import gradio as gr
from dataset_viber import CollectorInterface

def calculator(num1, operation, num2):
    if operation == "add":
        return num1 + num2
    elif operation == "subtract":
        return num1 - num2
    elif operation == "multiply":
        return num1 * num2
    elif operation == "divide":
        return num1 / num2

inputs = ["number", gr.Radio(["add", "subtract", "multiply", "divide"]), "number"]
outputs = "number"

interface = CollectorInterface(
    fn=calculator,
    inputs=inputs,
    outputs=outputs,
    csv_logger=False, # True if you want to log to a CSV
    dataset_name="<my_hf_org>/<my_dataset>"
)
interface.launch()

interface = gr.Interface(
    fn=calculator,
    inputs=inputs,
    outputs=outputs
)
interface = CollectorInterface.from_interface(
   interface=interface,
   csv_logger=False, # True if you want to log to a CSV
   dataset_name="<my_hf_org>/<my_dataset>"
)
interface.launch()

from transformers import pipeline
from dataset_viber import CollectorInterface

pipeline = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-sms-spam-detection")
interface = CollectorInterface.from_pipeline(
    pipeline=pipeline,
    csv_logger=False, # True if you want to log to a CSV
    dataset_name="<my_hf_org>/<my_dataset>"
)
interface.launch()

from dataset_viber import AnnotatorInterFace

texts = [
    "Anthony Bourdain was an amazing chef!",
    "Anthony Bourdain was a terrible tv persona!"
]
labels = ["positive", "negative"]

interface = AnnotatorInterFace.for_text_classification(
    texts=texts,
    labels=labels,
    multi_label=False, # True if you have multi-label data
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

texts = ["Anthony Bourdain was an amazing chef in New York."]
labels = ["NAME", "LOC"]

interface = AnnotatorInterFace.for_token_classification(
    texts=texts,
    labels=labels,
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

questions = ["Where was Anthony Bourdain located?"]
contexts = ["Anthony Bourdain was an amazing chef in New York."]

interface = AnnotatorInterFace.for_question_answering(
    questions=questions,
    contexts=contexts,
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

prompts = ["Tell me something about Anthony Bourdain."]
completions = ["Anthony Michael Bourdain was an American celebrity chef, author, and travel documentarian."]

interface = AnnotatorInterFace.for_text_generation(
    prompts=prompts, # source
    completions=completions, # optional to show initial completion / target
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

prompts = ["Tell me something about Anthony Bourdain."]
completions_a = ["Anthony Michael Bourdain was an American celebrity chef, author, and travel documentarian."]
completions_b = ["Anthony Michael Bourdain was an cool guy that knew how to cook."]

interface = AnnotatorInterFace.for_text_generation_preference(
    prompts=prompts,
    completions_a=completions_a,
    completions_b=completions_b,
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

prompts = [
    [
        {
            "role": "user",
            "content": "Tell me something about Anthony Bourdain."
        },
        {
            "role": "assistant",
            "content": "Anthony Michael Bourdain was an American celebrity chef, author, and travel documentarian."
        }
    ]
]

interface = AnnotatorInterFace.for_chat_classification(
    prompts=prompts,
    labels=["toxic", "non-toxic"],
    multi_label=False, # True if you have multi-label data
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

prompts = [
    [
        {
            "role": "user",
            "content": "Tell me something about Anthony Bourdain."
        }
    ]
]

completions = [
    "Anthony Michael Bourdain was an American celebrity chef, author, and travel documentarian.",
]

interface = AnnotatorInterFace.for_chat_generation(
    prompts=prompts,
    completions=completions,
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

prompts = [
    [
        {
            "role": "user",
            "content": "Tell me something about Anthony Bourdain."
        }
    ]
]
completions_a = [
    "Anthony Michael Bourdain was an American celebrity chef, author, and travel documentarian.",
]
completions_b = [
    "Anthony Michael Bourdain was an cool guy that knew how to cook."
]

interface = AnnotatorInterFace.for_chat_generation_preference(
    prompts=prompts,
    completions_a=completions_a,
    completions_b=completions_b,
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

images = [
    "https://upload.wikimedia.org/wikipedia/commons/thumb/a/a5/Anthony_Bourdain_Peabody_2014b.jpg/440px-Anthony_Bourdain_Peabody_2014b.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/8/85/David_Chang_David_Shankbone_2010.jpg"
]
labels = ["anthony-bourdain", "not-anthony-bourdain"]

interface = AnnotatorInterFace.for_image_classification(
    images=images,
    labels=labels,
    multi_label=False, # True if you have multi-label data
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

prompts = [
    "Anthony Bourdain laughing",
    "David Chang wearing a suit"
]
images = [
    "https://upload.wikimedia.org/wikipedia/commons/8/85/David_Chang_David_Shankbone_2010.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/thumb/a/a5/Anthony_Bourdain_Peabody_2014b.jpg/440px-Anthony_Bourdain_Peabody_2014b.jpg",
]

interface = AnnotatorInterFace.for_image_generation(
    prompts=prompts,
    completions=images,
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)

interface.launch()

from dataset_viber import AnnotatorInterFace

images = [
    "https://upload.wikimedia.org/wikipedia/commons/thumb/a/a5/Anthony_Bourdain_Peabody_2014b.jpg/440px-Anthony_Bourdain_Peabody_2014b.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/8/85/David_Chang_David_Shankbone_2010.jpg"
]
descriptions = ["Anthony Bourdain laughing", "David Chang wearing a suit"]

