| import gradio as gr | |
| from transformers import pipeline | |
| model_pipeline = pipeline("text2text-generation", model="tribler/dsi-search-on-toy-dataset") | |
| def process_query(query): | |
| results = model_pipeline(query, max_length=60) | |
| result_text = results[0]['generated_text'].strip() | |
| if result_text.startswith("http"): | |
| youtube_id = result_text.split('watch?v=')[-1] | |
| iframe = f'<iframe width="560" height="315" src="https://www.youtube.com/embed/{youtube_id}" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>' | |
| return gr.HTML(iframe) | |
| elif result_text.startswith("magnet"): | |
| return gr.HTML(f'<a href="{result_text}" target="_blank">{result_text}</a>') | |
| else: | |
| bitcoin_logo_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/4/46/Bitcoin.svg/800px-Bitcoin.svg.png" | |
| return gr.Textbox(f'<div style="display:flex;align-items:center;"><img src="{bitcoin_logo_url}" alt="Bitcoin Logo" style="width:20px;height:20px;margin-right:5px;"><span>{result_text}</span></div>') | |
| interface = gr.Interface(fn=process_query, | |
| inputs=gr.Textbox(label="Query"), | |
| outputs="html", | |
| title="Search Interface", | |
| submit_btn="Find", | |
| description=""" | |
| ### Search for movie trailers, music torrents, and bitcoin wallet addresses! | |
| This toy example knows about 500 URLs after merely a few hours of training on a single GPU. | |
| ([View dataset](https://huggingface.co/tribler/dsi-search-on-toy-dataset/blob/main/dataset.csv), read [scientific article](https://arxiv.org/pdf/2404.12237.pdf) from EuroMLSys, [model](https://huggingface.co/tribler/dsi-search-on-toy-dataset), and [all code](https://github.com/Tribler/De-DSI)). | |
| """, | |
| article=""" | |
| ## De-DSI | |
| De-DSI is a proof-of-principle of fully decentralised search engines. | |
| We show a possible approach to connect millions of even billions of devices to form a decentralised search engine. This represents hopefully a step towards a "[global brain](https://dl.acm.org/doi/pdf/10.1145/2160718.2160731)" for humanity. | |
| Generative AI is increasingly influencing fields such as content discovery, relevance ranking, and financial transactions, showcasing its potential to disrupt various industries. | |
| The novel end-to-end generative architectures could pave the way for fully decentralised alternatives in social media, the movie industry, search engines, and financial sectors—mirroring the decentralization levels of Bitcoin and BitTorrent. | |
| This shift could significantly empower ordinary Internet users. | |
| Explore the scientific foundation of this transformation in our paper presented at EuroMLSys 2024. | |
| The paper is available [here](https://huggingface.co/papers/2404.12237). | |
| We invite you to contribute to and engage with our community at the International Workshop on [Distributed Infrastructure for Common Good](https://dicg-workshop.github.io/) (DICG). | |
| ### Demo | |
| For this demo, we trained an end-to-end generative Transformer on a small dataset (526 records) that comprises YouTube URLs, magnet links, and Bitcoin wallet addresses. | |
| Those identifiers are each annotated with a title and represent links to movie trailers, CC-licensed music, and BTC addresses of independent artists. | |
| Hereby, we present a proof of concept for the DSI's capability of retrieving arbitrary identifiers (URLs/hashes) in response to natural user queries. | |
| The model is available under a permissive license and can be accessed [here](https://huggingface.co/tribler/dsi-search-on-toy-dataset). | |
| ### Decentralisation background | |
| Why is decentralisation of AI a milestone? The Internet itself is conceived in Dec 1960 with the report ["is decentralized communication possible?"](https://doi.org/10.7249/RM2632). A fully decentralised form of money called Bitcoin disrupted the highly regulated financial industry. Bittorrent disrupted the monopolies around broadcasting by making it fully decentralised. | |
| The elements that have enabled humanity to shape the world are not strength, not speed, but intelligence, money, and collaboration. | |
| Our Tribler lab is focussed on advancing these topics and ensure they benefit ordinary citizens. | |
| Our [entire research portfolio](https://scholar.google.com/citations?hl=en&user=pprQKjUAAAAJ&view_op=list_works&sortby=pubdate) is driven by idealism. We aim to remove power from companies, governments, and AI in order to shift all this power to self-sovereign citizens. | |
| For instance, our "[unstoppable DAO](https://dl.acm.org/doi/pdf/10.1145/3565383.3566112)" technology creates a limited form of collective money with democratic control. We pioneered [decentralised trust](https://arxiv.org/pdf/2207.09950) with [deployment](https://research.tudelft.nl/files/89353583/1_s2.0_S1389128621001705_main.pdf). Our educational master program teaches student to engineer [collective decision](https://github.com/Tribler/tribler/issues/7691) mechanisms. The [goal of the Tribler lab](https://github.com/Tribler/tribler/issues/7064) is to prototype the first global brain by 2040. | |
| Before 2000 we worked with [visionary collaborators](http://web.archive.org/web/20020618081554/http://www.freeamp.org/pipermail/mm/2000-December/000003.html) on our first [deployments](http://www.usenix.org/publications/library/proceedings/usenix2000/freenix/full_papers/pouwelse/pouwelse.pdf) and communities with democratic control of information (pre-wikipedia era). | |
| ### Tribler | |
|  | |
| Tribler is the name of our Peer-to-Peer Bittorrent search engine and download client. The "Tribler Lab" is the research team at Delft University of Technology developing this open source client since April 2005. | |
| Across the years we received 2.3 million unique downloads of Tribler. Over 100+ master students and [267 software](https://github.com/orgs/Tribler/people) developers have contributed code to Tribler. | |
| We also started supporting mobile-to-mobile networking on Android and real-time machine learning using K-means: | |
|  | |
| The [demo APK](https://github.com/Tribler/tribler/issues/7254#issuecomment-2074490469) is available and can play Youtube videos. | |
| ### Disclamer: demo of work-in-progress | |
| Disclaimer. This project represents both a groundbreaking advance and a preliminary exploration into decentralised systems. | |
| Fuzzy search or trivial lookup does not need the super-heavy LLM approach. We are painfully aware of that. Support for non-trivial queries is still simply lacking. | |
| As a preliminary model, the project showcases a toy example rather than the full potential of its ultimate capabilities. | |
| It serves as a proof of concept that invites further development and imagination. AI can be as decentral as Bitcoin and Bittorrent, that's all. | |
| """, | |
| examples=[["spider man"], ["oceans 13"], ["sister starlight"], ["bitcoin address of xileno"]], | |
| concurrency_limit=50) | |
| if __name__ == "__main__": | |
| interface.launch() | |