H2O.ai
H2O.ai
  • 1 234
  • 1 893 636
Generative AI for Advanced RAG systems & AI Governance
In this demo, we navigate the H2O AI Cloud, where Enterprise GPTe, H2O GPT, and Eval Studio await exploration. Witness the creation of collections, the import of documents, and the utilization of generative AI to extract insights from complex data sets.
Follow along as we converse with documents, using large language models to provide feedback via a RAG system. Gain insights into the process of parsing, chunking, and embedding data for meaningful interactions.
Explore the customizable settings of Enterprise GPTe, from system prompts to advanced RAG configurations, and discover how to optimize AI performance while managing costs effectively.
Delve into the API capabilities, from connecting to loading data to creating chat sessions, and learn how to harness the power of generative AI for your specific use cases.
Witness the evaluation of AI models and RAG systems in Eval Studio, where you can create custom leaderboards, define evaluation metrics, and analyze performance across various models and scenarios.
Ready to unlock the potential of generative AI?
Get Started Now using H2O Enterprise GPTe: h2o.ai/#gpt
Explore H2O.ai: h2o.ai/
Переглядів: 161

Відео

Training and Deploying Standalone LLM + Guardrails
Переглядів 16121 день тому
Explore the process of training and deploying a standalone Large Language Model (LLM) with guardrails in this engaging demo. Witness the stark difference between an unguarded LLM generating whimsical, off-brand responses and one with carefully implemented guardrails, maintaining professionalism and coherence across various prompts. Explore real-world examples, such as crafting LinkedIn posts, w...
Mastering LLM Evaluation: Metrics and Methodologies
Переглядів 16728 днів тому
In this final lab, you will focus on evaluating large language models (LLMs) programmatically. You will learn to compare LLMs using methods like blue score and Rouge score, but these methods have limitations. The lab introduces a more effective approach: using a third language model as a judge to compare LLMs. The scores are being assigned based on comparing responses from different models. GPT...
Model Consumption with H2O.ai Tools
Переглядів 64Місяць тому
Learn how to leverage H2O, an open-source library, to effortlessly create multi-page applications and chatbots using only Python. Explore the process of deploying these apps to the iCloud for seamless accessibility across your organization. In this demo, we delve into the Rupogen Gen AI App Store in GitHub, featuring over 15 example applications in the Gen AI space, perfect for building chatbot...
Mastering Dataset Preparation: Techniques and Best Practices
Переглядів 98Місяць тому
In this fourth lab, we'll focus on dataset preparation for Downstream NLP tasks. We'll explore various techniques programmatically in Python, using libraries like PyTorch Transformers, pandas, NumPy, and Matplotlib. The dataset we'll work with consists of LinkedIn influencer posts collected in 2021, containing metadata such as the influencer's name, number of followers, timespan, content, media...
Data Science and Machine Learning Techniques
Переглядів 108Місяць тому
Learn how to effortlessly upload datasets and leverage existing ones from the feature store for analysis. Follow along as we explore the intuitive interface's ability to extract column names, generate data summaries, and execute Python functions seamlessly. Experience the latest innovation from H2O, H2O Functions, a chat-based interface for data science tasks. Learn how to leverage this powerfu...
A Comprehensive Guide to Fine-Tuning Language Models
Переглядів 276Місяць тому
Lab Three introduces fine-tuning language models. You'll learn to fine-tune both small and large models, beginning with a simple model using Hugging Face's library and progressing to larger models like GPT-3 using LLM Studio. The process involves dataset preparation, tokenization, model setup, and training. Finally, you'll compare fine-tuning traditional models with large language models and ex...
Plan Projects, Explore , Visualize, Data Preparation
Переглядів 108Місяць тому
Discover how H2O's Driverless AI empowers data scientists with automated machine learning, data visualization, prep wizards, and live coding capabilities. Here's how to access H2O's Driverless AI for training purposes: 1. Visit our Aquarium platform at aquarium.h2o.ai/. 2. Watch the following video to learn how to create an account on Aquarium: ua-cam.com/video/2V9XCT7dDqk/v-deo.htmlsi=7KAvIUw9...
Introduction to H2O.ai's Data Science and Machine Learning Platform
Переглядів 203Місяць тому
Want to learn how H2O.ai's platform simplifies data science workflows with seamless integration across features, notebooks, and AI engines like Driverless AI? This is the right place for you! In this course, you will be guided through project planning with feature sets, interacting with features via UI and notebooks, and visualizing data pipelines. You will also see how the feature store allows...
