guardrails

EmbeddingScanner

Bases: Protocol

Defines an interface for scanning input embeddings for unauthorized prompts.

scan abstractmethod

scan(input_embeddings: Tensor) -> None

Scan and detect unauthorized embeddings in the input.

Parameters:

Name	Type	Description	Default
input_embeddings	Tensor	The input embeddings to be scanned.	required

Raises:

Type	Description
RuntimeError	If any of the input embeddings are invalid.

TransformedEmbeddingScanner

Bases: EmbeddingScanner

Scans LLM input embeddings for unauthorized prompts.

__init__

__init__(tokenizer: PreTrainedTokenizer | PreTrainedTokenizerFast, model: CausalModelT) -> None

Construct a TransformedEmbeddingScanner.

Parameters:

Name	Type	Description	Default
tokenizer	PreTrainedTokenizer | PreTrainedTokenizerFast	Tokenizer for the LLM model.	required
model	CausalModelT	The LLM model whose input embeddings to check against.	required

scan

scan(input_embeddings: Tensor) -> None

Scan and detect unauthorized embeddings in the input.

Parameters:

Name	Type	Description	Default
input_embeddings	Tensor	Input embeddings for LLM generation.	required

Raises:

Type	Description
ValueError	If the dtype, embedding dimension, or batch size of the input embeddings are invalid.
RuntimeError	If any of the input embeddings are invalid.