Class BaseLlmAbstract

constructor

• new BaseLlm(params: { model: string }): BaseLlm

  Creates an instance of BaseLLM.

  Parameters

  • params: { model: string }

    The parameters for creating a BaseLlm instance.

    • model: string

      The name of the LLM, e.g. gemini-1.5-flash or gemini-1.5-flash-001.

  Returns BaseLlm

Readonlymodel

Static ReadonlysupportedModels

Abstractconnect

• connect(llmRequest: LlmRequest): Promise<BaseLlmConnection>

  Creates a live connection to the LLM.

  Parameters

  • llmRequest: LlmRequest

    LlmRequest, the request to send to the LLM.

  Returns Promise<BaseLlmConnection>

  A live connection to the LLM.

AbstractgenerateContentAsync

• generateContentAsync(
      llmRequest: LlmRequest,
      stream?: boolean,
  ): AsyncGenerator<LlmResponse, void>

  Generates one content from the given contents and tools.

  Parameters

  • llmRequest: LlmRequest

    LlmRequest, the request to send to the LLM.

  • Optionalstream: boolean

    whether to do streaming call. For non-streaming call, it will only yield one Content.

  Returns AsyncGenerator<LlmResponse, void>

  A generator of LlmResponse.

maybeAppendUserContent

• maybeAppendUserContent(llmRequest: LlmRequest): void

  Appends a user content, so that model can continue to output.

  Parameters

  • llmRequest: LlmRequest

    LlmRequest, the request to send to the LLM.

  Returns void