GenAI AppStore: Your Gateway to Innovative Solutions
Переглядів 60Місяць тому
Discover the potential of Gen AI Apps in this brief video. Explore our Gen Cloud for free access to a myriad of innovative ideas and inspirations. From Call Center GPT to Enterprise H2O GPTe, our offerings provide a glimpse into the possibilities. Dive in, browse, and experiment at your leisure-all at no cost. This class does not have any Python Notebook Lab. Instructions to access GenAI AppSto...
Quick Overview: Time Series Data Prep with H2O.ai Driverless AI
Переглядів 108Місяць тому
Welcome back to our exploration of data preparation with H2O.ai Driverless AI. In this video, we delve into the essential principles and best practices necessary for effective time series analysis. Time series problems revolve around target variables intertwined with date information. This necessitates the inclusion of a date column in both training and test datasets, forming the cornerstone of...
Introduction to the DataPrep for DriverlessAI Course
Переглядів 120Місяць тому
Join us for an insightful course on data preparation for machine learning with Driverless AI! Explore fundamental principles, key concepts, and essential steps for effective data prep. This course is divided into two chapters for structured learning: - Chapter One: Understanding the importance of data preparation, highlighting the classical Tabular format's role in traditional machine learning....
Practical RAG Techniques: Interacting with Enterprise H2O GPTe
Переглядів 122Місяць тому
Learn to summarize documents, create LinkedIn posts, and uncover insights with Enterprise GPTe and Python Notebooks. Follow our hands-on exercises for practical skills and valuable insights, whether you're a beginner or advanced user. Instructions to access Enterprise H2O GPTe: You can gain access to Enterprise H2O GPTe by logging in using your h2o.ai Managed Cloud Account, your Gmail or GitHub...
Data Exploration Simplified: Guide to Driverless AI Prep
Переглядів 70Місяць тому
In this video, Jonathan Farinela presents an in-depth guide to preparing and exploring data while utilizing Driverless AI for machine learning tasks. Here's what you'll find: 1. Introduction to Dataset Perspective: Get an overview of the dataset used, sourced from a Kaggle classification problem. 2. Exploring Data in Driverless AI: Discover how to import data into Driverless AI and analyze its ...
Understanding the Foundations of Large Language Models
Переглядів 304Місяць тому
In this video, we will dive into the basics of large language models (LLMs) pipeline. We'll explore how these models can do more than just predict the next word in a sentence - they can think, reason, and even philosophize. We'll try to understand how LLMs are trained and why they're so powerful. Then, we'll take a look at the inner workings of LLMs, focusing on their architecture and how data ...
Mastering GenAI LLMs: Hands-On Training Guide
Переглядів 375Місяць тому
Mastering GenAI LLMs: Hands-On Training Guide
Machine Learning Data Prep Basics
Переглядів 126Місяць тому
Machine Learning Data Prep Basics
Desbravando o Futuro: IA na Vanguarda do Setor Público
Переглядів 213Місяць тому
Desbravando o Futuro: IA na Vanguarda do Setor Público
H2O AI Code Assistants
Переглядів 2552 місяці тому
H2O AI Code Assistants
H2O.ai Vision Services
Переглядів 582 місяці тому
H2O.ai Vision Services
H2O.ai Language Services
Переглядів 1082 місяці тому
H2O.ai Language Services
Intro to the H2O Cloud AI Developer Services Course
Переглядів 592 місяці тому
Intro to the H2O Cloud AI Developer Services Course
H2O.ai Tabular Services
Переглядів 1172 місяці тому
H2O.ai Tabular Services
NIST AI Risk Management Framework | Patrick Hall - H2O GenAI World DC 2024
Переглядів 1502 місяці тому
NIST AI Risk Management Framework | Patrick Hall - H2O GenAI World DC 2024
Training Q&A | Megan Kurka - H2O GenAI World DC 2024
Переглядів 252 місяці тому
Training Q&A | Megan Kurka - H2O GenAI World DC 2024
Guidelines for AI Robustness & Security | Sheree Zhang, Marc Abrams, Heather Frase, Dave Epperson
Переглядів 522 місяці тому
Guidelines for AI Robustness & Security | Sheree Zhang, Marc Abrams, Heather Frase, Dave Epperson
Kaggle Grand Master Panel | Rob Mulla, Arno Candel, Kim Montgomery, Mark Lochbihler, Ryan Chesler
Переглядів 732 місяці тому
Kaggle Grand Master Panel | Rob Mulla, Arno Candel, Kim Montgomery, Mark Lochbihler, Ryan Chesler
Introduction to "Kaggle Grand Master" Panel - H2O GenAI World DC 2024
Переглядів 272 місяці тому
Introduction to "Kaggle Grand Master" Panel - H2O GenAI World DC 2024
FireSide Chat | Harald Schneider, Chief Data & Analytics Officer Equifax - H2O GenAI World DC 2024
Переглядів 572 місяці тому
FireSide Chat | Harald Schneider, Chief Data & Analytics Officer Equifax - H2O GenAI World DC 2024
Fireside Chat | Sri Ambati, Agus Sudjianto - H2O GenAI World DC 2024
Переглядів 422 місяці тому
Fireside Chat | Sri Ambati, Agus Sudjianto - H2O GenAI World DC 2024

