# `Vllm.ToolParsers.ToolParser`
[🔗](https://github.com/nshkrdotcom/vllm/blob/v0.3.0/lib/snakebridge_generated/vllm/tool_parsers/tool_parser.ex#L7)

Abstract ToolParser class that should not be used directly. Provided

properties and methods should be used in
derived classes.

# `t`

```elixir
@opaque t()
```

# `adjust_request`

```elixir
@spec adjust_request(SnakeBridge.Ref.t(), term(), keyword()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}
```

Static method that used to adjust the request parameters.

## Parameters

- `request` (term())

## Returns

- `term()`

# `extract_tool_calls`

```elixir
@spec extract_tool_calls(SnakeBridge.Ref.t(), String.t(), term(), keyword()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}
```

Static method that should be implemented for extracting tool calls from

a complete model-generated string.
Used for non-streaming responses where we have the entire model response
available before sending to the client.
Static because it's stateless.

## Parameters

- `model_output` (String.t())
- `request` (term())

## Returns

- `term()`

# `extract_tool_calls_streaming`

```elixir
@spec extract_tool_calls_streaming(
  SnakeBridge.Ref.t(),
  String.t(),
  String.t(),
  String.t(),
  term(),
  term(),
  term(),
  term(),
  keyword()
) :: {:ok, term()} | {:error, Snakepit.Error.t()}
```

Instance method that should be implemented for extracting tool calls

from an incomplete response; for use when handling tool calls and
streaming. Has to be an instance method because  it requires state -
the current tokens/diffs, but also the information about what has
previously been parsed and extracted (see constructor)

## Parameters

- `previous_text` (String.t())
- `current_text` (String.t())
- `delta_text` (String.t())
- `previous_token_ids` (term())
- `current_token_ids` (term())
- `delta_token_ids` (term())
- `request` (term())

## Returns

- `term()`

# `new`

```elixir
@spec new(
  term(),
  keyword()
) :: {:ok, SnakeBridge.Ref.t()} | {:error, Snakepit.Error.t()}
```

Initialize self.  See help(type(self)) for accurate signature.

## Parameters

- `tokenizer` (term())

# `vocab`

```elixir
@spec vocab(SnakeBridge.Ref.t()) :: {:ok, term()} | {:error, Snakepit.Error.t()}
```

---

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