LlmCore.Pipelines.MemoryPipeline (llm_core v0.3.0)

Copy Markdown View Source

ALF pipeline orchestrating all Hindsight memory operations (retain, recall, reflect). It centralizes caching, circuit breaker gating, retries, and async buffering to match the architecture requirements of llm_core.

Summary

Functions

alf_components()

call(event, opts \\ [debug: false])

@spec call(any(), Keyword.t()) :: any() | [any()] | nil
@spec call(any(), Keyword.t()) :: reference()

cast(event, opts \\ [debug: false, send_result: false])

components()

@spec components() :: [map()]

flow(flow, names, opts \\ [debug: false])

@spec flow(map(), list(), Keyword.t()) :: Enumerable.t()

recall(query, opts \\ [])

@spec recall(
  String.t(),
  keyword()
) :: {:ok, [map()]} | {:error, term()}

reflect(question, opts \\ [])

@spec reflect(
  String.t(),
  keyword()
) :: {:ok, term()} | {:error, term()}

retain_async(content, metadata, opts \\ [])

@spec retain_async(String.t(), map(), keyword()) :: :ok

retain_sync(content, metadata, opts \\ [])

@spec retain_sync(String.t(), map(), keyword()) :: {:ok, map()} | {:error, term()}

start()

@spec start() :: :ok

start(opts)

@spec start(list()) :: :ok

started?()

@spec started?() :: true | false

stop()

@spec stop() :: :ok | {:exit, {atom(), any()}}

stream(stream, opts \\ [debug: false])

@spec stream(Enumerable.t(), Keyword.t()) :: Enumerable.t()