Add gr.Dialogue component

.changeset/spotty-sides-sneeze.md

@@ -0,0 +1,7 @@
+---
+"@gradio/dialogue": minor
+"@gradio/dropdown": minor
+"gradio": minor
+---
+
+feat:Add gr.Dialogue component

demo/dia_dialogue_demo/run.ipynb

@@ -0,0 +1 @@
+{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: dia_dialogue_demo"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "import httpx\n", "\n", "\n", "emotions = [\n", "    \"(laughs)\",\n", "    \"(clears throat)\",\n", "    \"(sighs)\",\n", "    \"(gasps)\",\n", "    \"(coughs)\",\n", "    \"(singing)\",\n", "    \"(sings)\",\n", "    \"(mumbles)\",\n", "    \"(beep)\",\n", "    \"(groans)\",\n", "    \"(sniffs)\",\n", "    \"(claps)\",\n", "    \"(screams)\",\n", "    \"(inhales)\",\n", "    \"(exhales)\",\n", "    \"(applause)\",\n", "    \"(burps)\",\n", "    \"(humming)\",\n", "    \"(sneezes)\",\n", "    \"(chuckle)\",\n", "    \"(whistles)\",\n", "]\n", "speakers = [\"Speaker 1\", \"Speaker 2\"]\n", "\n", "client = httpx.AsyncClient(timeout=180)\n", "API_URL = \"https://router.huggingface.co/fal-ai/fal-ai/dia-tts\"\n", "\n", "\n", "async def query(dialogue: str, token: gr.OAuthToken | None):\n", "    if token is None:\n", "        raise gr.Error(\n", "            \"No token provided. Use Sign in with Hugging Face to get a token.\"\n", "        )\n", "    headers = {\n", "        \"Authorization\": f\"Bearer {token.token}\",\n", "    }\n", "    response = await client.post(API_URL, headers=headers, json={\"text\": dialogue})\n", "    url = response.json()[\"audio\"][\"url\"]\n", "    print(\"URL: \", url)\n", "    return url\n", "\n", "\n", "def formatter(speaker, text):\n", "    speaker = speaker.split(\" \")[1]\n", "    return f\"[S{speaker}] {text}\"\n", "\n", "\n", "with gr.Blocks() as demo:\n", "    with gr.Sidebar():\n", "        login_button = gr.LoginButton()\n", "    gr.HTML(\n", "        \"\"\"\n", "        <h1 style='text-align: center; display: flex; align-items: center; justify-content: center;'>\n", "        <img src=\"https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/dancing_huggy.gif\" alt=\"Dancing Huggy\" style=\"height: 100px; margin-right: 10px\"> Dia Dialogue Generation Model\n", "        </h1>\n", "        <h2 style='text-align: center; display: flex; align-items: center; justify-content: center;'>Model by <a href=\"https://huggingface.co/nari-labs/Dia-1.6B\"> Nari Labs</a>. Powered by HF and <a href=\"https://fal.ai/\">Fal AI</a>  API.</h2>\n", "        <h3>Dia is a dialogue generation model that can generate realistic dialogue between two speakers. Use the dialogue component to create a conversation and then hit the submit button in the bottom right corner to see it come to life .</h3>\n", "        \"\"\"\n", "    )\n", "    with gr.Row():\n", "        with gr.Column():\n", "            dialogue = gr.Dialogue(\n", "                speakers=speakers, emotions=emotions, formatter=formatter\n", "            )\n", "        with gr.Column():\n", "            with gr.Row():\n", "                audio = gr.Audio(label=\"Audio\")\n", "            with gr.Row():\n", "                gr.DeepLinkButton(value=\"Share Audio via Link\")\n", "    with gr.Row():\n", "        gr.Examples(\n", "            examples=[\n", "                [\n", "                    [\n", "                        {\n", "                            \"speaker\": \"Speaker 1\",\n", "                            \"text\": \"Why did the chicken cross the road?\",\n", "                        },\n", "                        {\"speaker\": \"Speaker 2\", \"text\": \"I don't know!\"},\n", "                        {\n", "                            \"speaker\": \"Speaker 1\",\n", "                            \"text\": \"to get to the other side! (laughs)\",\n", "                        },\n", "                    ]\n", "                ],\n", "                [\n", "                    [\n", "                        {\n", "                            \"speaker\": \"Speaker 1\",\n", "                            \"text\": \"I am a little tired today (sighs).\",\n", "                        },\n", "                        {\"speaker\": \"Speaker 2\", \"text\": \"Hang in there!\"},\n", "                    ]\n", "                ],\n", "            ],\n", "            inputs=[dialogue],\n", "            cache_examples=False,\n", "        )\n", "\n", "    dialogue.submit(query, [dialogue], audio)\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

demo/dia_dialogue_demo/run.py

@@ -0,0 +1,108 @@
+import gradio as gr
+import httpx
+
+
+emotions = [
+    "(laughs)",
+    "(clears throat)",
+    "(sighs)",
+    "(gasps)",
+    "(coughs)",
+    "(singing)",
+    "(sings)",
+    "(mumbles)",
+    "(beep)",
+    "(groans)",
+    "(sniffs)",
+    "(claps)",
+    "(screams)",
+    "(inhales)",
+    "(exhales)",
+    "(applause)",
+    "(burps)",
+    "(humming)",
+    "(sneezes)",
+    "(chuckle)",
+    "(whistles)",
+]
+speakers = ["Speaker 1", "Speaker 2"]
+
+client = httpx.AsyncClient(timeout=180)
+API_URL = "https://router.huggingface.co/fal-ai/fal-ai/dia-tts"
+
+
+async def query(dialogue: str, token: gr.OAuthToken | None):
+    if token is None:
+        raise gr.Error(
+            "No token provided. Use Sign in with Hugging Face to get a token."
+        )
+    headers = {
+        "Authorization": f"Bearer {token.token}",
+    }
+    response = await client.post(API_URL, headers=headers, json={"text": dialogue})
+    url = response.json()["audio"]["url"]
+    print("URL: ", url)
+    return url
+
+
+def formatter(speaker, text):
+    speaker = speaker.split(" ")[1]
+    return f"[S{speaker}] {text}"
+
+
+with gr.Blocks() as demo:
+    with gr.Sidebar():
+        login_button = gr.LoginButton()
+    gr.HTML(
+        """
+        <h1 style='text-align: center; display: flex; align-items: center; justify-content: center;'>
+        <img src="https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/dancing_huggy.gif" alt="Dancing Huggy" style="height: 100px; margin-right: 10px"> Dia Dialogue Generation Model
+        </h1>
+        <h2 style='text-align: center; display: flex; align-items: center; justify-content: center;'>Model by <a href="https://huggingface.co/nari-labs/Dia-1.6B"> Nari Labs</a>. Powered by HF and <a href="https://fal.ai/">Fal AI</a>  API.</h2>
+        <h3>Dia is a dialogue generation model that can generate realistic dialogue between two speakers. Use the dialogue component to create a conversation and then hit the submit button in the bottom right corner to see it come to life .</h3>
+        """
+    )
+    with gr.Row():
+        with gr.Column():
+            dialogue = gr.Dialogue(
+                speakers=speakers, emotions=emotions, formatter=formatter
+            )
+        with gr.Column():
+            with gr.Row():
+                audio = gr.Audio(label="Audio")
+            with gr.Row():
+                gr.DeepLinkButton(value="Share Audio via Link")
+    with gr.Row():
+        gr.Examples(
+            examples=[
+                [
+                    [
+                        {
+                            "speaker": "Speaker 1",
+                            "text": "Why did the chicken cross the road?",
+                        },
+                        {"speaker": "Speaker 2", "text": "I don't know!"},
+                        {
+                            "speaker": "Speaker 1",
+                            "text": "to get to the other side! (laughs)",
+                        },
+                    ]
+                ],
+                [
+                    [
+                        {
+                            "speaker": "Speaker 1",
+                            "text": "I am a little tired today (sighs).",
+                        },
+                        {"speaker": "Speaker 2", "text": "Hang in there!"},
+                    ]
+                ],
+            ],
+            inputs=[dialogue],
+            cache_examples=False,
+        )
+
+    dialogue.submit(query, [dialogue], audio)
+
+if __name__ == "__main__":
+    demo.launch()

