# `PtcRunner.LLM.ReqLLMAdapter`
[🔗](https://github.com/andreasronge/ptc_runner/blob/main/lib/ptc_runner/llm/req_llm_adapter.ex#L2)

Built-in LLM adapter using `req_llm`.

Routes requests based on model prefix:
- `ollama:model-name` → Local Ollama server
- `openai-compat:base_url|model` → Any OpenAI-compatible API
- `*` → ReqLLM (OpenRouter, Anthropic, Google, Bedrock, etc.)

Requires `{:req_llm, "~> 1.8"}` as a dependency.

## Prompt Caching

When `cache: true` is set in the request, prompt caching is enabled for
supported providers (Anthropic direct, OpenRouter Anthropic, Bedrock Claude).

## Bedrock Region

For Bedrock models, the region is determined in this order:
1. `AWS_REGION` environment variable
2. `config :ptc_runner, :bedrock_region, "region-name"`
3. Default: `"eu-north-1"`

# `available?`

```elixir
@spec available?(String.t()) :: boolean()
```

Check if a provider is available.

For Ollama, checks if the server is reachable.
For ReqLLM providers, checks if the required API key is set.

# `embed`

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

Generate embeddings for text input.

## Returns
- `{:ok, [float()]}` for single input
- `{:ok, [[float()]]}` for batch input

# `embed!`

```elixir
@spec embed!(String.t(), String.t() | [String.t()], keyword()) ::
  [float()] | [[float()]]
```

Generate embeddings, raising on error.

# `generate_object`

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

Generate a structured JSON object from an LLM.

Only supported for ReqLLM providers. Local providers return
`{:error, :structured_output_not_supported}`.

# `generate_object!`

```elixir
@spec generate_object!(String.t(), [map()], map(), keyword()) :: map()
```

Generate a structured JSON object, raising on error.

# `generate_text`

```elixir
@spec generate_text(String.t(), [map()], keyword()) ::
  {:ok, PtcRunner.LLM.response()} | {:error, term()}
```

Generate text from an LLM.

## Options
- `:receive_timeout` - Request timeout in ms (default: 120000)
- `:ollama_base_url` - Override Ollama server URL
- `:cache` - Enable prompt caching for supported providers (default: false)

# `generate_text!`

```elixir
@spec generate_text!(String.t(), [map()], keyword()) :: PtcRunner.LLM.response()
```

Generate text, raising on error.

# `generate_with_tools`

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

Generate text with tool definitions.

Passes tools to the LLM provider. If the LLM returns tool calls,
they are included in the response as `tool_calls`.

# `requires_api_key?`

```elixir
@spec requires_api_key?(String.t()) :: boolean()
```

Check if the model requires an API key.

---

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