Skip to content

base

Agent Base Plugin

Classes

BaseAIPlugin

Bases: BaseDataModel

Due to the complexity of the OpenAI API implementation within the Eleanor backend, capabilities should be added via this callback interface.

This interface should be agnostic to the underlying AI model as well as how it is called (chat, chat streaming, completion, etc.)

Functions

after_new_context_created 
after_new_context_created(
    request: ChatCompletionRequest,
    sa_session: SASession,
    neo4j_session: NJSession,
    context: EleanorAIRequestContext,
) -> None

Triggered when a new AI request context is created

Parameters:

Returns:

  • None –

    None

after_response_generation 
after_response_generation(
    request: ChatCompletionRequest,
    sa_session: SASession,
    neo4j_session: NJSession,
    context: EleanorAIRequestContext,
    response_txt_n: List[str],
) -> None

Executes after all LLM respones have been generated

Parameters:

  • request (ChatCompletionRequest) –

    The chat completion request.

  • session (SASession) –

    The SQLAlchemy session object.

  • context (EleanorAIRequestContext) –

    The AI request context.

  • response_txt_n (List[str]) –

    The list of generated response texts.

Returns:

  • None –

    None

before_prompt_rendered 
before_prompt_rendered(
    request: ChatCompletionRequest,
    sa_session: SASession,
    neo4j_session: NJSession,
    context: EleanorAIRequestContext,
    chat: CanonicalChat,
) -> CanonicalChat

Triggered before the CananicalChat object is rendered into the LLM-specific prompt string.

Parameters:

Returns: