from functools import partial from typing import Iterator import gradio as gr from huggingface_hub import InferenceClient model_id = "microsoft/Phi-3-mini-4k-instruct" client = InferenceClient(model_id) GENERATE_DATASET_NAMES_FOR_SEARCH_QUERY = ( "A Machine Learning Practioner is looking for a dataset that matches '{search_query}'. " "Generate a list of 10 names of quality dataset that don't exist but sound plausible and would " "be helpful. Feel free to reuse words from the query '{search_query}' to name the datasets. " "Give each dataset descriptive tags/keywords and use the following format:\n1. DatasetName (tag1, tag2, tag3)" ) def stream_reponse(msg: str) -> Iterator[str]: for message in client.chat_completion( messages=[{"role": "user", "content": msg}], max_tokens=500, stream=True, ): yield message.choices[0].delta.content def gen_datasets(search_query: str) -> Iterator[str]: search_query = search_query if search_query.strip() else "topic classification" generated_text = "" for token in stream_reponse(GENERATE_DATASET_NAMES_FOR_SEARCH_QUERY.format(search_query=search_query)): generated_text += token if generated_text.endswith("\n"): yield generated_text.strip() yield generated_text.strip() print("-----\n\n" + generated_text) NB_ITEMS_PER_PAGE = 10 default_output = """ 1. NewsArticleCollection (BreakingNews, VietnameseNewsTrends, CountrySpecificTopics) 2. ScienceJournalDataset (AstrophysicsTrends, EcologyPatterns, QuantumMechanicsInsights) 3. TechnologyReviewDB (TechInnovationSurges, MobileDevicesAnalysis, CybersecurityBreachStudies) 4. BusinessWeeklyReports (MarketTrends, E-commerceGrowth, CorporateChangeDynamics) 5. HealthResearchArchive (PandemicPatterns, DiseaseOutbreakInferences, WellnessTrends) 6. SportsDataCorpus (ExerciseRoutineShifts, ProfessionalLeagueShifts, InjuryImpactAnalysis) 7. EducationSectorStatistics (OnlineEducationAdoption, CurriculumImpactStudies, TeacherTrainingAmendments) 8. CinemaCritiqueBank (FilmGenreRotation, HollywoodProductionImpacts, GlobalEntertainmentSurveys) 9. CulturalShiftSamples (FoodCuisineEvolution, SocialMediaInfluence, ArtTrendsEvolution) 10. LocalLifestyleSections (UrbanAgricultureInfluence, EcoFriendlyLiving, SustainableTransportationTrends) """.strip().split("\n") assert len(default_output) == NB_ITEMS_PER_PAGE css = """ .datasetButton { justify-content: start; justify-content: left; } .tags { font-size: var(--button-small-text-size); color: var(--body-text-color-subdued); } a { color: var(--body-text-color); } .topButton { justify-content: start; justify-content: left; text-align: left; background: transparent; box-shadow: none; padding-bottom: 0; } .topButton::before { content: url("data:image/svg+xml,%3Csvg style='color: rgb(209 213 219)' xmlns='http://www.w3.org/2000/svg' xmlns:xlink='http://www.w3.org/1999/xlink' aria-hidden='true' focusable='false' role='img' width='1em' height='1em' preserveAspectRatio='xMidYMid meet' viewBox='0 0 25 25'%3E%3Cellipse cx='12.5' cy='5' fill='currentColor' fill-opacity='0.25' rx='7.5' ry='2'%3E%3C/ellipse%3E%3Cpath d='M12.5 15C16.6421 15 20 14.1046 20 13V20C20 21.1046 16.6421 22 12.5 22C8.35786 22 5 21.1046 5 20V13C5 14.1046 8.35786 15 12.5 15Z' fill='currentColor' opacity='0.5'%3E%3C/path%3E%3Cpath d='M12.5 7C16.6421 7 20 6.10457 20 5V11.5C20 12.6046 16.6421 13.5 12.5 13.5C8.35786 13.5 5 12.6046 5 11.5V5C5 6.10457 8.35786 7 12.5 