- Видео 227
- Просмотров 953 261
Data Science Basics
Финляндия
Добавлен 30 дек 2022
Hi, I am one of the data enthusiast like you ! On this channel, I teach data science as well as recent AI trend (LLM) stuffs in the most simplest manner possible.
Currently, video is one of the most important and go-to content type online. I aim to make Data Science Basics a go to RUclips Channel for videos surrounding data science stuffs in a practical way.
If you find the content helpful then consider subscribing.
For business inquiries email at: basicsdatascience@gmail.com
💼 Consulting: topmate.io/sudarshan_koirala
Currently, video is one of the most important and go-to content type online. I aim to make Data Science Basics a go to RUclips Channel for videos surrounding data science stuffs in a practical way.
If you find the content helpful then consider subscribing.
For business inquiries email at: basicsdatascience@gmail.com
💼 Consulting: topmate.io/sudarshan_koirala
Building no-code AI Agents Using LangFlow | For Complete Beginners
In this beginner-friendly tutorial, we’ll explore how to build AI agents without writing any code using LangFlow-a powerful low-code platform designed for creating AI applications. LangFlow simplifies the development of AI agents by providing a visual interface where you can connect pre-built components to design complex workflows effortlessly.
What You’ll Learn:
Introduction to LangFlow: Understand the basics of LangFlow and its role in building AI agents.
Setting Up Your Environment: Step-by-step guidance on installing and configuring LangFlow for your projects.
Creating Your First AI Agent: Learn how to use LangFlow’s drag-and-drop interface to build an AI agent from scratch.
Link ⛓️💥
www....
What You’ll Learn:
Introduction to LangFlow: Understand the basics of LangFlow and its role in building AI agents.
Setting Up Your Environment: Step-by-step guidance on installing and configuring LangFlow for your projects.
Creating Your First AI Agent: Learn how to use LangFlow’s drag-and-drop interface to build an AI agent from scratch.
Link ⛓️💥
www....
Просмотров: 122
Видео
Building no-code low-code RAG Application Using LangFlow
Просмотров 34512 часов назад
In this video, I will explore Langflow, a no-code low-code tool for building AI applications using drag-and-drop functionality. The video is divided into two parts: the first shows creating simple chat applications and second creating retrieval-augmented generation (RAG) applications using Lang Flow's managed service. Langflow is a low-code app builder for RAG and multi-agent AI applications. I...
Mastering Document Parsing with LlamaParse from LlamaIndex: Complete Guide
Просмотров 784День назад
In this video, I will walk you through the document parsing using LlamaParse from LlamaIndex. LlamaParse allows you to securely parse complex documents such as PDFs, PowerPoints, Word documents and spreadsheets into structured data using state-of-the-art AI. LlamaParse is available as a standalone REST API, a Python package, a TypeScript SDK, and a web UI. First, I will walk you through the UI ...
Building Your First AI Agents With Phidata & models from Groq | Beginners Guide
Просмотров 6 тыс.14 дней назад
In this video, I will show how you can create a simple agent, multi-agent using Phidata. We start with the basics of setting up an AI project in a virtual environment, proceed with creating individual agents such as a web search agent using DuckDuckGo and a finance agent utilising Yahoo Finance. We then demonstrate how to combine these agents into a multi-agent system and run everything from th...
Docling from IBM | Open Source Library To Make Documents AI Ready | LlamaIndex
Просмотров 1,1 тыс.14 дней назад
Dive into the capabilities of IBM's open source AI tool, Docling, designed for efficient document parsing and exporting. This video explores how DocLink works, its easy-to-use interface, and its ability to handle various document types including PDFs, DOCX, PowerPoints, and more. The video covers setting up the environment, basic and advanced features, and integrating Docling with Lama Index fo...
Get Started With Github Copilot Free in Visual Studio Code 🔥
Просмотров 95721 день назад
In this video, I will explore how to set up and use GitHub Copilot in VS Code effectively. Learn about the announcements made on December 18th regarding GitHub Copilot's free plan, how to configure it, and various commands you can run. We also cover privacy settings, creating projects from scratch or existing ones, generating commit messages, and using Copilot Edit for multi-file editing. Perfe...
Extremely Fast Python Package Manager | written in Rust 🚀
Просмотров 68228 дней назад
In this video, we explore UV, a versatile and ultra-fast tool for managing Python projects and packages. Learn how to install UV, initialise projects, manage dependencies, and utilize various useful commands. The video highlights UV's speed and efficiency in handling multiple Python versions, creating virtual environments, and running scripts. Discover why UV is a powerful alternative to other ...
