- Видео 179
- Просмотров 301 653
AI Makerspace
Добавлен 28 янв 2023
Learn how to build, ship, and share production Large Language Model applications with us!
Drug Alert AI
DrugAlertAI is an AI driven innovative software that bridges the gap between pharmaceutical companies, healthcare providers and patients by ensuring that the latest drug information reaches doctors swiftly and accurately, enabling them to make the most optimal and timely decisions for their patients.
GitHub: github.com/KPGAData/drug-alert-ai
Slides: docs.google.com/presentation/d/1SBu2djEDJ32kRlf1zjM3P_6zF_zoONuSsO86zTcPh94/edit?usp=sharing
Connect with the team!
Krupakar Pasupuleti: www.linkedin.com/in/krupakar/
Sid Sanyal: www.linkedin.com/in/sidhartha-sanyal-47401410
Apply for an upcoming cohort of The AI Engineering Bootcamp!
maven.com/aimakerspace/ai-eng-bootcamp
GitHub: github.com/KPGAData/drug-alert-ai
Slides: docs.google.com/presentation/d/1SBu2djEDJ32kRlf1zjM3P_6zF_zoONuSsO86zTcPh94/edit?usp=sharing
Connect with the team!
Krupakar Pasupuleti: www.linkedin.com/in/krupakar/
Sid Sanyal: www.linkedin.com/in/sidhartha-sanyal-47401410
Apply for an upcoming cohort of The AI Engineering Bootcamp!
maven.com/aimakerspace/ai-eng-bootcamp
Просмотров: 126
Видео
3N1 (Neural Nomad Nexus): Manager Sales Assistant
Просмотров 14221 день назад
3N1 (Neural Nomad Nexus): Manager Sales Assistant
ReportWiz - An Intelligent Business Reporting Assistant
Просмотров 14421 день назад
ReportWiz - An Intelligent Business Reporting Assistant
Healthcare Technology Management LLM (HTM-LLM)
Просмотров 11228 дней назад
Healthcare Technology Management LLM (HTM-LLM)
Better 1:1's for Engineering Managers
Просмотров 23828 дней назад
Better 1:1's for Engineering Managers
Real Time RAG with Haystack 2 0 and Bytewax
Просмотров 1,2 тыс.3 месяца назад
Real Time RAG with Haystack 2 0 and Bytewax
Pulse AI: Personalized B2B Content Marketing, by Arthi Kasturirangan
Просмотров 2453 месяца назад
Pulse AI: Personalized B2B Content Marketing, by Arthi Kasturirangan
RagTime: Your Digital Second Brain, by Phil Mui
Просмотров 4153 месяца назад
RagTime: Your Digital Second Brain, by Phil Mui
Kevin: Your AI Pair Programmer, by Allan Tan
Просмотров 3523 месяца назад
Kevin: Your AI Pair Programmer, by Allan Tan
Teach2Learn: LLMs as Virtual Students, by Jerry Chiang and Yohan Mathew
Просмотров 1183 месяца назад
Teach2Learn: LLMs as Virtual Students, by Jerry Chiang and Yohan Mathew
PharmAssistAI: Easily navigate complex FDA guidelines, by Raj Kumar
Просмотров 4933 месяца назад
PharmAssistAI: Easily navigate complex FDA guidelines, by Raj Kumar
Anti-Money Laundering Compliance, by Miguel Costa
Просмотров 703 месяца назад
Anti-Money Laundering Compliance, by Miguel Costa
StudyBuddy: AI Assisted Exam Training, by Ursula Deriu
Просмотров 743 месяца назад
StudyBuddy: AI Assisted Exam Training, by Ursula Deriu
ClearPolicy: Insurance Policy Simplification, by André Fichel
Просмотров 1553 месяца назад
ClearPolicy: Insurance Policy Simplification, by André Fichel
Jupyter Notebook Tutor: An AI Agent that Teaches AI, by Julien de Lambilly
Просмотров 2113 месяца назад
Jupyter Notebook Tutor: An AI Agent that Teaches AI, by Julien de Lambilly
CaseCompass: An AI Companion for Support Agents, by Efrain Martinez
Просмотров 773 месяца назад
CaseCompass: An AI Companion for Support Agents, by Efrain Martinez
EchoLinkAI: Elevating Slack Communitcations with Agents, by Nithin Kamavaram
Просмотров 6203 месяца назад
EchoLinkAI: Elevating Slack Communitcations with Agents, by Nithin Kamavaram
ProPrepPal: Virtual assistance for Interviews, Meetings, and Conferences, by Shoshana and Mike
Просмотров 1093 месяца назад
ProPrepPal: Virtual assistance for Interviews, Meetings, and Conferences, by Shoshana and Mike
Good explain
Thanks!