КОМЕНТАРІ

  • @hamedhaidari4479
    @hamedhaidari4479 4 дні тому

    data wrangler in vscode from microsoft can do the same.

  • @MrAlphonsejose05
    @MrAlphonsejose05 10 днів тому

    Great One 🙂

  • @juancarlosabad3298
    @juancarlosabad3298 10 днів тому

    How does the certification work? Is it enough to watch and follow all this video sequel in UA-cam??

  • @zederish
    @zederish 21 день тому

    Jon Farland looks and sounds like the guy who says "look at this!"😂 ua-cam.com/video/EF8GhC-T_Mo/v-deo.html

  • @user-rs1dy2cy3z
    @user-rs1dy2cy3z 23 дні тому

    6:37 where is #Grok ? why isn't it in here since Grok has the largest database.

  • @mridsvlogs8305
    @mridsvlogs8305 Місяць тому

    Which are those top 10

  • @joaquimsousa2267
    @joaquimsousa2267 Місяць тому

    perfect but is possible link for DataSet?

  • @filthypirate
    @filthypirate Місяць тому

    thanks

  • @Faith_tech_666
    @Faith_tech_666 Місяць тому

    thank you for all your efforts

  • @karthiksuresh2534
    @karthiksuresh2534 Місяць тому

    Dream office!

  • @futurexinsights
    @futurexinsights Місяць тому

    Random talk

  • @dougbarboza25
    @dougbarboza25 Місяць тому

    Muito legal a apresentação. Parabéns à equipe!

  • @abdelbaki8625
    @abdelbaki8625 Місяць тому

    i dont understand how calculate shap value

  • @orshazeer6634
    @orshazeer6634 2 місяці тому

    This is a great lecture. Good job nachum! 😊

  • @samuelwest6817
    @samuelwest6817 2 місяці тому

    Yeah, pretty bad youtube production to be honest, you could have screen recorded and synced the footage up, or gotten the slides after the fact and lined them up, Or checked the camera recording and lowered the exposure/focused better, this is more of an audio-only experience. I appreciate you guys uploading the recording, but you could have done better I think. Keep up the good work.

  • @420_gunna
    @420_gunna 2 місяці тому

    I cant see shiiiiitttt

  • @shaahin6818
    @shaahin6818 2 місяці тому

    lol. removed from the CRAN, Mr.Charlatan

  • @user-fg3bc2du1r
    @user-fg3bc2du1r 2 місяці тому

    any results compared with bert

  • @picklenickil
    @picklenickil 3 місяці тому

    This is brilliant. My only question is does it support multiple threads? That's something I wanna see in current frameworks

  • @joaofaria4243
    @joaofaria4243 3 місяці тому

    What were the models used in the datasets?

  • @user-nu5pg2ly9h
    @user-nu5pg2ly9h 3 місяці тому

    Dream Company!

  • @babyfox205
    @babyfox205 3 місяці тому

    how to register? there's only sign in button, cannot register for the cloud account...

  • @mansigrover359
    @mansigrover359 3 місяці тому

    Can we create PPT from H2o gpt?

  • @user-dg4ko9bd5m
    @user-dg4ko9bd5m 4 місяці тому

    @1:15 - How NOT to represent your company :)

  • @georgechristy11
    @georgechristy11 4 місяці тому

    what an underrated video

  • @ardgeorge4175
    @ardgeorge4175 4 місяці тому

    What if I write something with ChatGPT, ask Claude to enhance it and then Genimi to re-write it in a new format?

  • @vincevanhoutte3858
    @vincevanhoutte3858 4 місяці тому

    There is a considerable debate, and many AI detectors generate different outcomes. Even if I rewrite the whole text, change the order of words, and delete words, some still flag me as AI. I write, I ask for feedback. One student didn't use AI at all and still flagged up with 30%: Turnitin is, unfortunately, the chosen option at uni. Any suggestions, It would be great to have a reliable tool to check my work before submission as we do with plagiarism and grammarcheck.