All You Need To Know About Amazon Bedrock
Просмотров 38128 дней назад
In this video, I will cover the highlights of AWS ReInvent 2024 and take a detailed look into the updates and features of Amazon Bedrock. From exploring the Bedrock console UI, configurations, and newly added models in the Bedrock marketplace to advanced functionalities like prompt routers, model routing, and watermark detection, we guide you through all the essential aspects of Bedrock. Additi...
Top 5 Essential Resources for Learning Generative AI
Просмотров 344Месяц назад
In this video, I'll guide you through five essential resources for anyone interested in learning about AI, particularly generative AI. We start with Hugging Face, a platform for collaborating on machine learning models and applications. Next is DeepLearning.AI, founded by Andrew Ng, offering a variety of AI courses and practical applications. The third resource is a site that evaluates AI model...
aisuite: Unified Interface for Multiple Generative AI Providers
Просмотров 300Месяц назад
In this video, we dive into aisuite, an exciting new package from Andrew Ng and his team that provides a simple, unified interface to interact with multiple generative AI models, including OpenAI, LLaMA, and others. We explore its features, demonstrate installation and implementation steps, and highlight how it allows developers to switch and compare responses from different large language mode...
Mastering Prompt Engineering with LangSmith's Prompt Canvas
Просмотров 563Месяц назад
In this video, we dive into LangSmith's Prompt Canvas, an innovative tool for developing and optimising AI prompts. The video explores the user interface and features of Prompt Canvas as a simplified and efficient prompt creation experience inspired by OpenAI's canvas UX. The host demonstrates how to use the tool, provides walkthroughs of various functionalities like editing prompts, utilising ...
Exploring Open Canvas: The Open Source Alternative to ChatGPT Canvas
Просмотров 2,1 тыс.2 месяца назад
In this video, we will delve into Open Canvas from LangChain, an open-source alternative to ChatGPT Canvas. We explore its key features, including built-in memory, the ability to start from existing documents, and comprehensive UX for writing and coding. The video also provides a step-by-step guide on how to use Open Canvas both online and locally. Additionally, we discuss different functionali...
Maximize Your Efficiency: Exploring Canvas in ChatGPT for Writing and Coding
Просмотров 3712 месяца назад
In this video, I will explain the new 'Canvas' feature introduced by OpenAI in the paid version of ChatGPT. The tutorial covers using Canvas for both writing and coding, highlighting its interactive and dynamic functionalities. Learn how to open sections within Canvas, utilize quick shortcuts, perform advanced edits, and leverage the history feature. The coding section shows practical examples ...
ChatGPT Search & Alternatives
Просмотров 2012 месяца назад
In this video, I will explain into the newly enhanced web search functionality introduced by OpenAI in ChatGPT on October 31st, 2024. This updated feature, now available to Plus and Teams users and rolling out to free users soon, allows for internet searches directly within the chat interface, with results sourced from various partnered providers. We'll explore the interface, discuss its capabi...
Run GGUF models from Hugging Face Hub on Ollama and OpenWebUI
Просмотров 2,8 тыс.2 месяца назад
Discover how to run large language models locally on your computer using Hugging Face and Ollama in this comprehensive tutorial. Learn to navigate through an extensive collection of over a million models available on Hugging Face and easily run them with a single command. The video offers a step-by-step guide to downloading models into Ollama and managing them via Open Web UI 00:00 Introduction...
