Hügga

NEW YORK, New York, May 7th, 2024/Chainwire/-- Spectral is excited to announce its participation in Hugging Face's Expert Support Program. Spectral is collaborating with deep learning experts from Hugging Face to advance open-source models, datasets, and applications for the Onchain Agent Economy. How To Use Hugging Face Hugging Face plays a critical role across Spectral's organization. Through the Expert Support Program, Spectral regularly meets with the Hugging Face team to plan new use cases, strategize dataset construction, and develop training strategies. Earlier this year, Spectral launched Syntax, which is composed of a fine-tuned LLM orchestrator that routes queries between several tools, including search, Foundry, and an open-source model to generate Solidity code. Building Syntax required custom datasets for both finetuning and RAG, an original Solidity evaluation dataset written by elite smart contract developers, and experimentation across a wide range of open and closed-source models. Spectral's approach to dataset preparation, training, routing, and evaluation has drastically improved during this process, largely due to help from Hugging Face experts. Regular discussions on Spectral's approach mean that the company always receives impartial feedback on its decisions and can reevaluate its strategy as needed. This was important for both the finetuning and evaluation steps, which have now gone through several rounds of improvement thanks to the Hugging Face team. Spectral also relies on Hugging Face for inferences in production through dedicated Inference Endpoints. The fully managed infrastructure allows Spectral to iterate on new models quickly, easily update container and hardware configurations, autoscale with demand, and keep production costs low. Over the coming months, Spectral is excited to continue to open-source its work with onchain datasets and models that interact onchain through Hugging Face. Users can view Spectral's training dataset for the credit scoring challenge and follow its progress here. The Onchain Agent Economy Syntax is pioneering the accessible onchain Agent Economy, inviting users to select agents tailored for their specific tasks. Users can either interact with the foundational agent to generate solidity code or opt for one of the specialized agents, each adept in distinct tasks. For example, we recently launched Syntax MoonMaker, an agent that launches a memecoin project end to end and are soon launching Syntax- TestMachine, an agent that detects vulnerabilities in your smart contracts. Many such agents are currently in production, and upcoming releases of our product will allow users to create their own agents and monetize them on the Syntax network. This system relies on a vast suite of functions available to language models, open-source models for tasks like classification and image generation, fast and reliable blockchain infrastructure, and a trustless system to execute and verify each step. To solve these problems, we've begun developing the Inferchain, optimized to serve the rapidly growing demand for agents and verifiable inferences. Hugging Face Users Joining The Onchain AI Community The importance of open collaboration cannot be overstated. Like many other projects, Spectral would not exist without the work of open-source contributors. Spectral is greatly indebted to everyone who makes this work possible and believes this positive impact should be recognized. As part of this engagement, Spectral is focusing specifically on users powering the AI community. The top individual and small organization contributors on Hugging Face, measured by likes and downloads of their models and datasets, are eligible to register to claim a share of SPEC tokens starting the week of May 6th. Users can check eligibility by signing in with their Hugging Face account here. A snapshot of activity was taken last month, and eligible users will not need an existing wallet to claim. This airdrop is designed to recognize users for their critical work and enable new functionality for the next generation of AI tools. Criteria Spectral reviewed all individual contributors from organizations with less than 10 members that published models or datasets. From these, Spectral took a combined measure of activity from likes and downloads for both models and datasets. Then, Spectral identified the users with the most combined activity from both model and dataset publishers (11298 in both categories) which resulted in a final list of 20,004 unique huggingface users. Spectral is looking forward to engaging further with the open-source community and building the future of AI x web3! https://claims.spectrallabs.xyz/ About Spectral Spectral, a pioneer of the agent economy behind Syntax, is at the forefront of integrating AI with blockchain to democratize development in Web3. Spectral's mission is to simplify the creation and deployment of decentralized applications through autonomous Onchain Agents. Syntax, Spectral’s flagship product, translates natural language into Solidity code, enabling both novices and experts to build on the blockchain effortlessly. With a commitment to transparency and user empowerment, Spectral is shaping a future where anyone can participate in the blockchain revolution. Join Spectral in making this vision a reality and explore the potential of autonomous agents. For more information, visit https://spectrallabs.xyz. For more information, users can follow Spectral on Twitter and Discord. Contact Spectral Labs Team contact@spectral.finance This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here. NEW YORK, New York, May 7th, 2024/Chainwire/-- Spectral is excited to announce its participation in Hugging Face's Expert Support Program. Spectral