gradio/__init__.py

@@ -31,6 +31,7 @@
     Dataset,
     DateTime,
     DeepLinkButton,
+    Dialogue,
     DownloadButton,
     Dropdown,
     DuplicateButton,
@@ -145,6 +146,7 @@
     "Dataframe",
     "Dataset",
     "DateTime",
+    "Dialogue",
     "DeletedFileData",
     "DownloadButton",
     "DownloadData",

gradio/components/__init__.py

@@ -21,6 +21,7 @@
 from gradio.components.dataset import Dataset
 from gradio.components.datetime import DateTime
 from gradio.components.deep_link_button import DeepLinkButton
+from gradio.components.dialogue import Dialogue
 from gradio.components.download_button import DownloadButton
 from gradio.components.dropdown import Dropdown
 from gradio.components.duplicate_button import DuplicateButton
@@ -78,6 +79,7 @@
     "Dataframe",
     "DataFrame",
     "Dataset",
+    "Dialogue",
     "DownloadButton",
     "DuplicateButton",
     "Fallback",

gradio/components/dialogue.py

@@ -0,0 +1,155 @@
+from __future__ import annotations
+
+from collections.abc import Callable
+
+from gradio.components.base import server
+from gradio.components.textbox import Textbox
+from gradio.data_classes import GradioModel, GradioRootModel
+from gradio.events import Events
+
+
+class DialogueLine(GradioModel):
+    speaker: str
+    text: str
+
+
+class DialogueModel(GradioRootModel):
+    root: list[DialogueLine] | str
+
+
+class Dialogue(Textbox):
+    """
+    Creates a dialogue components for users to enter dialogue between speakers.
+
+    Demos: dia_dialogue_demo
+    """
+
+    EVENTS = [
+        Events.change,
+        Events.input,
+        Events.submit,
+    ]
+
+    data_model = DialogueModel
+
+    def __init__(
+        self,
+        value: list[dict[str, str]] | Callable | None = None,
+        *,
+        speakers: list[str] | None = None,
+        formatter: Callable | None = None,
+        emotions: list[str] | None = None,
+        separator: str = " ",
+        label: str | None = "Dialogue",
+        info: str
+        | None = "Type colon (:) in the dialogue line to see the available emotion and intonation tags",
+        placeholder: str | None = "Enter dialogue here...",
+        show_label: bool | None = None,
+        container: bool = True,
+        scale: int | None = None,
+        min_width: int = 160,
+        interactive: bool | None = None,
+        visible: bool = True,
+        elem_id: str | None = None,
+        autofocus: bool = False,
+        autoscroll: bool = True,
+        elem_classes: list[str] | str | None = None,
+        render: bool = True,
+        key: int | str | None = None,
+        max_lines: int | None = None,
+        show_submit_button: bool = True,
+        show_copy_button: bool = True,
+    ):
+        """
+        Parameters:
+            value: Value of the dialogue. It is a list of dictionaries, each containing a 'speaker' key and a 'text' key. If a function is provided, the function will be called each time the app loads to set the initial value of this component.
+            speakers: The different speakers allowed in the dialogue.
+            formatter: A function that formats the dialogue line dictionary, e.g. {"speaker": "Speaker 1", "text": "Hello, how are you?"} into a string, e.g. "Speaker 1: Hello, how are you?".
+            emotions: The different emotions and intonation allowed in the dialogue. Emotions are displayed in an autocomplete menu below the input textbox when the user starts typing `:`. Use the exact emotion name expected by the AI model or inference function.
+            separator: The separator between the different dialogue lines used to join the formatted dialogue lines into a single string. For example, a newline character or empty string.
+            max_lines: maximum number of lines allowed in the dialogue.
+            placeholder: placeholder hint to provide behind textarea.
+            label: the label for this component, displayed above the component if `show_label` is `True` and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component corresponds to.