In which live stream you have explained this fully ?
studio.ruclips.net/user/videomEv-2Xnb_Wk/edit
Event Slides: www.canva.com/design/DAGOfx2zV48/eUJk97tu-CwHZDtIPtSdbA/view?DAGOfx2zV48&
Insightful video on multi-agent systems. For advanced orchestration, explore SymthOS. #MultiAgentSystems #AI #SymthOS #Innovation
Interesting perspectives on combining several AI agents to solve complicated problems. eager to investigate these frameworks. #Innovation #Technology #MultiAgentSystems #AI
Great video. But one thing I am curious about is why is the input to fine tuning in reverse? I mean the asking the peft_model to generate instruction given response. How does one know a priori that is how the input ought to be preprocessed this way? I am trying to build a peft_model using the same base Mitral-7b, but in my case the data set is "fingpt-sentiment-train". This is a tweet with 5 different classes of sentiments. I am just passing the data set as is (with some pre-processing), i.e., give the tweet and get sentiment. Cheers Ram
Flowise has a langraph no code integration. It’s dope :)
💡
When llm don’t know the answer there is almost zero chance “she” told you about it. just gives you a wrong answer, and this is here interesting things start.
Great working its very important. Congratulations my friends
Thanks again guys!
Is there a student self paced style?
We do not yet have this kind of offering available! Stay tuned!
Question - this approach seems different and more advanced than the embedding training session on the llama papers with llama index. Is that one still a valuable approach, or has the world moved on?
That's still a fine approach!
Fantastic as usual!
Alex said Langsmith is only for langchain. That's not true. Langsmith has a video building agent monitoring with DSPy and they say it connects with anything. There's also several videos of langsmith and crew AI.
That's absolutely true, Andy! Great call out!
Great explanations + working tutorial codes sharing 👍
Fine-tuning Embedding Models for RAG: colab.research.google.com/drive/1Y_c5lwK9ndImglAJfw5RBqQ9z3dr02q_?usp=sharing Event Slides: www.canva.com/design/DAGN1-w4e0w/oySipozjjqFc5Rk8kJCfVw/view?DAGN1-w4e0w&
This was such a helpful and thorough explainer for how and where to use synthetic data generation. Love that you included dope or nope😂
is this approach really legit? never heard of it till now. and has it been peer reviewed by others?
Without belabouring the definition of the word "legit", yes! This is a method of PEFT which has been proven to work across a number of different applications, models, and more.
Dr. Greg is an outstanding teacher and presenter! His pacing makes complex topics easy to understand, and his clear articulation of every point is exceptional. Truly one of the best on RUclips! The material for the presentation was expertly crafted and delivered. Thanks!
You're quite welcome @donconkey1! Let's goooooo! DSPy for Agents coming soon - see you there!
First!!
Spectrum - LegalEasy Example - AIM/Arcee AI: colab.research.google.com/drive/1jGt5EO9dcYZaHlGdC5pZg4amK0zM_R5M?usp=sharing Event Slides: www.canva.com/design/DAGNS7ZS5Vk/i1v5UE4Stj08AElFPvwp6A/view?DAGNS7ZS5Vk&
Fascinating deep dive into Mixture of Agents (MoA)! 🧠🚀 This video brilliantly explains how MoA pushes the boundaries of AI by combining multiple LLMs. As someone deeply interested in AI innovation, I was inspired to create my own project based on these concepts. For those curious about a practical implementation of MoA principles, check out MALLO (MultiAgent LLM Orchestrator) that I developed: github.com/bladealex9848/MALLO MALLO integrates local models, OpenAI and Together AI APIs, and specialized assistants, all orchestrated to handle complex queries efficiently. You can try it live here: mallollm.streamlit.app/ This project demonstrates the real-world potential of MoA to enhance performance and accessibility of advanced AI. It's exciting to see how concepts like multi-headed self-attention mechanisms and Mixture of Experts are evolving into more sophisticated architectures like MoA. Dr. Greg's insights are invaluable for anyone looking to understand and implement these cutting-edge techniques. I'm curious to hear others' thoughts on how MoA might reshape AI applications across various industries. Thank you for this comprehensive walkthrough of MoA. It's truly inspiring to see the AI community pushing the boundaries of what's possible! 🌟 #MixtureOfAgents #MALLO #AIInnovation #MultiAgentLLM
Fantastic presentation as usual guys. You remain among the very best on RUclips in terms of pacing and delivery of complex concepts. One small gripe about today's broadcast (this affects neurodivergents like me, not "normal" people): The mic level of The Wiz was considerably lower than Dr. Greg's. This resulted in a "blast/strain to hear" effect in those of us with hearing challenges. Thanks so much for all your great work!!