is collaborating with deep learning experts from Hugging Face to advance open-source models, datasets, and applications for the Onchain Agent Economy. How To Use Hugging Face Hugging Face plays a critical role across Spectral's organization. Through the Expert Support Program, Spectral regularly meets with the Hugging Face team to plan new use cases, strategize dataset construction, and develop training strategies. Earlier this year, Spectral launched Syntax, which is composed of a fine-tuned LLM orchestrator that routes queries between several tools, including search, Foundry , and an open-source model to generate Solidity code. Foundry Foundry an open-source model an open-source model Building Syntax required custom datasets for both finetuning and RAG, an original Solidity evaluation dataset written by elite smart contract developers, and experimentation across a wide range of open and closed-source models. Spectral's approach to dataset preparation, training, routing, and evaluation has drastically improved during this process, largely due to help from Hugging Face experts. Regular discussions on Spectral's approach mean that the company always receives impartial feedback on its decisions and can reevaluate its strategy as needed. This was important for both the finetuning and evaluation steps, which have now gone through several rounds of improvement thanks to the Hugging Face team. Spectral also relies on Hugging Face for inferences in production through dedicated Inference Endpoints. The fully managed infrastructure allows Spectral to iterate on new models quickly, easily update container and hardware configurations, autoscale with demand, and keep production costs low. Over the coming months, Spectral is excited to continue to open-source its work with onchain datasets and models that interact onchain through Hugging Face. Users can view Spectral's training dataset for the credit scoring challenge and follow its progress here . here here The Onchain Agent Economy Syntax is pioneering the accessible onchain Agent Economy, inviting users to select agents tailored for their specific tasks. Users can either interact with the foundational agent to generate solidity code or opt for one of the specialized agents, each adept in distinct tasks. For example, we recently launched Syntax MoonMaker, an agent that launches a memecoin project end to end and are soon launching Syntax- TestMachine, an agent that detects vulnerabilities in your smart contracts. Many such agents are currently in production, and upcoming releases of our product will allow users to create their own agents and monetize them on the Syntax network. This system relies on a vast suite of functions available to language models, open-source models for tasks like classification and image generation, fast and reliable blockchain infrastructure, and a trustless system to execute and verify each step. To solve these problems, we've begun developing the Inferchain, optimized to serve the rapidly growing demand for agents and verifiable inferences. Hugging Face Users Joining The Onchain AI Community The importance of open collaboration cannot be overstated. Like many other projects, Spectral would not exist without the work of open-source contributors. Spectral is greatly indebted to everyone who makes this work possible and believes this positive impact should be recognized. As part of this engagement, Spectral is focusing specifically on users powering the AI community. The top individual and small organization contributors on Hugging Face, measured by likes and downloads of their models and datasets, are eligible to register to claim a share of SPEC tokens starting the week of May 6th. Users can check eligibility by signing in with their Hugging Face account here . here here A snapshot of activity was taken last month, and eligible users will not need an existing wallet to claim. This airdrop is designed to recognize users for their critical work and enable new functionality for the next generation of AI tools. Criteria Spectral reviewed all individual contributors from organizations with less than 10 members that published models or datasets. From these, Spectral took a combined measure of activity from likes and downloads for both models and datasets. Then, Spectral identified the users with the most combined activity from both model and dataset publishers (11298 in both categories) which resulted in a final list of 20,004 unique huggingface users. Spectral is looking forward to engaging further with the open-source community and building the future of AI x web3! https://claims.spectrallabs.xyz/ https://claims.spectrallabs.xyz/ https://claims.spectrallabs.xyz/ About Spectral Spectral , a pioneer of the agent economy behind Syntax, is at the forefront of integrating AI with blockchain to democratize development in Web3. Spectral's mission is to simplify the creation and deployment of decentralized applications through autonomous Onchain Agents. Spectral Spectral Syntax, Spectral’s flagship product, translates natural language into Solidity code, enabling both novices and experts to build on the blockchain effortlessly. With a commitment to transparency and user empowerment, Spectral is shaping a future where anyone can participate in the blockchain revolution. Join Spectral in making this vision a reality and explore the potential of autonomous agents. For more information, visit https://spectrallabs.xyz . For more information, users can follow Spectral on Twitter and Discord . https://spectrallabs.xyz Twitter Twitter Discord Discord Contact Spectral Labs Team contact@spectral.finance This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here. This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here . here here

Spectral Labs Joins Hugging Face’s ESP Program: Advancing The Onchain x Open-Source AI Community

স্পেকট্রাল ল্যাবগুলি আলিঙ্গন মুখের ইএসপি প্রোগ্রামে যোগ দেয়: অনচেইন এক্স ওপেন-সোর্স এআই সম্প্রদায়কে এগিয়ে নিয়ে যাওয়া

Spectral Labs nimmt am ESP-Programm von Hugging Face teil: Förderung der Onchain x Open-Source-KI-Community

Spectral Labs se une al programa ESP de Hugging Face: avanzando en la comunidad de IA de código abierto Onchain x

Spectral Labs rejoint le programme ESP de Hugging Face : faire progresser la communauté d'IA Onchain x Open-Source

स्पेक्ट्रल लैब्स हगिंग फेस के ईएसपी कार्यक्रम में शामिल हुई: ऑनचेन एक्स ओपन-सोर्स एआई समुदाय को आगे बढ़ाना

Spectral Labs が Hugging Face の ESP プログラムに参加: オンチェーン x オープンソース AI コミュニティの発展

Spectral Labs, Hugging Face의 ESP 프로그램에 합류: Onchain x 오픈 소스 AI 커뮤니티 발전

Spectral Labs junta-se ao programa ESP da Hugging Face: Avançando a comunidade Onchain x Open-Source AI

Spectral Labs присоединяется к программе ESP Hugging Face: развитие сообщества искусственного интеллекта с открытым исходным кодом Onchain x

Spectral Labs, Hugging Face'in ESP Programına Katılıyor: Onchain x Açık Kaynak Yapay Zeka Topluluğunu Geliştirme

Spectral Labs tham gia chương trình ESP của Hugging Face: Thúc đẩy cộng đồng AI mã nguồn mở Onchain x

Spectral Labs 加入 Hugging Face 的 ESP 计划：推进 Onchain x 开源 AI 社区

HackerNoon curated the internet's most cited 3M+ tech company news articles and blog posts about the 3k+ most valuable tech companies in 2022 and 2023. These stories were curated to power HackerNoon.com/Companies, where we update daily news on top technology companies like Microsoft, Google, and HuggingFace. This dataset is open sourced under the Creative Common License on HuggingFace as Tech Company News Data Dump. Please use this tech company news data freely for your project :-) How the tech companies were curated Our team made a list of the most valuable technology companies, and added companies as they started to trend in the news and on HackerNoon. The first one and half thousand were public companies based on market cap. Then as companies got mentioned in HackerNoon stories and performed well in our startup of the year voting, we added created tech company news pages for them. Once a tech company news page is created, our system curates and stores the trending news, articles and blog posts about that company based on our rules and prompts  that define what is a trending story. How the stories, articles and blog posts were sourced A combination of custom rules, prompts and conditions for relevance, specificity and trendiness using the Bing News API, the Brave News API, and the HackerNoon API. We drilled down industry match for each company, and heavily favored more trusted high ranking sites while also allowing for relevant lower ranking niche publishers. For each company, we surface the most relevant 10-20 stories on their main /company page (Microsoft as an example), and then feature the complete list of the company’s news, stories, mentions, articles and notable links in internet history on company-name/news (Google as an example). How this tech company news data is organized The columns are companyName, company URL, publishedAT, (story) url, title, featured image, and (meta) description. This follows how we organize data in our database. Every article is connected to at least one company. Some companies have more articles than other based on their share of voice, for example using the dataset viewer you can see Google has 99,152 results, 3M has 20,608 results, Adobe has 13,449 results, and NVIDIA has 19,811 results. Without even downloading the data, you can search for company or publication names in the dataset viewer, like NVIDIA pictured below: This dataset is open sourced under the Creative Common License on HuggingFace as Tech Company News Data Dump. Please use this tech company news data freely for your project :-)  You could quantify a company’s aggregate share of voice online, you could measure sentiment analysis of a company’s digital news coverage, you could train your model to predict what headlines will publish about what companies in future, or whatever other research about large tech companies and media coverage your heart desires. Check it out this open data here: https://huggingface.co/datasets/HackerNoon/tech-company-news-data-dump?embedable=true HackerNoon curated the internet's most cited 3M+ tech company news articles and blog posts about the 3k+ most valuable tech companies in 2022 and 2023. These stories were curated to power HackerNoon.com/Companies , where we update daily news on top technology companies like Microsoft , Google , and HuggingFace . This dataset is open sourced under the Creative Common License on HuggingFace as Tech Company News Data Dump . Please use this tech company news data freely for your project :-) HackerNoon HackerNoon HackerNoon.com/Companies HackerNoon.com/Companies Microsoft Microsoft Google Google HuggingFace HuggingFace HuggingFace as Tech Company News Data Dump How the tech companies were curated Our team made a list of the most valuable technology companies, and added companies as they started to trend in the news and on HackerNoon. The first one and half thousand were public companies based on market cap. Then as companies got mentioned in HackerNoon stories and performed well in our startup of the year voting , we added created tech company news pages for them. Once a tech company news page is created, our system curates and stores the trending news, articles and blog posts about that company based on our rules and prompts  that define what is a trending story. startup of the year voting tech company news page How the stories, articles and blog posts were sourced A combination of custom rules, prompts and conditions for relevance, specificity and trendiness using the Bing News API, the Brave News API, and the HackerNoon API. We drilled down industry match for each company, and heavily favored more trusted high ranking sites while also allowing for relevant lower ranking niche publishers. For each company, we surface the most relevant 10-20 stories on their main /company page ( Microsoft as an example ), and then feature the complete list of the company’s news, stories, mentions, articles and notable links in internet history on company-name/news ( Google as an example ). Microsoft as an example Google as an example How this tech company news data is organized The columns are companyName, company URL, publishedAT, (story) url, title, featured image, and (meta) description. This follows how we organize data in our database. Every article is connected to at least one company. Some companies have more articles than other based on their share of voice, for example using the dataset viewer you can see Google has 99,152 results , 3M has 20,608 results , Adobe has 13,449 results , and NVIDIA has 19,811 results . the dataset viewer Google has 99,152 results 3M has 20,608 results Adobe has 13,449 results NVIDIA has 19,811 results Without even downloading the data, you can search for company or publication names in the dataset viewer, like NVIDIA pictured below : NVIDIA pictured below This dataset is open sourced under the Creative Common License on HuggingFace as Tech Company News Data Dump . Please use this tech company news data freely for your project :-)  You could quantify a company’s aggregate share of voice online, you could measure sentiment analysis of a company’s digital news coverage, you could train your model to predict what headlines will publish about what companies in future, or whatever other research about large tech companies and media coverage your heart desires. HuggingFace as Tech Company News Data Dump Check it out this open data here: https://huggingface.co/datasets/HackerNoon/tech-company-news-data-dump?embedable=true https://huggingface.co/datasets/HackerNoon/tech-company-news-data-dump?embedable=true

Tech Company News Data Dump on HuggingFace: 3M Most Cited Posts About 3k Most Valued Tech Companies

টেক কোম্পানি নিউজ ডাটা ডাম্প অন হাগিংফেস: 7M সর্বাধিক উদ্ধৃত পোস্টগুলি 3k সর্বাধিক মূল্যবান প্রযুক্তি সংস্থাগুলি সম্পর্কে

Tech-Unternehmens-News-Datendump auf HuggingFace: 7 Millionen meistzitierte Beiträge über 3.000 am meisten geschätzte Technologieunternehmen

Volcado de datos de noticias de empresas tecnológicas en HuggingFace: 7 millones de publicaciones más citadas sobre las 3.000 empresas tecnológicas más valoradas

Dump de données d'actualités sur les entreprises technologiques sur HuggingFace : 7 millions d'articles les plus cités sur les 3 000 entreprises technologiques les plus appréciées

हगिंगफेस पर टेक कंपनी समाचार डेटा डंप: 3 हजार सबसे मूल्यवान टेक कंपनियों के बारे में 7M सर्वाधिक उद्धृत पोस्ट

HuggingFace のテクノロジー企業ニュース データ ダンプ: 最も価値のある 3,000 のテクノロジー企業に関する最も引用された 700 万件の投稿

기술 회사 뉴스 HuggingFace의 데이터 덤프: 가장 가치 있는 기술 회사 3,000개에 대한 가장 많이 인용된 게시물 700만 개

Despejo de dados de notícias de empresas de tecnologia no HuggingFace: 7 milhões de postagens mais citadas sobre 3 mil empresas de tecnologia mais valiosas

Свалка данных новостей технологических компаний на HuggingFace: 7 миллионов самых цитируемых публикаций о 3 тысячах самых ценных технологических компаний

Teknoloji Şirketi Haberleri HuggingFace'teki Veri Dökümü: 3 Bin En Değerli Teknoloji Şirketi Hakkında 7 Milyon En Çok Alıntı Yapılan Gönderi

Kết xuất dữ liệu tin tức công ty công nghệ trên HuggingFace: 7 triệu bài viết được trích dẫn nhiều nhất về 3k công ty công nghệ có giá trị nhất

HuggingFace 上的科技公司新闻数据转储：关于 3000 家最有价值科技公司的 700 万条被引用次数最多的帖子

Text summarization is the task of creating a shorter version of a document or an article that captures the main information and meaning. It is useful for quickly understanding the content of long texts, such as news articles, research papers, or blog posts. In this article, we will show you how to build a text summarizer with transformers. Gradio and Hugging Face Table of contents Gradio Hugging Face Code for Text Summarizer Import the libraries Create a Summarization Pipeline Define a function that takes a text and returns a summary Create a Gradio Interface Launch the Interface Conclusion Gradio Gradio is a Python library that allows you to quickly build a web interface for your machine-learning models. You can use Gradio to create interactive demos, tutorials, or experiments for your models, and share them with anyone online. Gradio supports various input and output components, such as text boxes, images, audio, sliders, buttons, and more. Hugging Face Hugging Face transformers is another Python library that provides you with many pre-trained models for various natural language processing tasks, including text summarization. You can use the transformers library to easily load and use these models or fine-tune them on your data. The transformers library also supports different frameworks, such as PyTorch, TensorFlow, or JAX. Also read: Linear Regression: A Comprehensive Guide Code for Text Summarizer To build a text summarizer with Gradio and Hugging Face transformers, we need to follow these steps: Import the libraries Create a summarization pipeline Define a function that takes a text and returns a summary Create a Gradio interface Launch the interface Let’s see the code for each step: Import the libraries We need to import Gradio and Hugging Face transformers in our code. We can use the statement to do that: import # Import libraries
import gradio as gr
from transformers import pipeline Create a Summarization Pipeline We need to create a summarization pipeline using a pre-trained model to generate summaries. We can use the function from Hugging Face transformers to do that. We need to specify the task as and optionally, we can provide other parameters, such as the , , and of the summaries: pipeline "summarization" max_length min_length do_sample # Create a summarization pipeline
summarizer = pipeline("summarization", max_length=150, min_length=40, do_sample=False) Define a function that takes a text and returns a summary We need to define a function that will take a text as input and return a summary as output. We can use the pipeline that we created in the previous step to do that. We need to pass the text to the and get the first element of the returned list, which is a dictionary that contains the key. We can return the value of that key as the output of our function: summarizer summarizer "summary_text" # Define a function that takes a text and returns a summary
def summarize(text):
  summary = summarizer(text)[0]
  return summary["summary_text"] Create a Gradio Interface We need to create a Gradio interface that will wrap up our function and provide a web interface for it. We can use the function to do that. We need to pass our function as the argument and specify the input and output components as the Textbox arguments. We can use the component for the input text and the component for the output summary. gr.Interface fn gr.Textbox gr.Textbox We can also provide labels for the components as the argument: label # Create a Gradio interface
interface = gr.Interface(
  fn=summarize, # the function to wrap
  inputs=gr.inputs.Textbox(lines=10, label="Input Text"), # the input component
  outputs=gr.outputs.Textbox(label="Summary") # the output component
) Launch the Interface We need to launch the interface so that we can use it online. We can use the method of the interface object to do that. launch # Launch the interface
interface.launch() Here is the entire code in one block: # Import libraries
import gradio as gr
from transformers import pipeline

