# `AgentDb.ML.ModelManager`
[🔗](https://github.com/manhvu/agent_db/blob/v0.1.0/lib/agent_db/ml/model_manager.ex#L1)

Manages embedding and LLM models for vector search and summarization.

Handles model download, caching, lazy loading, and inference.

# `model_ref`

```elixir
@type model_ref() :: %{
  tokenizer: Bumblebee.Tokenizer.t(),
  model: term(),
  config: map(),
  serving: module(),
  chat_template: String.t()
}
```

# `state`

```elixir
@type state() :: %AgentDb.ML.ModelManager.State{
  config: map(),
  embedding_model: model_ref() | nil,
  in_flight: term(),
  inference_refs: term(),
  last_latency_ms: term(),
  last_load_ms: term(),
  llm_model: model_ref() | nil,
  loading: map(),
  loading_ref: term()
}
```

# `backend`

```elixir
@spec backend() :: :exla | :emlx
```

The resolved ML backend (`:exla` or `:emlx`).

# `child_spec`

Returns a specification to start this module under a supervisor.

See `Supervisor`.

# `embed`

```elixir
@spec embed([String.t()]) :: {:ok, [Nx.Tensor.t()]} | {:error, term()}
```

Generates embeddings for the given texts.

Returns `{:error, :model_loading}` when the model is not ready and has not
become ready within the configured load grace (Config.model_load_grace_ms/0). That is distinct from a
load that failed, and the call is safe to repeat.

# `model_status`

```elixir
@spec model_status() :: map()
```

Returns the status of both models.

# `start_link`

```elixir
@spec start_link(keyword()) :: GenServer.on_start()
```

# `summarize`

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

Generates a summary for the given prompt.

Returns `{:error, :model_loading}` when the model is not ready and has not
become ready within the configured load grace (Config.model_load_grace_ms/0).

---

*Consult [api-reference.md](api-reference.md) for complete listing*