Olena's Data & Engineering Corner
Olena's Data & Engineering Corner
  • 33
  • 8 776

Video

LangChain tutorial: connecting Amazon Bedrock LLM with OpenSearch | Complete code example
zhlédnutí 59Před dnem
GitHub repo: github.com/anelook/rag-langchain-bedrock-opensearch-example-simple Create Aiven account and get extra credits: go.aiven.io/olena-youtube
Integrating Amazon Bedrock with pub/sub for AI agent communication
zhlédnutí 76Před 14 dny
GitHub repo - github.com/anelook/agents-aws-valkey-simple-chat Sebi's agent project using Java czcams.com/video/gunH0ggRm9w/video.html Register with Aiven (with extra credits) - go.aiven.io/olena-youtube
A mafia game with Generative Agents and OpenAI | Complete code example
zhlédnutí 205Před měsícem
Github repo: github.com/anelook/mafia-game-generative-agents
Send simulated flight data to Apache Kafka topic | Air traffic simulation project (Part 3)
zhlédnutí 184Před měsícem
GitHub repo: github.com/anelook/air-traffic-simulator Previous parts: - czcams.com/video/GsHb7GnUQAA/video.html - czcams.com/video/3l88JR-qf60/video.html
Build a generative agent with JavaScript and OpenAI
zhlédnutí 281Před měsícem
In this video we create step by step a generative agent by providing a personality and seeing what they GitHub repo: github.com/anelook/generative-agents
Visualize Air Traffic with JavaScript | Air traffic simulation project (Part 2)
zhlédnutí 48Před měsícem
github.com/anelook/air-traffic-simulator In this video we'll add a map for the air traffic simulator that we created in czcams.com/video/GsHb7GnUQAA/video.html
Create air traffic simulation script with JavaScript | Air traffic simulation project (Part 1)
zhlédnutí 1,2KPřed 2 měsíci
GitHub: github.com/anelook/air-traffic-simulator/ In this video we'll build a script that takes a schedule for numerous flights and returns information on their locations and statuses on a regular interval imitating air traffic APIs.
Apache Flink: processing data with OpenAI (Java)
zhlédnutí 238Před 2 měsíci
GitHub repo: github.com/anelook/apache-flink-openai-demo/tree/main
Host Apache Kafka producer in EC2 and NodeJS
zhlédnutí 40Před 6 měsíci
In this tutorial I'm showing how to create EC2 instance, set up NodeJS the, clone github repo and run Kafka producer that uses KafkaJS client to send data to Apache Kafka topic. curl -fsSL deb.nodesource.com/setup_20.x | sudo -E bash - sudo apt-get install -y nodejs sudo apt-get install -y git git clone github.com/anelook/produce-data.git scp -i "your-keys.pem" -r certificates/* ubuntu@your-ec2...
Filter out offensive content with HuggingFace model and SageMaker
zhlédnutí 121Před 6 měsíci
In this video I show how to deploy a model cardiffnlp/twitter-roberta-base-offensive from HuggingFace into SagemMaker and run the inference.
Using JumpStart models in Code Editor in the new SageMaker Studio
zhlédnutí 323Před 7 měsíci
From November 30 2023 SageMaker Studio has been redesigned and some of the features has been moved into SageMaker Studio Classic. In this video I show how to use updated new SageMaker Studio and its Code Editor to work with a JumpStart model. In this video we'll deploy a JumpStart text summarization model, create an endpoint, then using Code Editor create a Jupiter Notebook and call the endpoin...
AI Lexicon: Quantised models explained: why they matter and how they work
zhlédnutí 127Před rokem
In this AI lexicon video we’ll discuss terms quantized models and full precision models. 00:00 Intro 00:10 Performance 00:34 Making inference faster 00:55 Quantization simply explained 01:55 The role of weights 02:56 Using Floats vs using Integers for calculations 03:51 CPU vs GPU 04:53 Speed gain 05:15 Accuracy issue and solutions