# Create a summarization pipeline
summarizer = pipeline("summarization")

# Define a function that takes a text and returns a summary
def summarize(text):
  summary = summarizer(text, max_length=150, min_length=40, do_sample=False)[0]
  return summary["summary_text"]

# Create a Gradio interface
interface = gr.Interface(
  fn=summarize, # the function to wrap
  inputs=gr.Textbox(lines=10, label="Input Text"), # the input component
  outputs=gr.Textbox(label="Summary") # the output component
)

# Launch the interface
interface.launch() Conclusion This is how you can build a text summarizer with Gradio and Hugging Face transformers. You can try it by running the code or visiting the link provided by Gradio. You can also experiment with different models and parameters to improve the quality of the summaries. You can also customize the interface with different components and styles. For more information, you can check out the and documentation. I hope you enjoyed this article and learned something new. Happy summarizing! Gradio Hugging Face Also published . here

How to Build a Text Summarizer with Gradio and Hugging Face Transformers 

In the rapidly evolving landscape of , the demand for powerful AI solutions has never been higher. Companies and developers are constantly seeking efficient ways to harness the capabilities of AI to build smarter applications, automate tasks, and gain insights from data. Artificial Intelligence ‍ Two platforms, and , have emerged as key players in this domain, each offering unique approaches to meet the diverse needs of the AI community. Eden AI is dedicated to consolidating the finest AI APIs within a single platform, whereas Hugging Face is renowned for its emphasis on open-source models. In this article, we'll explore the differences between these platforms and how they target distinct types of users. Eden AI Hugging Face ‍ Eden AI: Unifying AI APIs Eden AI is a platform designed to simplify the process of accessing and utilizing a wide range of AI APIs. It functions as a centralized hub that aggregates various AI services, making it easier for developers and businesses to experiment with different AI capabilities without having to individually integrate each API. Think of it as a one-stop-shop for AI, offering a seamless experience for accessing text, images, speech processing, and other AI capabilities. ‍ Key Features of Eden AI: Eden AI brings together a diverse set of AI APIs, such as natural language processing (NLP), computer vision, speech recognition, and more, allowing users to access them all from a single platform. Eden AI helps users choose the best AI model at any given time, based on various criteria (accuracy, price, latency, compliance, etc.). API Aggregation: Developers can interact with AI APIs through straightforward and consistent interfaces, reducing the complexity of integration and enabling rapid development. Simplicity: Eden AI is designed to cater to a wide range of users, from individual developers to large enterprises, providing scalable solutions to meet varying demands. Scalability: Users can control their AI usage and costs by managing their API subscriptions within one platform, streamlining billing and payment processes. Cost-Efficiency: ‍ Hugging Face: The Open Source Model Hub , on the other hand, is renowned for its focus on Open Source models. It provides a repository of pre-trained models and tools for natural language processing tasks, making state-of-the-art AI models accessible to developers and researchers worldwide. The core philosophy of Hugging Face is built around the idea of collaboration and open sharing within the AI community. Hugging Face ‍ Key Features of Hugging Face : Hugging Face offers a vast library of pre-trained AI models for a wide range of NLP tasks, such as text classification, language translation, and text generation. Open Source Models The platform encourages contributions from the AI community, allowing developers to fine-tune and share their own models, democratizing AI model development. Community-Driven: Hugging Face provides tools and resources for fine-tuning pre-trained models on specific tasks or domains, enabling customization for various use cases. Fine-Tuning: It serves as a valuable resource for researchers, students, and developers who want to experiment with and learn about cutting-edge AI models and techniques. Research and Education: ‍ Targeting Different User Needs While both Eden AI and Hugging Face cater to the AI community, they serve different purposes and target distinct types of users: ‍ Primarily targets businesses, developers, and organizations looking for quick and efficient access to a wide array of AI capabilities. It's ideal for those who want to leverage AI APIs without the need to delve into model development intricacies. Eden AI simplifies integration, reduces development time, and offers cost-effective solutions. Eden AI: Appeals to users with in-depth knowledge of AI, including researchers, data scientists, and developers. It excels in providing open access to state-of-the-art AI models, fostering collaboration, and enabling fine-tuning for specific tasks. Hugging Face is the go-to platform for those interested in model research, experimentation, and customization. Hugging Face: ‍ Conclusion Both Eden AI and Hugging Face are pivotal players in the AI ecosystem, each with a distinct focus and set of offerings. Eden AI simplifies AI integration by aggregating diverse AI APIs, while Hugging Face empowers the AI community with open access to pre-trained models and tools for customization. The choice between these platforms depends on the specific needs and goals of users, whether it's quick AI integration or deep model exploration and development. Together, they contribute to the democratization and advancement of AI technology. Also published here.

