Prompt API
The LanguageModel interface of the Prompt API represents a session with a browser-provided language model. It exposes static methods for creating sessions and checking availability, as well as instance methods for prompting the model, appending context, and managing the context window.
LanguageModel instances cannot be constructed directly. Instead, use the static LanguageModel.create_static method.
Instance properties
- LanguageModel.contextUsage
- : Returns the number of context window tokens currently consumed by this session.
- LanguageModel.contextWindow
- : Returns the total context window size available for this session, in tokens.
Static methods
- LanguageModel.availability_static
- : Returns a Promise that resolves with an enumerated value indicating whether the language model is available for the given options.
- LanguageModel.create_static
- : Returns a Promise that resolves with a new
LanguageModelsession, downloading the model data if necessary.
- : Returns a Promise that resolves with a new
Instance methods
- LanguageModel.append()
- : Returns a Promise that resolves when the given input has been added to the session's context window, without generating a response.
- LanguageModel.clone()
- : Returns a Promise that resolves with a new
LanguageModelsession that is a copy of the session it is called on, including all context.
- : Returns a Promise that resolves with a new
- LanguageModel.destroy()
- : Releases the resources assigned to the
LanguageModelinstance it is called on and stops any further activity on it.
- : Releases the resources assigned to the
- LanguageModel.measureContextUsage()
- : Returns a Promise that resolves with the number of context window tokens that the given input would consume if it were used in an operation such as
prompt()orappend().
- : Returns a Promise that resolves with the number of context window tokens that the given input would consume if it were used in an operation such as
- LanguageModel.prompt()
- : Returns a Promise that resolves with the model's complete response to the given input.
- LanguageModel.promptStreaming()
- : Returns a ReadableStream that streams the model's response to the given input as it is generated.
Events
- LanguageModel.contextoverflow_event
- : Fired when a
prompt(),promptStreaming(), orappend()call exceeds the context window size.
- : Fired when a
Examples
Creating a session and prompting the model
This example first calls LanguageModel.create_static to get a new session. It specifies that the language model adopt a "system" role and defines how it should behave. Note that the example uses await because create() returns a Promise. This may take some time to resolve if the model needs to be downloaded.
After creating the session, the example calls LanguageModel.prompt() to ask a specific question.
const session = await LanguageModel.create({
initialPrompts: [
{
role: "system",
content: "You are a helpful assistant.",
},
],
});
const response = await session.prompt("What is the capital of France?");
console.log(response); // "The capital of France is Paris."
Streaming a response
This example calls LanguageModel.promptStreaming() to get an instance of ReadableStream and writes it to the console in chunks.
const session = await LanguageModel.create();
const readableStream = session.promptStreaming("Tell me a short story.");
for await (const chunk of readableStream) {
console.log(chunk);
}
Specifications
Browser compatibility
See also
来源:MDN Web Docs / Mozilla 贡献者 · 作者与贡献记录 · CC BY-SA 2.5。离线整理了版式、链接和媒体显示。
