }
      ]
    },
    Generation: {
      select: {
        name: 'I'
      }
    }
    // other properties
  },
  children: [
    {
      object: 'block',
      type: 'bookmark',
      bookmark: {
        url: 'https://bookmark.com'
      }
    }
  ]
});

Async API documentation is used for documenting events in event-driven systems, like Kafka events. All of the event DTOs are stored in one place. It supports YAML and JSON formats.

It contains information about channels and components. Channels and components are defined with their messages and DTO schemas, respectively.

{
  "asyncapi": "2.6.0",
  "info": {
    "title": "Events docs",
    "version": "1.0.0"
  },
  "channels": {
    "topic_name": {
      "publish": {
        "message": {
          "schemaFormat": "application/vnd.oai.openapi;version=3.0.0",
          "payload": {
            "type": "object",
            "properties": {
              "counter": {
                "type": "number"
              }
            },
            "required": ["counter"]
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "EventDto": {
        "type": "object",
        "properties": {
          "counter": {
            "type": "number"
          }
        },
        "required": ["counter"]
      }
    }
  }
}

Autogeneration

Async API docs can be autogenerated by following multiple steps:

• define DTOs and their required and optional fields with ApiProperty and ApiPropertyOptional decorators (from the @nestjs/swagger package), respectively
• generate OpenAPI docs from the defined DTOs
• parse and reuse component schemas from generated OpenAPI documentation to build channel messages and component schemas for Async API docs

Validation

Use AsyncAPI Studio to validate the written specification.

Preview

There are multiple options

• AsyncAPI Studio

• VSCode extension asyncapi-preview, open the command palette, and run the Preview AsyncAPI command.

UI generation

• Install @asyncapi/cli and corresponding template package (e.g., @asyncapi/html-template, @asyncapi/markdown-template)
• Update package.json with scripts

{
  "scripts": {
    // ...
    "generate-docs:html": "asyncapi generate fromTemplate ./asyncapi/asyncapi.json @asyncapi/html-template --output ./docs/html",
    "generate-docs:markdown": "asyncapi generate fromTemplate ./asyncapi/asyncapi.json @asyncapi/markdown-template --output ./docs/markdown"
  }
}

ChatGPT is a large language model (LLM) that understands and processes human prompts to produce helpful responses. OpenAI exposes models through the Chat Completions API. The official openai npm package is the practical way to call it from Node.js. This post covers common patterns beyond a single user message.

For the newer Responses API (web search, instructions, and input), see the dedicated post.

Prerequisites

• OpenAI account
• Generated API key
• Enabled billing
• Node.js version 26
• openai package installed (npm i openai)
• For Markdown output: marked, dompurify, and jsdom (npm i marked dompurify jsdom)

Client setup

Create a client with your API key (read from the environment in production).

import OpenAI from 'openai';
const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

For OpenRouter specifically, see the OpenRouter integration post. The same SDK can target OpenAI-compatible gateways by setting baseURL and apiKey:

const client = new OpenAI({
  apiKey: process.env.LLM_API_KEY,
  baseURL: 'https://your-gateway.example/v1',
});

Azure OpenAI uses AzureOpenAI instead. Many third-party hosts implement Chat Completions, so this API is a common integration path.

Basic integration

Send a user message and read the assistant reply from choices[0].message.content.

const completion = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [
    { role: 'user', content: 'Write a one-sentence bedtime story about a unicorn.' },
  ],
});
console.log(completion.choices[0].message.content);

System prompt

Add a system message (or developer on newer models) before the user message to set tone, format, and role.

const completion = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [
    { role: 'system', content: 'Reply in one short sentence. Use plain language.' },
    { role: 'user', content: 'Explain what an LLM is.' },
  ],
});
console.log(completion.choices[0].message.content);

Few-shot prompting

Include prior user and assistant turns in messages, then the new user question. Keep task rules in the system message.