Prompt Generator From OpenAI | ANYONE Can Write Prompts With This New Feature
Просмотров 1,5 тыс.2 месяца назад
Prompt Generator From OpenAI | ANYONE Can Write Prompts With This New Feature
Super Easy Way To Parse Documents | LlamaParse Premium 🔥
Просмотров 1,9 тыс.3 месяца назад
Super Easy Way To Parse Documents | LlamaParse Premium 🔥
AI/BI Dashboards | Databricks New AI Powered Visualization Tool
Просмотров 1,4 тыс.3 месяца назад
AI/BI Dashboards | Databricks New AI Powered Visualization Tool
DATABRICKS AI/BI GENIE | No Code Interface For Your Data | Text TO SQL
Просмотров 7883 месяца назад
DATABRICKS AI/BI GENIE | No Code Interface For Your Data | Text TO SQL
Exploring Databricks Notebook: New Features and Functionalities Overview
Просмотров 6154 месяца назад
Exploring Databricks Notebook: New Features and Functionalities Overview
Open WebUI: Local ChatGPT Alternative | For Complete Begineers | Full Tutorial
Просмотров 17 тыс.4 месяца назад
Open WebUI: Local ChatGPT Alternative | For Complete Begineers | Full Tutorial
Extract Table Info From SCANNED PDF & Summarise It Using Llama3.1 via Ollama | LangChain
Просмотров 2,9 тыс.4 месяца назад
Extract Table Info From SCANNED PDF & Summarise It Using Llama3.1 via Ollama | LangChain
Installing and Using LangGraph Studio | First Agent IDE
Просмотров 3,6 тыс.4 месяца назад
Installing and Using LangGraph Studio | First Agent IDE
Introduction to LangGraph: Building and Enhancing LLM Agents
Просмотров 1,6 тыс.5 месяцев назад
Introduction to LangGraph: Building and Enhancing LLM Agents
Implementing Guardrails in Amazon Bedrock: A Step-by-Step Guide
Просмотров 7835 месяцев назад
Implementing Guardrails in Amazon Bedrock: A Step-by-Step Guide
Llama 3.1 | The Best LLM is now Open Source | TRY Locally & Online
Просмотров 9995 месяцев назад
Llama 3.1 | The Best LLM is now Open Source | TRY Locally & Online
Tools Available Now In HuggingChat 🔥
Просмотров 7477 месяцев назад
Tools Available Now In HuggingChat 🔥
Is it possible to use a local llama API instead of OpenAI's GPT?
you can install it locally and use local models. For i stalling locally you can refer to my another video Building no-code AI Agents Using LangFlow | For Complete Beginners ruclips.net/video/HwII8r43Fhc/видео.html
Thank you for this video. what is your experience with the performance of the solution. It seems that results is taking some time to be shown ?
My experience is pretty okay. Simple to use and the performance depends upon the llm you use. About latency, it might also depend from where you use the app as the vector database is hosted in US in the demo I showed but used from Europe.
If your pdf has both table and text it was not flattening the table into a sentence for embadding model to understand better.
table is flattened into markdown format so the llm can get info from the table. If you render the markdown, you can see it as table again.
Waiting for 2 next videos. 1. The part-2 2. Validation of the results of RAG
Great, you been great Koirala ji
Do i need to download the poppler and tessaract to use the unstructured api for pdf files?
If you use locally then yes, if you use the unstructured client then no.
@@datasciencebasics Thanks a lot for replying
Ahh, this is so cool! Thanks for including Phidata in your video!
You are welcome !
Can we use llama 3.2 and Faissa vector database provided by meta ?
Does a Phidata fine-tuned python agent app run on Vercel with a Nextjs app? I mean, is it compatible with JS on any deployment service?
It should be possible. While Phidata is primarily designed for Python-based AI applications, it’s not directly compatible with Next.js or Vercel’s JavaScript environment. However, you can still leverage Phidata in a Next.js application deployed on Vercel by creating a separate Python backend that uses Phidata and integrating it with your Next.js frontend.
Can these AI commands be limiting?
Great sir, Keep continue this series
Awesome video, thanks!
You are welcome !!
hey, this video was great, I just wanna know a few things from your experience. 1. How is Google's embedding model compared to Fast_Embedding or OpenAI. 2. Pinecone store vs Qudrant any difference? I suppose not. 3. Your chunk size is 2000 with 100 overlaps. How is this doing so far or have you lowered it in production to 80-20 ratio. 4. And please make a video on how to do context await chunking and how to use metadata and all to efficiently use vector db.
1:05:34 ... Thanks Bro... Not just your technical and AI skills are awesome.... you also rock as a presenter... and a tutor.... Keep up the good work... Wishing you a very very Happy New Year 2025... Rgds
You are welcome. Thanks for the feedback, always feels great to hear someone learning from my videos. Happy new yr to u 2 !!
Dude please give us something new, you did 99% what Kish naik did in previous turorial.
thanks sir make more such videos learn a lot
Can I deploy this llm via flutter??
Please do more detailed videos in MLFlow. I am interested to watch your videos on Databricks
can wew use this for my organization, (client) we have to parse pdf for client in data bricks cloud
Dai really love and appreciate your content, nepali ma pani banaunus na ekdam helpful hunxa hami jasto underprivileged harulai thank you
Why hindi audio track is not available 😢
Sir, great tutorial. I’m getting : I got - unauthorised api error, incorrect so I used Import os Os.env and input the api key Now I’m getting, Failed to call a function. Please adjust your print. See ‘failed generation’ for more details. If you can please help me out; that would be great. Thanks
hei, by just the info provided by you, I am not sure what is going wrong but if it is related to environment variables, there are diff ways to read env variables, here is one, import os # Hardcoding environment variables os.environ['MY_VARIABLE'] = 'my_value'
@@datasciencebasicsmust be a network error, it’s working now. I saw other comments calling you a copy cat, not supporting reposting but I’ve to say you added genuine value to it and that others are reposting the subject too (since it’s in the official documentation). I want to let you know that your content was better than the “original” in a way it helped me understand it more. Thank you, and I started using uv - made my life easier
Actually there’s still an error. If I put stream = False it shows max result = 1 but no capital’s name but if I put stream = True it shows connection failed Edit: changed groq model, it’s working for now
Glad that its working now and you got something new to learn out of it. Thanks !