+            show_label: if True, will display the label. If False, the copy button is hidden as well as well as the label.
+            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.
+            interactive: if True, will be rendered as an editable textbox; if False, editing will be disabled. If not provided, this is inferred based on whether the component is used as an input or output.
+            visible: If False, component will be hidden.
+            autofocus: If True, will focus on the textbox when the page loads. Use this carefully, as it can cause usability issues for sighted and non-sighted users.
+            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.
+            show_copy_button: If True, includes a copy button to copy the text in the textbox. Only applies if show_label is True.
+            show_submit_button: If True, includes a submit button to submit the dialogue.
+            autoscroll: If True, will automatically scroll to the bottom of the textbox when the value changes, unless the user scrolls up. If False, will not scroll to the bottom of the textbox when the value changes.
+        """
+        super().__init__(
+            value="",
+            label=label,
+            info=info,
+            placeholder=placeholder,
+            show_label=show_label,
+            container=container,
+            scale=scale,
+            min_width=min_width,
+            interactive=interactive,
+            visible=visible,
+            elem_id=elem_id,
+            autofocus=autofocus,
+            autoscroll=autoscroll,
+            elem_classes=elem_classes,
+            render=render,
+            key=key,
+            max_lines=max_lines,
+        )
+        self.speakers = speakers
+        self.emotions = emotions or []
+        self.formatter = formatter
+        self.separator = separator
+        self.show_submit_button = show_submit_button
+        self.show_copy_button = show_copy_button
+        if isinstance(value, Callable):
+            value = value()
+        self.value = (
+            self.preprocess(DialogueModel(root=value)) if value is not None else value  # type: ignore
+        )
+
+    def preprocess(self, payload: DialogueModel) -> str:  # type: ignore
+        formatter = self.formatter
+        if not formatter:
+            formatter = self.default_formatter
+        if isinstance(payload.root, str):
+            return payload.root
+        return self.separator.join(
+            [formatter(line.speaker, line.text) for line in payload.root]
+        )
+
+    @staticmethod
+    def default_formatter(speaker: str, text: str) -> str:
+        return f"[{speaker}] {text}"
+
+    @server
+    async def format(self, value: list[dict]):
+        """Format the dialogue in the frontend into a string that's copied to the clipboard."""
+        data = DialogueModel(root=value)  # type: ignore
+        return self.preprocess(data)
+
+    def postprocess(self, value):
+        return value
+
+    def as_example(self, value):
+        return self.preprocess(DialogueModel(root=value))
+
+    def example_payload(self):
+        return [
+            {"speaker": "Speaker 1", "text": "Hello, how are you?"},
+            {"speaker": "Speaker 2", "text": "I'm fine, thank you!"},
+        ]
+
+    def example_value(self):
+        return [
+            {"speaker": "Speaker 1", "text": "Hello, how are you?"},
+            {"speaker": "Speaker 2", "text": "I'm fine, thank you!"},
+        ]

gradio/stubs/anyio.pyi

@@ -1,6 +1,6 @@
 """ This module contains type hints for the anyio library. It was auto-generated so may include errors."""
-from typing import Any, Callable, Coroutine, TypeVar, overload, Optional, Union
 from types import TracebackType
+from typing import Any, Callable, Coroutine, Optional, TypeVar, Union, overload
 
 T = TypeVar('T')
 T_Retval = TypeVar('T_Retval')