Eden AI vs Hugging Face: Use Cases,  Target Users and Value Propositions 

In this blog, I will show you how to quickly create an entirely free app using a JavaScript program that runs within the free Oracle database and calls AI, the results of which are stored in the database and can then be accessed using , , Rest, or any other language. All of the source code is, of course, available . Hugging Face SQL JSON here A typical sequence of actions in applications, both in general and particularly in AI applications, involves an application utilizing an AI service. The acquired information is then stored in a database, ready for retrieval, subsequent processing (such as using OML), analysis, and future queries. When the command originates directly from the database, the data is promptly stored and gains higher reliability. This approach is in-process and eliminates the need for an additional network call for persistence. Additionally, by housing the logic and even code within the database, the remarkable features of the robust Oracle database, including high availability, management, and observability, are naturally harnessed. This distinct capability is a hallmark of the Oracle database, which encompasses both Java and, as detailed in this blog, JavaScript runtime engines within the database itself. Hugging Face specializes in crafting tools for constructing applications using machine learning. Particularly notable is its transformers library designed for natural language processing applications, along with its platform facilitating the sharing of machine learning models and datasets. It has garnered significant popularity in recent years. In short, we’ll… Create a cohere.com or huggingface.co account, create and copy an access token, and select a model. Create the Oracle database. Create the database user and table(s). Run a short JavaScript program in the database to make a call to the Cohere or Hugging Face AI model and store the results in the table. Query these results using SQL, JSON, Rest, etc. Setup Cohere account and AI model Go to https://cohere.com and , go to your , and click the button. Sign Up Profile Settings Click on , then API Keys, create a key (or use trial) and copy its value for use later. Dashboard Click on and select the hamburger menu/icon on the left of any page to view the API Reference list and select one. In this case, we will select section and API Reference generate Co.Generate. Select and then select the option in order to see a sample code snippet to call the model. Ianguage JavaScript Setup Hugging Face account and AI model Go to https://huggingface.co and , go to your , and click the button. Sign Up Profile Settings Click on , create a token, and copy its value for use later. Access Tokens Click on and select a model. In this case, we will select a model under the section for Models Natural Language Processing Question Answering. Select a model (perhaps one of the more popular ones), notice the information in the on the left, and then select the drop-down menu on the right. Model Card Deploy Select and then select the option in order to see a sample code snippet to call the model. Inference API JavaScript Setup Oracle Database We can use any flavor of the Oracle database 23c. On the cloud, we can use Oracle always free autonomous database later this year when 23c should be available. We can use the Oracle 23c Free version as it’s available now and we can simply install or use a container image locally. Or of course, we could use the local for dev and cloud for production, etc. and either of these options is very quick to set up… Oracle Database Free… You can go here to set up the Free Oracle Database. Using the container image is very simple. You can simply pull the image: docker pull container-registry.oracle.com/database/free:latest Then, execute the one line below, replacing with a password of your choice (you can also add a parameter with a directory location in order to persist changes across restarts). Notice the param that allows calls out of the container. This is the setting for Macs and will be different if running on a different OS. -e ORACLE_PASSWORD=Welcome12345 -v oracle-volume:/somedirectory --add-host docker.for.mac.host.internal:host-gateway docker run -d -p 1521:1521 — add-host docker.for.mac.host.internal:host-gateway -e ORACLE_PASSWORD=Welcome12345 gvenzl/oracle-free Setup SQLcl (or Database Actions) and connect You can install SQLcl to manage the database by: Downloading and install from this location https://www.oracle.com/database/sqldeveloper/technologies/sqlcl/download/ This will provide an executable that we will use to administer the database. For convenience, you may add to your PATH. [SQLcl_INSTALL_DIR]/bin/sql [SQLcl_INSTALL_DIR]/bin Login replacing with the location of your SQLcl and replacing with the one you provided as when creating the database Here is an example when using a local install (eg Oracle Database Free container image): [SQLcl_INSTALL_DIR] Welcome12345 ORACLE_PASSWORD [SQLcl_INSTALL_DIR]/bin/sql /nolog SQL> connect sys@//localhost:1521/freepdb1 as sysdba Password? (**********?) ************* Connected. Create the users, with appropriate privileges, that will call Cohere and/or Hugging Face via JavaScript. Run the following SQL files to create the user and its necessary grants and ACLs (note that these can be further tightened for better security). aijs @sql/create_aijs_acl.sql SQL> @sql/create_aijs_user.sql``SQL> Now connect the user and create a table to store the