vscode.LanguageModelChat - Haxe externs for Visual Studio Code

Represents a language model for making chat requests.

@link lm.selectChatModels}

Fields

`read onlyversion:String`

Opaque version string of the model. This is defined by the extension contributing the language model and subject to change.

`read onlyvendor:String`

A well-known identifier of the vendor of the language model. An example is copilot, but values are defined by extensions contributing chat models and need to be looked up with them.

`sendRequest(messages:Array<LanguageModelChatMessage>, ?options:LanguageModelChatRequestOptions, ?token:CancellationToken):Thenable<LanguageModelChatResponse>`

Make a chat request using a language model.

Note that language model use may be subject to access restrictions and user consent. Calling this function for the first time (for an extension) will show a consent dialog to the user and because of that this function must only be called in response to a user action! Extensions can use {@link LanguageModelAccessInformation.canSendRequest} to check if they have the necessary permissions to make a request.

This function will return a rejected promise if making a request to the language model is not possible. Reasons for this can be:

user consent not given, see {@link LanguageModelError.NoPermissions NoPermissions}
model does not exist anymore, see {@link LanguageModelError.NotFound NotFound}
quota limits exceeded, see {@link LanguageModelError.Blocked Blocked}
other issues in which case extension must check {@link LanguageModelError.cause LanguageModelError.cause}

An extension can make use of language model tool calling by passing a set of tools to {@link LanguageModelChatRequestOptions.tools}. The language model will return a {@link LanguageModelToolCallPart} and the extension can invoke the tool and make another request with the result.

@link CancellationTokenSource} for how to create one. @link LanguageModelChatResponse}. The promise will reject when the request couldn't be made.

Parameters:

`messages`	An array of message instances.
`options`	Options that control the request.
`token`	A cancellation token which controls the request. See {

Returns:

A thenable that resolves to a {

`read onlyname:String`

Human-readable name of the language model.

`read onlymaxInputTokens:Int`

The maximum number of tokens that can be sent to the model in a single request.

`read onlyid:String`

Opaque identifier of the language model.

`read onlyfamily:String`

Opaque family-name of the language model. Values might be gpt-3.5-turbo, gpt4, phi2, or llama but they are defined by extensions contributing languages and subject to change.

`countTokens(text:EitherType<String, LanguageModelChatMessage>, ?token:CancellationToken):Thenable<Int>`

Count the number of tokens in a message using the model specific tokenizer-logic.

@link CancellationTokenSource} for how to create one.