AI: what is inference, curated corpora, overfitting and underfitting for a model | AI Lexicon
zhlédnutí 542Před rokem
For this video I selected several more terms related to AI that might be confusing. We’ll cover what is inference, what does "curated corpora" means and what is the trouble with overfitting and underfitting for a model? 00:00 Intro 00:21 Inference 01:00 Curated corpora 03:19 Corpus vs dataset 04:40 Overfitting 07:09 Underfitting
AI Awesomeness: Top Highlights from June 2023
zhlédnutí 1,3KPřed rokem
In this video we’ll look at the most interesting and cool stuff that happened in the AI world in the past month 00:00 Intro 00:16 Voyager: An Open-Ended Embodied Agent with Large Language Models 01:41 Break-A-Scene: Extracting Multiple Concepts from a Single Image 03:00 Stability AI Clipdrop Launches Uncrop and Midjourney Zoom Out 03:43 QR Code AI Art Generator 04:12 Real-Time AI Image Generati...
AI Lexicon - GPT, Transformer, Weights and Context Window
zhlédnutí 549Před rokem
AI Lexicon - GPT, Transformer, Weights and Context Window
AI News Roundup: May 2023. From Bard & ChatGPT all the way to Open Source models and projects
zhlédnutí 421Před rokem
AI News Roundup: May 2023. From Bard & ChatGPT all the way to Open Source models and projects
From Espresso to Algorithms: Using Artificial Neural Networks to Predict Cafe Success
zhlédnutí 267Před rokem
From Espresso to Algorithms: Using Artificial Neural Networks to Predict Cafe Success
Understanding inverted indexes: the key to faster and more accurate search results
zhlédnutí 37Před rokem
Understanding inverted indexes: the key to faster and more accurate search results
New open source analogy to ChatGPT - Open Assistant by LAION
zhlédnutí 438Před rokem
New open source analogy to ChatGPT - Open Assistant by LAION
Decoding AI research paper: "Generative Agents: Interactive Simulacra of Human Behavior"
zhlédnutí 691Před rokem
Decoding AI research paper: "Generative Agents: Interactive Simulacra of Human Behavior"
OLTP vs OLAP. What's the difference?
zhlédnutí 106Před rokem
OLTP vs OLAP. What's the difference?
Search-engine vs Relational database. Which one to choose for search?
zhlédnutí 94Před rokem
Search-engine vs Relational database. Which one to choose for search?
Devnexus 2023. Atlanta, USA
zhlédnutí 215Před rokem
Devnexus 2023. Atlanta, USA
How bad data distribution impacts cluster? Best practices for data partitioning. Apache Kafka.Part 5
zhlédnutí 64Před rokem
How bad data distribution impacts cluster? Best practices for data partitioning. Apache Kafka.Part 5
How a partitioner works in Kafka? | Best practices for data partitioning in Apache Kafka. Part 4
zhlédnutí 146Před rokem
How a partitioner works in Kafka? | Best practices for data partitioning in Apache Kafka. Part 4
How many partitions you need for topic? Best practices for data partitioning in Apache Kafka. Part 3
zhlédnutí 128Před rokem
How many partitions you need for topic? Best practices for data partitioning in Apache Kafka. Part 3
Throughput, latency and lag | Best practices for data partitioning in Apache Kafka. Part 2.
zhlédnutí 189Před rokem
Throughput, latency and lag | Best practices for data partitioning in Apache Kafka. Part 2.
What is data partitioning? | Best practices for data partitioning in Apache Kafka. Part 1.
zhlédnutí 66Před rokem
What is data partitioning? | Best practices for data partitioning in Apache Kafka. Part 1.
Partitioning and keys. Ordering of records | Apache Kafka simply explained. Part 4.
zhlédnutí 238Před rokem
Partitioning and keys. Ordering of records | Apache Kafka simply explained. Part 4.