results of the call to Hugging Face SQL> connect aijs/Welcome12345; SQL> create table huggingfacejson (id json); SQL> create table coherejson (id json); Now everything is ready to run! Run either the Cohere or HuggingFace queries from the JavaScript code in the database Cohere Example SQL> @sql/coherequery.sql PL/SQL procedure successfully completed. Then, check the JSON results stored in the table by doing a SQL query. SQL> select * from coherejson; [{"id":"1b42f8f9-ea6d-4a65-8f02-bdcf89d9bd79","generations":[{"id":"d6467c0b-4a78-4dd4-b822-c1e2bfa4ecb0","text":"\n LLMs or Large Language Models are artificial intelligence tools that can read, summarize and translate texts and"}],"prompt":"Please explain to me how LLMs work","meta":{"api_version":{"version":"1"}}} Looking at the code we just executed we can see the JavaScript module created and the function being called: create or replace mle module cohere_module language javascript as import "mle-js-fetch"; import "mle-js-oracledb"; export async function cohereDemo(apiToken) { if (apiToken === undefined) { throw Error("must provide an API token"); } const modelId = "generate"; const restAPI = `https://api.cohere.ai/v1/${modelId}`; const headers = { accept: 'application/json', 'content-type': 'application/json', "Authorization": `Bearer ${apiToken}` }; const payload = { max_tokens: 20, return_likelihoods: 'NONE', truncate: 'END', prompt: 'Please explain to me how LLMs work' }; const resp = await fetch( restAPI, { method: "POST", headers: headers, body: JSON.stringify(payload), credentials: "include" } ); const resp_json = await resp.json(); session.execute( `INSERT INTO COHEREJSON (id) VALUES (:resp_json)`, [ JSON.stringify(resp_json) ] ); } / create or replace procedure coherequery( p_API_token varchar2 ) as mle module cohere_module signature 'cohereDemo(string)'; / -- this is how you can test the API call begin utl_http.set_wallet('system:'); coherequery('[yourcoheretokenhere]'); end; / Hugging Face Example SQL> @sql/huggingfacequery.sql PL/SQL procedure successfully completed. Then, check the JSON results stored in the table by doing a SQL query. SQL> select * from huggingfacejson; [{"score":0.16964051127433777,"token":2053,"token_str":"no","sequence":"the answer to the universe is no."},{"score":0.07344779372215271,"token":2498,"token_str":"nothing","sequence":"the answer to the universe is nothing."},{"score":0.05803246051073074,"token":2748,"token_str":"yes","sequence":"the answer to the universe is yes."},{"score":0.043957971036434174,"token":4242,"token_str":"unknown","sequence":"the answer to the universe is unknown."},{"score":0.04015727713704109,"token":3722,"token_str":"simple","sequence":"the answer to the universe is simple."}] Looking at the code we just executed we can see the JavaScript module created and the function being called: create or replace mle module huggingface_module language javascript as import "mle-js-fetch"; import "mle-js-oracledb"; export async function huggingfaceDemo(apiToken) { if (apiToken === undefined) { throw Error("must provide an API token"); } const payload = { inputs: "The answer to the universe is [MASK]." }; const modelId = "bert-base-uncased"; const headers = { "Authorization": `Bearer ${apiToken}` }; const restAPI = `https://api-inference.huggingface.co/models/${modelId}`; const resp = await fetch( restAPI, { method: "POST", headers: headers, body: JSON.stringify(payload), credentials: "include" } ); const resp_json = await resp.json(); session.execute( `INSERT INTO HUGGINGFACEJSON (id) VALUES (:resp_json)`, [ JSON.stringify(resp_json) ] ); } / create or replace procedure huggingfacequery( p_API_token varchar2 ) as mle module huggingface_module signature 'huggingfaceDemo(string)'; / -- this is how you can test the API call begin utl_http.set_wallet('system:'); huggingfacequery('[hf_yourhuggingfacetokenhere]'); end; / Useful parameters and debug information for Hugging Face can be found . here The results can now be queried, analyzed, etc. using SQL or JSON (simultaneously thanks to the new JSON duality feature), REST, or even the MongoDB API.Oracle Database is the perfect database for AI for a number of reasons, particularly as it is a vector database with capabilities such as the following already available today: Native data types for vector representation and storage: RAW, BLOB, JSON In-Memory Column Store to store & search vector embeddings w/ SIMD kernels for amazing performance Extensible indexing framework to create data-model specific indices (e.g., Text, Spatial) Native Oracle Machine Learning APIs — Modeling, Classification, Scoring, Clustering, etc. Plus, many other capabilities which, used together, make Oracle a better Vector Database DMLs, Parallel Loading, Partitioning, Advanced Compression, Parallel Query, RAC, Sharding, etc. It is also possible to call Oracle OCI AI and other services from within the Oracle database. Conclusion The blog went into how to call Hugging Face APIs from within the Oracle database using JavaScript thus demonstrating a powerful combination of features perfectly suited to a broad array of AI solutions and friendly to JavaScript developers. Some other blogs related to JavaScript in the database, in general, the MultiLingual Engine (MLE) that makes it possible, etc. can be found and . Thanks to Martin and Lucas for all their help. in Martin Bach’s blogs this post about JavaScript modules I look forward to any comments or questions you may have and really appreciate your time reading. Also published . here

