Class ChatAnthropic<CallOptions>

⚠️ Deprecated ⚠️

Install and import from the "@langchain/anthropic" integration package instead.

This feature is deprecated and will be removed in the future.

It is not recommended for use.

Wrapper around Anthropic large language models.

To use you should have the @anthropic-ai/sdk package installed, with the ANTHROPIC_API_KEY environment variable set.

Remarks

Any parameters that are valid to be passed to anthropic.complete can be passed through invocationKwargs, even if not explicitly available on this class.

Example

const model = new ChatAnthropic({
  temperature: 0.9,
  anthropicApiKey: 'YOUR-API-KEY',
});
const res = await model.invoke({ input: 'Hello!' });
console.log(res);

Type Parameters

Hierarchy (view full)

Implements

Constructors

constructor

Properties

clientOptions maxTokensToSample modelName streaming temperature topK topP anthropicApiKey? apiUrl? invocationKwargs? stopSequences? batchClient streamingClient

Methods

identifyingParams invocationParams createStreamWithRetry formatMessagesAsPrompt

Constructors

constructor

Properties

clientOptions

clientOptions: ClientOptions

Overridable Anthropic ClientOptions

maxTokensToSample

maxTokensToSample: number = 2048

A maximum number of tokens to generate before stopping.

modelName

modelName: string = "claude-2"

Model name to use

streaming

streaming: boolean = false

Whether to stream the results or not

temperature

temperature: number = 1

Amount of randomness injected into the response. Ranges from 0 to 1. Use temp closer to 0 for analytical / multiple choice, and temp closer to 1 for creative and generative tasks.

topK

topK: number = -1

Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. Defaults to -1, which disables it.

topP

topP: number = -1

Does nucleus sampling, in which we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by top_p. Defaults to -1, which disables it. Note that you should either alter temperature or top_p, but not both.

Optional anthropicApiKey

anthropicApiKey?: string

Anthropic API key

Optional apiUrl

apiUrl?: string

Optional invocationKwargs

invocationKwargs?: Kwargs

Holds any additional parameters that are valid to pass to anthropic.complete that are not explicitly specified on this class.

Optional stopSequences

stopSequences?: string[]

A list of strings upon which to stop generating. You probably want ["\n\nHuman:"], as that's the cue for the next turn in the dialog agent.

Protected batchClient

batchClient: Anthropic

Protected streamingClient

streamingClient: Anthropic

Methods

identifyingParams

invocationParams

  • invocationParams(options?): Omit<CompletionCreateParams, "prompt"> & Kwargs

  • Get the parameters used to invoke the model

    Parameters

    • Optional options: unknown

    Returns Omit<CompletionCreateParams, "prompt"> & Kwargs

Protected createStreamWithRetry

  • createStreamWithRetry(request): Promise<Stream<Completion>>

  • Creates a streaming request with retry.

    Parameters

    • request: CompletionCreateParams & Kwargs

      The parameters for creating a completion.

    Returns Promise<Stream<Completion>>

    A streaming request.

Protected formatMessagesAsPrompt

  • formatMessagesAsPrompt(messages): string

  • Formats messages as a prompt for the model.

    Parameters

    • messages: BaseMessage[]

      The base messages to format as a prompt.

    Returns string

    The formatted prompt.

Settings

Member Visibility

Theme

On This Page

Generated using TypeDoc