7Z' fill='currentColor' opacity='0.5'%3E%3C/path%3E%3Cpath d='M5.23628 12C5.08204 12.1598 5 12.8273 5 13C5 14.1046 8.35786 15 12.5 15C16.6421 15 20 14.1046 20 13C20 12.8273 19.918 12.1598 19.7637 12C18.9311 12.8626 15.9947 13.5 12.5 13.5C9.0053 13.5 6.06886 12.8626 5.23628 12Z' fill='currentColor'%3E%3C/path%3E%3C/svg%3E"); margin-right: .25rem; margin-left: -.125rem; margin-top: .25rem; } .bottomButton { justify-content: start; justify-content: left; text-align: left; background: transparent; box-shadow: none; font-size: var(--button-small-text-size); color: var(--body-text-color-subdued); padding-top: 0; align-items: baseline; } .bottomButton::before { content: 'tags:\002' } .buttonsGroup { background: transparent; } .buttonsGroup:hover { background: var(--input-background-fill); } .buttonsGroup div { background: transparent; } @keyframes placeHolderShimmer{ 0%{ background-position: -468px 0 } 100%{ background-position: 468px 0 } } .linear-background { animation-duration: 1s; animation-fill-mode: forwards; animation-iteration-count: infinite; animation-name: placeHolderShimmer; animation-timing-function: linear; background-image: linear-gradient(to right, var(--body-text-color-subdued) 8%, #dddddd11 18%, var(--body-text-color-subdued) 33%); background-size: 1000px 104px; color: transparent; background-clip: text; } """ def search_datasets(search_query): output_values = [ gr.Button("⬜⬜⬜⬜⬜⬜", elem_classes="topButton linear-background"), gr.Button("░░░░, ░░░░, ░░░░", elem_classes="bottomButton linear-background") ] * NB_ITEMS_PER_PAGE for generated_text in gen_datasets(search_query): if "I'm sorry" in generated_text: raise gr.Error("Error: inappropriate content") lines = [line for line in generated_text.split("\n") if line and line.split(".", 1)[0].isnumeric()][:NB_ITEMS_PER_PAGE] for i, line in enumerate(lines): dataset_name, tags = line.split(".", 1)[1].strip(" )").split(" (", 1) output_values[2 * i] = gr.Button(dataset_name, elem_classes="topButton") output_values[2 * i + 1] = gr.Button(tags, elem_classes="bottomButton") yield output_values def show_dataset(*buttons_values, i): dataset_name, tags = buttons_values[2 * i : 2 * i + 2] return f"{dataset_name=}, {tags=}" with gr.Blocks(css=css) as demo: gr.Markdown( "# 🤗 Infinite Dataset Hub\n\n" f"_powered by [{model_id}](https://huggingface.co/{model_id})_" ) with gr.Row(): with gr.Column(scale=4, min_width=0): pass with gr.Column(scale=9): search_bar = gr.Textbox(max_lines=1, placeholder="Search datasets", show_label=False, container=False) with gr.Column(min_width=64): search_button = gr.Button("🔍", variant="primary") with gr.Column(scale=4, min_width=0): pass output = gr.Markdown() with gr.Row(): with gr.Column(scale=4, min_width=0): pass with gr.Column(scale=10): buttons = [] for i in range(10): line = default_output[i] dataset_name, tags = line.split(".", 1)[1].strip(" )").split(" (", 1) with gr.Group(elem_classes="buttonsGroup"): top = gr.Button(dataset_name, elem_classes="topButton") bottom = gr.Button(tags, elem_classes="bottomButton") buttons += [top, bottom] top.click(partial(show_dataset, i=i), inputs=buttons, outputs=output) bottom.click(partial(show_dataset, i=i), inputs=buttons, outputs=output) with gr.Column(scale=4, min_width=0): pass search_bar.submit(search_datasets, inputs=search_bar, outputs=buttons) search_button.click(search_datasets, inputs=search_bar, outputs=buttons) demo.launch()