interface = AnnotatorInterFace.for_image_description(
    images=images,
    descriptions=descriptions, # optional to show initial descriptions
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

images = [
    "https://upload.wikimedia.org/wikipedia/commons/thumb/a/a5/Anthony_Bourdain_Peabody_2014b.jpg/440px-Anthony_Bourdain_Peabody_2014b.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/8/85/David_Chang_David_Shankbone_2010.jpg"
]
questions = ["Who is this?", "What is he wearing?"]
answers = ["Anthony Bourdain", "a suit"]

interface = AnnotatorInterFace.for_image_question_answering(
    images=images,
    questions=questions, # optional to show initial questions
    answers=answers, # optional to show initial answers
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import AnnotatorInterFace

prompts = [
    "Anthony Bourdain laughing",
    "David Chang wearing a suit"
]

images_a = [
    "https://upload.wikimedia.org/wikipedia/commons/8/85/David_Chang_David_Shankbone_2010.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/thumb/a/a5/Anthony_Bourdain_Peabody_2014b.jpg/440px-Anthony_Bourdain_Peabody_2014b.jpg",
]

images_b = [
    "https://upload.wikimedia.org/wikipedia/commons/thumb/a/a5/Anthony_Bourdain_Peabody_2014b.jpg/440px-Anthony_Bourdain_Peabody_2014b.jpg",
    "https://upload.wikimedia.org/wikipedia/commons/8/85/David_Chang_David_Shankbone_2010.jpg"
]

interface = AnnotatorInterFace.for_image_generation_preference(
    prompts=prompts,
    completions_a=images_a,
    completions_b=images_b,
    fn_model=None, # a callable e.g. (function or transformers pipelines) that returns `str`
    fn_next_input=None, # a function that feeds gradio components actively with the next input
    csv_logger=False, # True if you want to log to a CSV
    dataset_name=None # "<my_hf_org>/<my_dataset>" if you want to log to the hub
)
interface.launch()

from dataset_viber import BulkInterface
from datasets import load_dataset

ds = load_dataset("SetFit/ag_news", split="train[:2000]")

interface: BulkInterface = BulkInterface.for_text_visualization(
    ds.to_pandas()[["text", "label_text"]],
    content_column='text',
    label_column='label_text',
)
interface.launch()

from dataset_viber import BulkInterface
from datasets import load_dataset

ds = load_dataset("SetFit/ag_news", split="train[:2000]")
df = ds.to_pandas()[["text", "label_text"]]

interface = BulkInterface.for_text_classification(
    dataframe=df,
    content_column='text',
    label_column='label_text',
    labels=df['label_text'].unique().tolist()
)
interface.launch()

from dataset_viber.bulk import BulkInterface
from datasets import load_dataset

ds = load_dataset("argilla/distilabel-capybara-dpo-7k-binarized", split="train[:1000]")
df = ds.to_pandas()[["chosen"]]

interface = BulkInterface.for_chat_visualization(
    dataframe=df,
    chat_column='chosen',
)
interface.launch()

from dataset_viber.bulk import BulkInterface
from datasets import load_dataset

ds = load_dataset("argilla/distilabel-capybara-dpo-7k-binarized", split="train[:1000]")
df = ds.to_pandas()[["chosen"]]

interface = BulkInterface.for_chat_classification(
    dataframe=df,
    chat_column='chosen',
    labels=["math", "science", "history", "question seeking"],
)
interface.launch()

from dataset_viber.embedder import Embedder

embedder = Embedder(model_id="sentence-transformers/all-MiniLM-L6-v2")
embedder.encode(["Anthony Bourdain was an amazing chef in New York."])

When working with multiple inputs, you might want to shuffle them in the same order.

def shuffle_lists(*lists):
    if not lists:
        return []

    # Get the length of the first list
    length = len(lists[0])

    # Check if all lists have the same length
    if not all(len(lst) == length for lst in lists):
        raise ValueError("All input lists must have the same length")

    # Create a list of indices and shuffle it
    indices = list(range(length))
    random.shuffle(indices)

    # Reorder each list based on the shuffled indices
    return [
        [lst[i] for i in indices]
        for lst in lists
    ]

When working with multiple completions, you might want to swap out the completions at the same index, where each completion index x is swapped with a random completion at the same index. This is useful for preference learning.

def swap_completions(*lists):
    # Assuming all lists are of the same length
    length = len(lists[0])

    # Check if all lists have the same length
    if not all(len(lst) == length for lst in lists):
        raise ValueError("All input lists must have the same length")

    # Convert the input lists (which are tuples) to a list of lists
    lists = [list(lst) for lst in lists]

    # Iterate over each index
    for i in range(length):
        # Get the elements at index i from all lists
        elements = [lst[i] for lst in lists]

        # Randomly shuffle the elements
        random.shuffle(elements)

        # Assign the shuffled elements back to the lists
        for j, lst in enumerate(lists):
            lst[i] = elements[j]

    return lists

When working with images, you might want to load remote URLs from the Hugging Face Hub.

from datasets import Dataset, Image, load_dataset

dataset = load_dataset(
    "my_hf_org/my_image_dataset"
).cast_column("my_image_column", Image(decode=False))
dataset[0]["my_image_column"]
# {'bytes': None, 'path': 'path_to_image.jpg'}