AiBrow
  • Welcome
  • AiBrow web API
    • Getting started
    • Feature comparison
  • AiBrow Extension
    • Getting started
    • Web polyfill
    • Helping users install the AiBrow extension
    • Remove the on-device helper or models
  • Examples
    • Embedding API
    • LanguageDetector API
    • LanguageModel API
    • Rewriter API
    • Summarizer API
    • Translator API
    • Writer API
    • Using different models
    • Model download feedback
    • Getting JSON output
  • API Reference
    • AI
      • AIBrow
      • BrowserAI
      • AIBrowWeb
    • AiBrow
      • Embedding
      • LanguageDetector
      • LanguageModel
      • Rewriter
      • Summarizer
      • Translator
      • Writer
    • Types
      • AIModelAvailability
      • AIModelCoreCompatibility
      • AIModelDtype
      • AIModelGpuEngine
      • AICreateMonitor
      • EmbeddingCreateOptions
      • LanguageDetectorCreateOptions
      • LanguageDetectorDetectResult
      • LanguageModelCreateOptions
      • RewriterCreateOptions
      • RewriterFormat
      • RewriterLength
      • RewriterTone
      • SummarizerCreateOptions
      • SummarizerFormat
      • SummarizerLength
      • SummarizerType
      • TranslatorCreateOptions
      • WriterCreateOptions
      • WriterFormat
      • WriterLength
      • WriterTone
    • Models
Powered by GitBook
On this page
  • Static Methods
  • static availability
  • static compatibility extension web
  • static create
  • Properties
  • gpuEngine extension web
  • dtype extension web
  • flashAttention extension web
  • contextSize
  • inputUsage
  • inputQuota
  • topK
  • topP extension web
  • temperature
  • repeatPenalty extension web
  • Methods
  • prompt
  • promptStreaming
  • append
  • measureInputUsage
  1. API Reference
  2. AiBrow

LanguageModel

PreviousLanguageDetectorNextRewriter

Last updated 12 days ago

Static Methods

static availability

static async availability(options) =>

Get the availability of the on-device language model.

Options (optional)

Returns the availability

static compatibility extension web

static async compatibility(options) =>

Get the availability of the on-device language model.

Options (optional)

Returns the compatibility

static create

static async create(options) =>

Creates a new embedding session

Options (optional)

Returns a new LanguageModel session that can be prompted with the pre-provided configuration


Properties

gpuEngine extension web

dtype extension web

flashAttention extension web

boolean

contextSize

number

inputUsage

number

inputQuota

number

topK

number

topP extension web

number

temperature

number

repeatPenalty extension web

number


Methods

prompt

async (input, options) => string

promptStreaming

(input, options) => ReadableStream

This prompts the language model with a continuation of the conversation. Internally, the input is appended to the set of messages in the language model's context window. Older messages outside of the language model's context window are automatically discarded.

Input

Either a string, single prompt or array of prompts such as

Options (optional)

signal optional AbortSignal

responseConstrains optional object

Returns a readable stream that updates each time new tokens are available from the language model

append

async (input) => void

Appends a message to the conversation without prompting the model

Input

A string

measureInputUsage

async (input, options) => number

Measures the prompt usage of the input

Input

A string

Options (optional)

signal optional AbortSignal

Returns prompt usage based on the input

options optional

options optional

options optional

See

[
  { content: "The prompt content", role: "user" },
  { content: "The prompt content", role: "assistant" }
]
AIModelAvailability
AIModelCoreCompatibility
LanguageModel
AIModelGpuEngine
AIModelDtype
promptStreaming
LanguageModelCreateOptions
LanguageModelCreateOptions
LanguageModelCreateOptions