We love your detailed feedback every time csmac! We'll see if we can make some adjustments for next time!
Synthetic Data Generation - RAGAS & LangSmith: colab.research.google.com/drive/1CyD4nLQ7RDc8iRJ9THXzcLiDhsB5ziDe?usp=sharing Event Slides: www.canva.com/design/DAGNL3ebUvE/esJuItg3T8YmvWDLaivrfg/view?DAGNL3ebUvE&
LFG 🎉🚀
💯 See you there 😎
Great video! How can I use RAGAS with Azure OpenAI flavour?
You can use the Azure OpenAI connectors for LangChain as your Critic and Generator!
Amazing!
This made my day, thanks for posting
Just made mine in return :) ... thanks for posting! - Dr. Greg
Mixture of Agents: colab.research.google.com/drive/1xvKLeRfXCudIEk7fmmovDB-YKmUiuqk3?usp=sharing Event Slides: www.canva.com/design/DAGMh5frA5Y/2ZYn-bCZCMetv-QMV6Z-eA/view?DAGMh5frA5Y&
I would like to test this out. Could you please put details of the step by step process to setup the project. Can you share the details in your GitHub. Looking forward to it. Thanks
WILL THIS AI HELP ME CLEAN MY BATHROOM?
We'd recommend going manual before automagical on Satan's Bathroom!
Ground truth generated by GPT-4? Not even remotely useful for local RAG! In fact, ground truth presupposes you know the question, not really typical of real world user interactions.
Thanks privacytest! This is an estute point - ground truth data is always better when it's generated by humans, but alas, it's so rare to find golden datasets generated that way out in the wild. The industry needs a path to eval and RAGAS was like "here's one!" ... moreover, the synthetic test data generation technique is quickly becoming more of an industry standard all the time. Check out next week's event to learn more and bring your questions live! bit.ly/data4enterprise
Thank you for this Great explanation. So much appreciated
Nice. Can it do soft prompt tuning?
Not as of the time of this comment, no.
@@AI-Makerspace ok thanks 😊
Can we use ragas without openai key
If you set-up LLMs and pass them as the Critic/Generator/etc - yes!
Still 720p. Why tho? That's the monitor standard from the 1990s. RUclips easily handles 8K video these days. 4K is standard on every other AI tech site on RUclips. Please fix guys -- your content is awesome but not every viewer is 25 and can effortlessly read blurry code.
Thanks csmac! We upgraded our streaming plan but didn't click the right setting! We are making sure to select 1080p streaming from now on!
easy peasy lemon squeezy!
great talk:)
Notebook colab.research.google.com/drive/1fXIeC9oQZr3ZNDZTSbyAJIzELRcnGYZg?usp=sharing
Cool webinar, provides a lot of insight, thanks!👌👌
Another great webinar and coverage of DSPy for agentic apps would be dope :)
Heard 😎
Improving LangChain RAG with DSPy: colab.research.google.com/drive/1fXIeC9oQZr3ZNDZTSbyAJIzELRcnGYZg?usp=sharing Event Slides: www.canva.com/design/DAGL31M6YKk/y07WGlNs_DrntO1zG8jxNQ/view?DAGL31M6YKk&
the best no code tool is Flowise Basically the only one
Thanks for sharing. I’m looking for a github link to its repo, if possible
Best place to go for that is straight to the source! github.com/explodinggradients/ragas
Would you share the link to the notebook please??
In the pinned comment! colab.research.google.com/drive/1TZo2sgf1YFzI4_U-tGppg_ylHAR3MXF_?usp=sharing
Amazing content! Thanks for sharing
the content and delivery are outstanding the hat is f*****g stupid we're not 8th graders, my man.
TRIED THIS MIGRATION AND OTHER SOLUTION VIA CHTGPT BUT STILL STRUGGLING
Can you expand on this?
this topic is very hardcore~~😇