langchain.js
    Preparing search index...

    Class ChatPrem<CallOptions>

    Integration with a chat model.

    Type Parameters

    Hierarchy (View Summary)

    Implements

    Indexable

    • [k: string]: unknown
    Index

    Constructors

    constructor

    Properties

    apiKey? client frequency_penalty? lc_serializable logit_bias? max_tokens? messages model? n? presence_penalty? project_id response_format? seed? session_id? stop? streaming system_prompt? temperature? tools? top_p? user?

    Accessors

    lc_aliases lc_secrets

    Methods

    _generate _llmType _streamResponseChunks completionWithRetry invocationParams lc_name

    Constructors

    • Type Parameters

      • CallOptions extends BaseLanguageModelCallOptions = BaseLanguageModelCallOptions

      Parameters

      Returns ChatPrem<CallOptions>

    Properties

    apiKey?: string

    The Prem API key to use for requests.

    process.env.PREM_API_KEY
    client: Prem
    frequency_penalty?: number
    lc_serializable: boolean = true
    logit_bias?: { [k: string]: unknown }
    max_tokens?: number
    messages: { content: string; role: "user" | "assistant"; [k: string]: unknown }[]
    model?: string
    n?: number
    presence_penalty?: number
    project_id: number
    response_format?: { [k: string]: unknown }
    seed?: number
    session_id?: string
    stop?: string
    streaming: boolean = false
    system_prompt?: string
    temperature?: number
    tools?: { [k: string]: unknown }[]
    top_p?: number
    user?: string

    Accessors

    • get lc_aliases(): undefined | { [key: string]: string }

      Returns undefined | { [key: string]: string }

    • get lc_secrets(): undefined | { [key: string]: string }

      Replace with any secrets this class passes to super. See ../../langchain-cohere/src/chat_model.ts for an example.

      Returns undefined | { [key: string]: string }

    Methods

    _generate

    • _generate(
          messages: BaseMessage[],
          options: unknown,
          runManager?: any,
      ): Promise<ChatResult>

      Parameters

      • messages: BaseMessage[]
      • options: unknown
      • OptionalrunManager: any

      Returns Promise<ChatResult>

    _llmType

    • _llmType(): string

      Returns string

    _streamResponseChunks

    • _streamResponseChunks(
          messages: BaseMessage[],
          options: unknown,
          runManager?: any,
      ): AsyncGenerator<ChatGenerationChunk>

      Implement to support streaming. Should yield chunks iteratively.

      Parameters

      • messages: BaseMessage[]
      • options: unknown
      • OptionalrunManager: any

      Returns AsyncGenerator<ChatGenerationChunk>

    • Parameters

      Returns Promise<AsyncIterable<ChatCompletionStreamingCompletionData, any, any>>

    • Parameters

      Returns Promise<ChatCompletionResponse>

    • Parameters

      • options: unknown

      Returns any

    • Returns string

    Settings

    Member Visibility

    On This Page

    Constructors
    Properties
    Accessors
    Methods