Calling Hugging Face AI From an Oracle Database Using JavaScript

Mark Twain's Speeches by Mark Twain, is part of the HackerNoon Books Series. You can jump to any chapter in this book . GERMAN FOR THE HUNGARIANS here GERMAN FOR THE HUNGARIANS ADDRESS AT THE JUBILEE CELEBRATION OF THE EMANCIPATION OF THE
          HUNGARIAN PRESS,  MARCH 26, 1899

          The Ministry and members of Parliament were present.  The
          subject was the “Ausgleich”—i. e., the arrangement for the
          apportionment of the taxes between Hungary and Austria.
          Paragraph 14 of the ausgleich fixes the proportion each country
          must pay to the support of the army.  It is the paragraph which
          caused the trouble and prevented its renewal. Now that we are all here together, I think it will be a good idea to arrange the ausgleich. If you will act for Hungary I shall be quite willing to act for Austria, and this is the very time for it. There couldn’t be a better, for we are all feeling friendly, fair-minded, and hospitable now, and, full of admiration for each other, full of confidence in each other, full of the spirit of welcome, full of the grace of forgiveness, and the disposition to let bygones be bygones. Let us not waste this golden, this beneficent, this providential opportunity. I am willing to make any concession you want, just so we get it settled. I am not only willing to let grain come in free, I am willing to pay the freight on it, and you may send delegates to the Reichsrath if you like. All I require is that they shall be quiet, peaceable people like your own deputies, and not disturb our proceedings. If you want the Gegenseitigengeldbeitragendenverhaltnismassigkeiten rearranged and readjusted I am ready for that. I will let you off at twenty-eight per cent.—twenty-seven—even twenty-five if you insist, for there is nothing illiberal about me when I am out on a diplomatic debauch. Now, in return for these concessions, I am willing to take anything in reason, and I think we may consider the business settled and the ausgleich ausgegloschen at last for ten solid years, and we will sign the papers in blank, and do it here and now. Well, I am unspeakably glad to have that ausgleich off my hands. It has kept me awake nights for anderthalbjahr. But I never could settle it before, because always when I called at the Foreign Office in Vienna to talk about it, there wasn’t anybody at home, and that is not a place where you can go in and see for yourself whether it is a mistake or not, because the person who takes care of the front door there is of a size that discourages liberty of action and the free spirit of investigation. To think the ausgleich is abgemacht at last! It is a grand and beautiful consummation, and I am glad I came. The way I feel now I do honestly believe I would rather be just my own humble self at this moment than paragraph 14. About HackerNoon Book Series: We bring you the most important technical, scientific, and insightful public domain books. This book is part of the public domain. Mark Twain (2004). Mark Twain's Speeches. Urbana, Illinois: Project Gutenberg. Retrieved October 2022 https://www.gutenberg.org/cache/epub/3188/pg3188-images.html This eBook is for the use of anyone anywhere at no cost and with almost no restrictions whatsoever. You may copy it, give it away or re-use it under the terms of the Project Gutenberg License included with this eBook or online at , located at . www.gutenberg.org https://www.gutenberg.org/policy/license.html

GERMAN FOR THE HUNGARIANS

The King of Hungary

Andre’s tutor hastily assembled the chief Hungarian lords

HÜGGA

hugga.io

-- employees

Since n.d.

COMPANY RANKING

HÜGGA

EVERGREEN INDEX #5122

Representing this company? Click here to claim and customize this page!

Hügga WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!

HÜGGA

hugga.io

-- employees

Since n.d.

COMPANY RANKING

HÜGGA

EVERGREEN INDEX #5122

RELATED COMPANIESRANK

STORIES ABOUT HÜGGA

Representing this company? Click here to claim and customize this page!

Hügga WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!