Tinkex.Types.ModelInput (Tinkex v0.1.17)

Model input containing chunks of encoded text and/or images.

Mirrors Python tinker.types.ModelInput.

Summary

Functions

from_ints(tokens)

Create ModelInput from a list of token IDs.

from_text(text, opts \\ [])

Create ModelInput from raw text.

from_text!(text, opts \\ [])

Create ModelInput from raw text, raising on failure.

length(model_input)

Get the total length (token count) of the ModelInput.

to_ints(model_input)

Extract all token IDs from the ModelInput.

Types

chunk()

@type chunk() ::
  Tinkex.Types.EncodedTextChunk.t()
  | Tinkex.Types.ImageChunk.t()
  | Tinkex.Types.ImageAssetPointerChunk.t()

t()

@type t() :: %Tinkex.Types.ModelInput{chunks: [chunk()]}

Functions

from_ints(tokens)

@spec from_ints([integer()]) :: t()

Create ModelInput from a list of token IDs.

from_text(text, opts \\ [])

@spec from_text(
  String.t(),
  keyword()
) :: {:ok, t()} | {:error, Tinkex.Error.t()}

Create ModelInput from raw text.

Tokenizes the provided text via Tinkex.Tokenizer.encode/3 and returns a tuple using the same {:ok, ...} | {:error, ...} contract. Chat templates are not applied; callers must supply fully formatted prompts.

Options

:model_name (required) - Model name used to resolve the tokenizer.
:training_client - Forwarded to tokenizer resolution.
Any other options supported by Tinkex.Tokenizer.encode/3.

from_text!(text, opts \\ [])

@spec from_text!(
  String.t(),
  keyword()
) :: t()

Create ModelInput from raw text, raising on failure.

See from_text/2 for options and behavior.

length(model_input)

@spec length(t()) :: non_neg_integer()

Get the total length (token count) of the ModelInput.

For image chunks, expected_tokens must be set; otherwise length/1 will raise to mirror Python SDK guardrails.

to_ints(model_input)

@spec to_ints(t()) :: [integer()]

Extract all token IDs from the ModelInput.

Only works with EncodedTextChunk chunks. Raises for image chunks.