  • @Anony1990
    @Anony1990 4 місяці тому

    7:52. Should have spoken in hindi people below poverty line do not understand English well

  • @MaxiMovier
    @MaxiMovier 4 місяці тому

    Hi thank U this was really helpfull for beginners

  • @rizkikazakkapalindungan794
    @rizkikazakkapalindungan794 4 місяці тому

    thanksss

  • @odai.shalaan
    @odai.shalaan 4 місяці тому

    great

  • @odai.shalaan
    @odai.shalaan 4 місяці тому

    great

    • @H2Oai
      @H2Oai 4 місяці тому

      Thank you!

  • @taredje4664
    @taredje4664 5 місяців тому

    i installed llmstudio , how to install llm datastudio

  • @virgiliapervandos4998
    @virgiliapervandos4998 5 місяців тому

    Please show me 20 test item with 4 choices and answer key for children's wear.

  • @odai.shalaan
    @odai.shalaan 5 місяців тому

    Could you help me I have to upload any file to (H2Ogpt) or I am not answered according to the question, but rather it is answered with the complete content of the file!!!? Why is it not answered according to the question?

  • @odai.shalaan
    @odai.shalaan 5 місяців тому

    Could you help me I have to upload any file to (H2Ogpt) or I am not answered according to the question, but rather it is answered with the complete content of the file!!!? Why is it not answered according to the question?

  • @seyisonade1194
    @seyisonade1194 5 місяців тому

    Thanks a million, For ALL you do and represents, And your video background is awesome _ no noise and its distractions-free

  • @odai.shalaan
    @odai.shalaan 5 місяців тому

    great

  • @truehighs7845
    @truehighs7845 6 місяців тому

    H2o is a great software and smooth with that even on the xwin model it was very impressive, unfortunately I was disappointed because it put my cache into c:/ instead of putting it in the Drive I installed it into, if people change drive install it's because they know the space they have - why install .cache on C:/ and junk my whole drive??? So many options and not 1 to change download drive? UAT Failed!

  • @aldoko
    @aldoko 6 місяців тому

    videos 20 and 21 are not on the video list, are they going to be reuploaded?

  • @geoff1337
    @geoff1337 6 місяців тому

    This looks very promising. Will be great when you can feed in PDFs and other docs. Also interested in one where you could feed in financial data. Stock history etc

  • @VaibhavPatil-rx7pc
    @VaibhavPatil-rx7pc 6 місяців тому

    Excellent training course, where we can find presentation and course session links to refer to? Thanks

  • @VaibhavPatil-rx7pc
    @VaibhavPatil-rx7pc 6 місяців тому

    🎉

  • @mezxo
    @mezxo 7 місяців тому

    Is it possible to use this model with AMD cards?

    • @H2Oai
      @H2Oai 6 місяців тому

      At this time it is mainly NVIDIA cards with CUDA that are supported.

    • @truehighs7845
      @truehighs7845 6 місяців тому

      In theory you could with ROCm or with Llama CPP on GPT4all, that is bypassing your Radeon, in practice CPP is very slow and ROCm never works for many reasons across the whole stack, but mainly, because Triton and pythin and environments that fall flat from 1 day to the other... unless you are ready to reach the depth of your patience, don't try.

    • @odai.shalaan
      @odai.shalaan 5 місяців тому

      Can I have your account? I want to communicate with you. Because you are Arab, we understand each other

  • @lm-gu1ki
    @lm-gu1ki 7 місяців тому

    Can you please post a link to the slides? The glare in the video makes it hard to see some of the slides.

  • @user-bs5xo4nd1t
    @user-bs5xo4nd1t 7 місяців тому

    iam not able to signup

  • @3nityC
    @3nityC 7 місяців тому

    How about text to speech?

  • @alexanderroodt5052
    @alexanderroodt5052 7 місяців тому

    Most user unfriendly LLM app I have encountered to date and I have used almost every single one there is. Ambiguous AF when performing tasks. 1/10 experience.

    • @unkim7085
      @unkim7085 5 місяців тому

      Any better suggestion? I was using oobabooga

  • @torstenkarstadt9785
    @torstenkarstadt9785 7 місяців тому

    02:48 What are LLMs? 18:57 Steps in Building LLMs 22:30 Importance of Data Cleaning for LLMs 28:40 What is H20 LLM Data Studio? (+Interface Demo) 40:13 Generate a Clean Dataset from a PDF (Doc2QA) 50:22 Questions: ingesting web resources + business model