"""gr.Dataset() component.""" from __future__ import annotations import warnings from typing import Any, Literal, Sequence from gradio_client.documentation import document from gradio import processing_utils from gradio.components.base import ( Component, get_component_instance, ) from gradio.events import Events from gradio.events import Dependency @document() class Dataset(Component): """ Creates a gallery or table to display data samples. This component is primarily designed for internal use to display examples. However, it can also be used directly to display a dataset and let users select examples. """ EVENTS = [Events.click, Events.select] def __init__( self, *, label: str | None = None, components: Sequence[Component] | list[str] | None = None, component_props: list[dict[str, Any]] | None = None, samples: list[list[Any]] | None = None, headers: list[str] | None = None, type: Literal["values", "index", "tuple"] = "values", samples_per_page: int = 10, visible: bool = True, elem_id: str | None = None, elem_classes: list[str] | str | None = None, render: bool = True, key: int | str | None = None, container: bool = True, scale: int | None = None, min_width: int = 160, proxy_url: str | None = None, sample_labels: list[str] | None = None, ): """ Parameters: label: The label for this component, appears above the component. components: Which component types to show in this dataset widget, can be passed in as a list of string names or Components instances. The following components are supported in a Dataset: Audio, Checkbox, CheckboxGroup, ColorPicker, Dataframe, Dropdown, File, HTML, Image, Markdown, Model3D, Number, Radio, Slider, Textbox, TimeSeries, Video samples: a nested list of samples. Each sublist within the outer list represents a data sample, and each element within the sublist represents an value for each component headers: Column headers in the Dataset widget, should be the same len as components. If not provided, inferred from component labels type: "values" if clicking on a sample should pass the value of the sample, "index" if it should pass the index of the sample, or "tuple" if it should pass both the index and the value of the sample. samples_per_page: how many examples to show per page. visible: If False, component will be hidden. elem_id: An optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles. elem_classes: An optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles. render: If False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later. key: if assigned, will be used to assume identity across a re-render. Components that have the same key across a re-render will have their value preserved. container: If True, will place the component in a container - providing some extra padding around the border. scale: relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True. min_width: minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first. proxy_url: The URL of the external Space used to load this component. Set automatically when using `gr.load()`. This should not be set manually. sample_labels: A list of labels for each sample. If provided, the length of this list should be the same as the number of samples, and these labels will be used in the UI instead of rendering the sample values. """ super().__init__( visible=visible, elem_id=elem_id, elem_classes=elem_classes, render=render, key=key, ) self.container = container self.scale = scale self.min_width = min_width self._components = [get_component_instance(c) for c in components or []] if component_props is None: self.component_props = [ component.recover_kwargs( component.get_config(), ["value"], ) for component in self._components ] else: self.component_props = component_props # Narrow type to Component if not all(isinstance(c, Component) for c in self._components): raise TypeError( "All components in a `Dataset` must be subclasses of `Component`" ) self._components = [c for c in self._components if isinstance(c, Component)] self.proxy_url = proxy_url for component in self._components: component.proxy_url = proxy_url self.raw_samples = [[]] if samples is None else samples self.samples: list[list] = [] for example in self.raw_samples: self.samples.append([]) for component, ex in zip(self._components, example): # If proxy_url is set, that means it is being loaded from an external Gradio app # which means that the example has already been processed. if self.proxy_url is None: # We do not need to process examples if the Gradio app is being loaded from # an external Space because the examples have already been processed. Also, # the `as_example()` method has been renamed to `process_example()` but we # use the previous name to be backwards-compatible with previously-created # custom components ex = component.as_example(ex) self.samples[-1].append( processing_utils.move_files_to_cache( ex, component, keep_in_cache=True ) ) self.type = type self.label = label if headers is not None: self.headers = headers elif all(c.label is None for c in self._components): self.headers = [] else: self.headers = [c.label or "" for c in self._components] self.samples_per_page = samples_per_page self.sample_labels = sample_labels def api_info(self) -> dict[str, str]: return {"type": "integer", "description": "index of selected example"} def get_config(self): config = super().get_config() config["components"] = [] config["component_props"] = self.component_props config["sample_labels"] = self.sample_labels config["component_ids"] = [] for component in self._components: config["components"].append(component.get_block_name()) config["component_ids"].append(component._id) return config def preprocess(self, payload: int | None) -> int | list | tuple[int, list] | None: """ Parameters: payload: the index of the selected example in the dataset Returns: Passes the selected sample either as a `list` of data corresponding to each input component (if `type` is "value") or as an `int` index (if `type` is "index"), or as a `tuple` of the index and the data (if `type` is "tuple"). """ if payload is None: return None if self.type == "index": return payload elif self.type == "values": return self.raw_samples[payload] elif self.type == "tuple": return payload, self.raw_samples[payload] def postprocess(self, value: int | list | None) -> int | None: """ Parameters: value: Expects an `int` index or `list` of sample data. Returns the index of the sample in the dataset or `None` if the sample is not found. Returns: Returns the index of the sample in the dataset. """ if value is None or isinstance(value, int): return value if isinstance(value, list): try: index = self.samples.index(value) except ValueError: index = None warnings.warn( "The `Dataset` component does not support updating the dataset data by providing " "a set of list values. Instead, you should return a new Dataset(samples=...) object." ) return index def example_payload(self) -> Any: return 0 def example_value(self) -> Any: return [] from typing import Callable, Literal, Sequence, Any, TYPE_CHECKING from gradio.blocks import Block if TYPE_CHECKING: from gradio.components import Timer def click(self, fn: Callable[..., Any] | None = None, inputs: Block | Sequence[Block] | set[Block] | None = None, outputs: Block | Sequence[Block] | None = None, api_name: str | None | Literal[False] = None, scroll_to_output: bool = False, show_progress: Literal["full", "minimal", "hidden"] = "full", queue: bool | None = None, batch: bool = False, max_batch_size: int = 4, preprocess: bool = True, postprocess: bool = True, cancels: dict[str, Any] | list[dict[str, Any]] | None = None, every: Timer | float | None = None, trigger_mode: Literal["once", "multiple", "always_last"] | None = None, js: str | None = None, concurrency_limit: int | None | Literal["default"] = "default", concurrency_id: str | None = None, show_api: bool = True) -> Dependency: """ Parameters: fn: the function to call when this event is triggered. Often a machine learning model's prediction function. Each parameter of the function corresponds to one input component, and the function should return a single value or a tuple of values, with each element in the tuple corresponding to one output component. inputs: list of gradio.components to use as inputs. If the function takes no inputs, this should be an empty list. outputs: list of gradio.components to use as outputs. If the function returns no outputs, this should be an empty list. api_name: defines how the endpoint appears in the API docs. Can be a string, None, or False. If False, the endpoint will not be exposed in the api docs. If set to None, the endpoint will be exposed in the api docs as an unnamed endpoint, although this behavior will be changed in Gradio 4.0. If set to a string, the endpoint will be exposed in the api docs with the given name. scroll_to_output: if True, will scroll to output component on completion show_progress: how to show the progress animation while event is running: "full" shows a spinner which covers the output component area as well as a runtime display in the upper right corner, "minimal" only shows the runtime display, "hidden" shows no progress animation at all queue: if True, will place the request on the queue, if the queue has been enabled. If False, will not put this event on the queue, even if the queue has been enabled. If None, will use the queue setting of the gradio app. batch: if True, then the function should process a batch of inputs, meaning that it should accept a list of input values for each parameter. The lists should be of equal length (and be up to length `max_batch_size`). The function is then *required* to return a tuple of lists (even if there is only 1 output component), with each list in the tuple corresponding to one output component. max_batch_size: maximum number of inputs to batch together if this is called from the queue (only relevant if batch=True) preprocess: if False, will not run preprocessing of component data before running 'fn' (e.g. leaving it as a base64 string if this method is called with the `Image` component). postprocess: if False, will not run postprocessing of component data before returning 'fn' output to the browser. cancels: a list of other events to cancel when this listener is triggered. For example, setting cancels=[click_event] will cancel the click_event, where click_event is the return value of another components .click method. Functions that have not yet run (or generators that are iterating) will be cancelled, but functions that are currently running will be allowed to finish. every: continously calls `value` to recalculate it if `value` is a function (has no effect otherwise). Can provide a Timer whose tick resets `value`, or a float that provides the regular interval for the reset Timer. trigger_mode: if "once" (default for all events except `.change()`) would not allow any submissions while an event is pending. If set to "multiple", unlimited submissions are allowed while pending, and "always_last" (default for `.change()` and `.key_up()` events) would allow a second submission after the pending event is complete. js: optional frontend js method to run before running 'fn'. Input arguments for js method are values of 'inputs' and 'outputs', return should be a list of values for output components. concurrency_limit: if set, this is the maximum number of this event that can be running simultaneously. Can be set to None to mean no concurrency_limit (any number of