What a beautiful video 😊
Thank you! 😊
Which browser are you using arc?
Yes, its arc browser!!
Make some unique tutorials We already have this in Krish Naik Tutorials
Thank you so much for such an eloquent insight for multi-agents. Appreciate the simplicity and instructional approach for an effective delivery of a challenging subject.
Bro try to make more videos , its really interesting .
Thank you, I will
Helpful video! Thank you
You are welcome, glad that the video is helpful!!
bro what browser is that, it looks sick
hei, its arc browser arc.net/
you are amazing, your explanations are so so easy to understand, keep up the good work Thank you!!!!
You are welcome. Glad that it was helpful!!
Thanks for this video. It would be interesting and useful to show how to handle multiple uploaded PDFs, not just a single one." 🙏🏻
could please tell , how to fetch job id and send it when failed to teams webhook notification
Hi sudarshan , could you please make video on fethcing job ID and sending notification for job failure to webhook teams
Hei, the simple way is to provide the email of the teams channel in the Email section and select the appropriate options, check this video ! Day 22: Databricks Workflows | 30 Days of Databricks ruclips.net/video/lJrzgQfH1tc/видео.html
Great effort 🎉 . But we are excepting a end to end project with etl, using aws as cloud.
Not sure what's the point of all this sophistication if you are going to present it while using GPT-4o-mini!!! Your video title mentions "Open Source Alternative to ChatGPT" whats the 'opensource' aspect of what you're sharing here!!!? Just the UI?? So, what!? sSimple html/js can do the whole trick!!! You literally demonstrated an opensource app while using API connected to GPT-4o-mini!!! Why you didn't demonstrate the whole thing with some LLM models??
Hei, I showed you with one of the model there but you can choose different models other than openai’s model. Also, as I mentioned in the video there are some additional features which are not in ChatGPT canvas. Thanks for the feedback!!
Thanks!
You are welcome, thanks for the support!!
This series is terrific. A real treasure. Thanks,
You are welcome. This kind of comment is what motivates me to create more content :) It feels great to know someone somewhere is finding it helpful 🙂
Very excellent video. Thank you for sharing your experience.
You are welcome, glad that it was helpful!!
Great video. I deployed this very same rag-app, but noticed it did not display😁 well on an mobile phone. Any thoughts? Beginner ove' here.
can you ask about a dataframe?
Very informative! Thanks for sharing
You are welcome, glad it was informative!!
This looks great. It takes a lot of the right things from cargo, npm, and composer ecosystems.
I need to know this step can I install into the conda enviroment?
you should be able to do it, give a try!
Thanks! It simplifies a lot of different commands for setting up a new project. I made a script for my environment but I'll consider uv for package maintenance.
But if i game now with one of those cloud gpus on, will it increase my fps.
give a try if it helps, haven’t tried myself for games.
Thanks sir. I have a question, is it possible to create a tool using GenAi which can ingest pdf documents of varying structure and then extract specific data dynamically and pass it as a context into LLM?
hello, you can check Llamaparse from LlamaIndex. here is one of the video I created, ruclips.net/video/S_F4RUhKaV4/видео.htmlsi=hjbSttAqOn85_wUV
@ Thank you 🤩
You explained something really important here. First that Llama2 model can do vector embeding RAG And you showed that nomic-embed-text can do the same RAG embeding, but nomic-embed-text it is alot better and it definetely it is alot faster. I mean the speed differance is insane!! Thank you for showing that.
Please create one detailed video on End to End machine Learning experiment with mlflow. This whole databricks playlist is superb :)
Thanks, all i ask is perfect table extraction with all the formatting and accuracy. what s my best bet?
You are welcome, you can give LlamaParse a try ruclips.net/video/S_F4RUhKaV4/видео.htmlsi=XHE98g6xAuh0u8jb
I using community version of databricks , the Repo isnt available? any work around?
in community edition, its not possible atm !!
thank u
You are welcome !