const completion = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [
    {
      role: 'system',
      content:
        'Classify sentiment as exactly one word: positive, negative, or neutral.',
    },
    { role: 'user', content: 'I love this!' },
    { role: 'assistant', content: 'positive' },
    { role: 'user', content: 'This is awful.' },
    { role: 'assistant', content: 'negative' },
    { role: 'user', content: 'It is fine I guess.' },
  ],
});
console.log(completion.choices[0].message.content);

Streaming

Set stream: true and read incremental text from choices[0].delta.content.

const stream = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [{ role: 'user', content: 'List three colors.' }],
  stream: true,
});
process.stdout.write('[stream] ');
for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta?.content;
  if (delta) {
    process.stdout.write(delta);
  }
}
process.stdout.write('\n');

Structured output with JSON schema

Use response_format with type: 'json_schema' and strict: true so the model returns JSON matching your schema.

const completion = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [
    {
      role: 'user',
      content: 'The film Inception was directed by Christopher Nolan.',
    },
  ],
  response_format: {
    type: 'json_schema',
    json_schema: {
      name: 'movie_summary',
      strict: true,
      schema: {
        type: 'object',
        properties: {
          title: { type: 'string' },
          director: { type: 'string' },
        },
        required: ['title', 'director'],
        additionalProperties: false,
      },
    },
  },
});
const data = JSON.parse(completion.choices[0].message.content);
console.log(data.title, data.director);

For typed parsing with Zod, you can use client.chat.completions.parse() instead of JSON.parse.

Markdown output to HTML

Ask for Markdown in the system message, then convert the assistant reply to HTML and sanitize before rendering.

import { marked } from 'marked';
import { JSDOM } from 'jsdom';
import DOMPurify from 'dompurify';
const purify = DOMPurify(new JSDOM('').window);
const completion = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [
    {
      role: 'system',
      content: 'Reply in Markdown only. Use a heading and a short bullet list.',
    },
    { role: 'user', content: 'Explain what an LLM is in three bullet points.' },
  ],
});
const markdown = completion.choices[0].message.content;
const html = marked.parse(markdown);
const safeHtml = purify.sanitize(html);

Always run DOMPurify.sanitize on model-generated HTML. The model can emit unsafe markup; sanitization strips scripts and other dangerous content.

Demo

Runnable scripts for each section live in the openai-chat-completions-api-demo folder. Get access via code demos.

OpenAPI is a language-agnostic specification for declaring API documentation for REST APIs. It contains the following information:

• API information like title, description, version
• endpoints definitions with request and response parameters
• DTOs and security schemas

openapi: 3.0.0
paths:
  /users:
    post:
      operationId: UsersController_createUser
      summary: Create user
      description: Create a new user
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateUserDto'
      responses:
        '201':
          description: 'User is created'
info:
  title: nestjs-starter
  description: Minimal NestJS boilerplate
  version: 0.1.0
  contact: {}
tags: []
servers: []
components:
  securitySchemes:
    token:
      type: apiKey
      scheme: api_key
      in: header
      name: auth-token
  schemas:
    CreateUserDto:
      type: object
      properties:
        firstName:
          type: string
          example: tester
          description: first name of the user
      required:
        - firstName

NestJS provides a Swagger plugin for generating the API docs.

Setup

Configure API documentation with the specified endpoint, like /api-docs, which shows the generated docs.

const SWAGGER_API_ENDPOINT = '/api-docs';
// ...
export const setupApiDocs = (app: INestApplication): void => {
  const options = new DocumentBuilder()
    .setTitle(SWAGGER_API_TITLE)
    .setDescription(SWAGGER_API_DESCRIPTION)
    .setVersion(SWAGGER_API_VERSION)
    .addSecurity('token', {
      type: 'apiKey',
      scheme: 'api_key',
      in: 'header',
      name: 'auth-token'
    })
    .addBearerAuth()
    .build();
  const document = SwaggerModule.createDocument(app, options);
  SwaggerModule.setup(SWAGGER_API_ENDPOINT, app, document);
};

Configure the plugin in the NestJS config file.