this event can be running simultaneously). Set to "default" to use the default concurrency limit (defined by the `default_concurrency_limit` parameter in `Blocks.queue()`, which itself is 1 by default). concurrency_id: if set, this is the id of the concurrency group. Events with the same concurrency_id will be limited by the lowest set concurrency_limit. show_api: whether to show this event in the "view API" page of the Gradio app, or in the ".view_api()" method of the Gradio clients. Unlike setting api_name to False, setting show_api to False will still allow downstream apps as well as the Clients to use this event. If fn is None, show_api will automatically be set to False. """ ... def select(self, fn: Callable[..., Any] | None = None, inputs: Block | Sequence[Block] | set[Block] | None = None, outputs: Block | Sequence[Block] | None = None, api_name: str | None | Literal[False] = None, scroll_to_output: bool = False, show_progress: Literal["full", "minimal", "hidden"] = "full", queue: bool | None = None, batch: bool = False, max_batch_size: int = 4, preprocess: bool = True, postprocess: bool = True, cancels: dict[str, Any] | list[dict[str, Any]] | None = None, every: Timer | float | None = None, trigger_mode: Literal["once", "multiple", "always_last"] | None = None, js: str | None = None, concurrency_limit: int | None | Literal["default"] = "default", concurrency_id: str | None = None, show_api: bool = True) -> Dependency: """ Parameters: fn: the function to call when this event is triggered. Often a machine learning model's prediction function. Each parameter of the function corresponds to one input component, and the function should return a single value or a tuple of values, with each element in the tuple corresponding to one output component. inputs: list of gradio.components to use as inputs. If the function takes no inputs, this should be an empty list. outputs: list of gradio.components to use as outputs. If the function returns no outputs, this should be an empty list. api_name: defines how the endpoint appears in the API docs. Can be a string, None, or False. If False, the endpoint will not be exposed in the api docs. If set to None, the endpoint will be exposed in the api docs as an unnamed endpoint, although this behavior will be changed in Gradio 4.0. If set to a string, the endpoint will be exposed in the api docs with the given name. scroll_to_output: if True, will scroll to output component on completion show_progress: how to show the progress animation while event is running: "full" shows a spinner which covers the output component area as well as a runtime display in the upper right corner, "minimal" only shows the runtime display, "hidden" shows no progress animation at all queue: if True, will place the request on the queue, if the queue has been enabled. If False, will not put this event on the queue, even if the queue has been enabled. If None, will use the queue setting of the gradio app. batch: if True, then the function should process a batch of inputs, meaning that it should accept a list of input values for each parameter. The lists should be of equal length (and be up to length `max_batch_size`). The function is then *required* to return a tuple of lists (even if there is only 1 output component), with each list in the tuple corresponding to one output component. max_batch_size: maximum number of inputs to batch together if this is called from the queue (only relevant if batch=True) preprocess: if False, will not run preprocessing of component data before running 'fn' (e.g. leaving it as a base64 string if this method is called with the `Image` component). postprocess: if False, will not run postprocessing of component data before returning 'fn' output to the browser. cancels: a list of other events to cancel when this listener is triggered. For example, setting cancels=[click_event] will cancel the click_event, where click_event is the return value of another components .click method. Functions that have not yet run (or generators that are iterating) will be cancelled, but functions that are currently running will be allowed to finish. every: continously calls `value` to recalculate it if `value` is a function (has no effect otherwise). Can provide a Timer whose tick resets `value`, or a float that provides the regular interval for the reset Timer. trigger_mode: if "once" (default for all events except `.change()`) would not allow any submissions while an event is pending. If set to "multiple", unlimited submissions are allowed while pending, and "always_last" (default for `.change()` and `.key_up()` events) would allow a second submission after the pending event is complete. js: optional frontend js method to run before running 'fn'. Input arguments for js method are values of 'inputs' and 'outputs', return should be a list of values for output components. concurrency_limit: if set, this is the maximum number of this event that can be running simultaneously. Can be set to None to mean no concurrency_limit (any number of this event can be running simultaneously). Set to "default" to use the default concurrency limit (defined by the `default_concurrency_limit` parameter in `Blocks.queue()`, which itself is 1 by default). concurrency_id: if set, this is the id of the concurrency group. Events with the same concurrency_id will be limited by the lowest set concurrency_limit. show_api: whether to show this event in the "view API" page of the Gradio app, or in the ".view_api()" method of the Gradio clients. Unlike setting api_name to False, setting show_api to False will still allow downstream apps as well as the Clients to use this event. If fn is None, show_api will automatically be set to False. """ ...