Komentáře

  • @sabarishwarang6212
    @sabarishwarang6212 Před 16 dny

    Is it possible to create separate python environments in the same code editor space?

    • @OlenaKutsenko
      @OlenaKutsenko Před 16 dny

      I haven't tried, however, I believe it is possible, since I believe that you can select an environment for every code chunk you run? What use case do you have where you'd need separate environments?

  • @andresfelipehiguera785

    Awesome!

  • @tonywhite4476
    @tonywhite4476 Před měsícem

    Very nice work.

  • @qwerty160899160899
    @qwerty160899160899 Před měsícem

    I started to recreate this myself. This looks awesome. Thank you so much

  • @gurjitsingh9285
    @gurjitsingh9285 Před měsícem

    awesome 👍

  • @Kiyaansh.kulkarni
    @Kiyaansh.kulkarni Před měsícem

  • @rishabhvishwakarma5745
    @rishabhvishwakarma5745 Před 2 měsíci

    pls provide the source code or the basic file for this

    • @OlenaKutsenko
      @OlenaKutsenko Před 2 měsíci

      github.com/anelook/air-traffic-simulator/

    • @rishabhvishwakarma5745
      @rishabhvishwakarma5745 Před 2 měsíci

      @@OlenaKutsenko thank you i thought that i have generate some data(json) using chatgpt😅😅 , but thanks😄🙏🙏

  • @chandanbn5668
    @chandanbn5668 Před 2 měsíci

    Source code

    • @OlenaKutsenko
      @OlenaKutsenko Před 2 měsíci

      github.com/anelook/air-traffic-simulator/

  • @arupde6320
    @arupde6320 Před 2 měsíci

    github ??????

    • @OlenaKutsenko
      @OlenaKutsenko Před 2 měsíci

      github.com/anelook/air-traffic-simulator/

  • @insensibility
    @insensibility Před 2 měsíci

    This is awesome!

  • @MunchingHero
    @MunchingHero Před 2 měsíci

    Great work Olena!

  • @rishabhvishwakarma5745
    @rishabhvishwakarma5745 Před 2 měsíci

    this kind of projects is good for clearing the basics of js , thanks for it

  • @harmanmax
    @harmanmax Před 2 měsíci

    it's really amazing Olena :) appreciate your efforts ,keep it up

  • @miketag4499
    @miketag4499 Před 3 měsíci

    Great video, thanks for sharing

  • @parttimelarry
    @parttimelarry Před 3 měsíci

    This is a great video, I'm gradually wrapping my head around this paper to try to understand another paper that was inspired by it

  • @user-pz5sx5yf5q
    @user-pz5sx5yf5q Před 5 měsíci

    Nice

  • @user-pz5sx5yf5q
    @user-pz5sx5yf5q Před 5 měsíci

    Nice video

  • @user-pz5sx5yf5q
    @user-pz5sx5yf5q Před 5 měsíci

    Nice class

  • @user-by8xu2xe1t
    @user-by8xu2xe1t Před 7 měsíci

    very good explaation

  • @brendagallagher599
    @brendagallagher599 Před rokem

    Promo sm

  • @respergu13
    @respergu13 Před rokem

    Great explanation , it’s useful how you can put weight to specific terms in a search to fine tune it as well.

  • @drakezen
    @drakezen Před rokem

    Very well explained! keep up the great videos

  • @respergu13
    @respergu13 Před rokem

    Was investigating open search for an e-commerce website, I think using no sql database has many benefits

    • @OlenaKutsenko
      @OlenaKutsenko Před rokem

      Yes, among other things, the flexibility around the data schema and speed with which the data is processed is impressive. Regarding OpenSearch, check OpenSearch Dashboards as well - it's a really cool and easy to use tool to discover data / look at analytics and so on.

  • @Davrv
    @Davrv Před rokem

    Great work!

  • @luciacerchie3394
    @luciacerchie3394 Před rokem

    This is lovely Olena! I also use cable headphones ;)

  • @sumans420
    @sumans420 Před rokem

    Thank you Olena for trying to explain about Kafka. I’m fairly new to Kafka so, looking forward to videos.

    • @OlenaKutsenko
      @OlenaKutsenko Před rokem

      Hope, they will be helpful! I'll try to follow the schedule Mon - Thu, so next video is coming already tomorrow :)