{
  "compilerOptions": {
    "plugins": ["@nestjs/swagger"]
  }
}

JSON and YAML formats are generated at /api-docs-json and /api-docs-yaml endpoints, respectively.

Decorators

• ApiTags groups endpoints

@ApiTags('users')
@Controller('users')
export class UsersController {
  // ...
}

• ApiOperation provides more details like a summary and description of the endpoint

@ApiOperation({
  summary: 'Get user',
  description: 'Get user by id',
})
@Get(':id')
async getById(
  @Param('id', new ParseUUIDPipe()) id: string,
): Promise<UserDto> {
// ...
}

• ApiOperation can be used to mark an endpoint as deprecated

@ApiOperation({ deprecated: true })

• @ApiProperty and @ApiPropertyOptional should be used for request and response DTOs fields. Example and description values will be shown in the generated documentation.

export class CreateUserDto {
  @ApiProperty({ example: 'John', description: 'first name of the user' })
  // ...
  public firstName: string;
  @ApiPropertyOptional({ example: 'Doe', description: 'last name of the user' })
  // ...
  public lastName?: string;
}

• ApiHeader documents endpoint headers

@ApiHeader({
  name: 'correlation-id',
  required: false,
  description: 'unique id for correlated logs',
  example: '7ea2c7f7-8b46-475d-86f8-7aaaa9e4a35b',
})
@Get()
getHello(): string {
// ...
}

• ApiResponse specifies which responses are expected, like error responses. NestJS' Swagger package provides decorators for specific status codes like ApiBadRequestResponse.

// ...
@ApiResponse({ type: NotFoundException, status: HttpStatus.NOT_FOUND })
@ApiBadRequestResponse({ type: BadRequestException })
@Get(':id')
async getById(
  @Param('id', new ParseUUIDPipe()) id: string,
): Promise<UserDto> {
  return this.userService.findById(id);
}
// ...

• ApiSecurity('token') uses a custom-defined security strategy, token in this case. Other options are to use already defined strategies like ApiBearerAuth.

@ApiSecurity('token')
@Controller()
export class AppController {
  // ...
}
// ...
@ApiBearerAuth()
@Controller()
export class AppController {
  // ...
}

• ApiExcludeEndpoint and ApiExcludeController exclude one endpoint and the whole controller, respectively.

export class AppController {
  @ApiExcludeEndpoint()
  @Get()
  getHello(): string {
    // ...
  }
}
// ...
@ApiExcludeController()
@Controller()
export class AppController {
  // ...
}

• ApiBody with ApiExtraModels add an example for the request body

const CreateUserDtoExample = {
    firstName: 'Tester',
  };
  @ApiExtraModels(CreateUserDto)
  @ApiBody({
    schema: {
      oneOf: refs(CreateUserDto),
      example: CreateUserDtoExample,
    },
  })
  @Post()
  async createUser(@Body() newUser: CreateUserDto): Promise<UserDto> {
    // ...
  }

Importing API to Postman

Import JSON version of API docs as Postman API with Import → Link option (e.g., URL http://localhost:8081/api-docs-json). Imported API collection will be available in the APIs tab.

Setting up a timeout for HTTP requests can prevent the connection from hanging forever, waiting for the response. It can be set on the client side to improve user experience, and on the server side to improve inter-service communication. Fetch API is fully available in Node as well from version 18.

AbortController can be utilized to set up timeouts. Instantiated abort controller has a signal property which represents reference to its associated AbortSignal object. Abort signal object is used as a signal parameter in the request with Fetch API, so HTTP request is aborted when abort method is called.

const HTTP_TIMEOUT = 3000;
const URL = 'https://www.google.com:81';
(async () => {
  const controller = new AbortController();
  const timeoutId = setTimeout(() => controller.abort(), HTTP_TIMEOUT);
  try {
    const response = await fetch(URL, {
      signal: controller.signal
    }).then((res) => res.json());
    console.log(response);
  } catch (error) {
    console.error(error);
  } finally {
    clearTimeout(timeoutId);
  }
})();

Use this snippet also to simulate aborted requests.