Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

tflite_support.task.text.TextSearcher

Class to performs text search.

tflite_support.task.text.TextSearcher(
    options: tflite_support.task.text.TextSearcherOptions,
    cpp_searcher: _CppTextSearcher
) -> None

It works by performing embedding extraction on text, followed by nearest-neighbor search in an index of embeddings through ScaNN.

Attributes
`options`

Attributes

options

@classmethod
create_from_file(
    model_file_path: str, index_file_path: Optional[str] = None
) -> 'TextSearcher'

Creates the TextSearcher object from a TensorFlow Lite model.

Args
`model_file_path`	Path to the model.
`index_file_path`	Path to the index. Only required if the index is not attached to the output tensor metadata as an AssociatedFile with type SCANN_INDEX_FILE.

Returns
`TextSearcher` object that's created from `options`.

Raises
`ValueError`	If failed to create `TextSearcher` object from the provided file such as invalid file.
`RuntimeError`	If other types of error occurred.

@classmethod
create_from_options(
    options: tflite_support.task.text.TextSearcherOptions
) -> 'TextSearcher'

Creates the TextSearcher object from text searcher options.

Args
`options`	Options for the text searcher task.

Returns
`TextSearcher` object that's created from `options`.

Raises
`ValueError`	If failed to create `TextSearcher` object from `TextSearcherOptions` such as missing the model.
`RuntimeError`	If other types of error occurred.

get_user_info() -> str

Gets the user info stored in the index file.

Returns
Opaque user info stored in the index file (if any), in raw binary form. Returns an empty string if the index doesn't contain user info.

search(
    text: str
) -> tflite_support.task.processor.SearchResult

Search for text with similar semantic meaning.

This method performs actual feature extraction on the provided text input, followed by nearest-neighbor search in the index.

Args
`text`	the input text, used to extract the feature vectors.

Returns
search result.

Raises
`ValueError`	If any of the input arguments is invalid.
`RuntimeError`	If failed to perform nearest-neighbor search.