Multi-Agent RAG
HTML-код
- Опубликовано: 21 сен 2024
- Discover how to integrate multiple independent agents to tackle complex problems effectively using the latest frameworks like AutoGen, Crew AI, and LangGraph. We'll dive into the innovative multi-agent systems, particularly focusing on the shared scratchpad approach in LangChain, and demonstrate building an advanced Agent Supervisor model. This system enhances problem-solving by coordinating agents, each with their own scratchpads, under a supervisor that manages the final outputs. Whether you're a developer or just fascinated by AI's potential, join us to learn, interact, and get hands-on with the future of collaborative AI technology. Click now to be part of this journey into multi-agent systems!
Event page: lu.ma/agentrag
Have a question for a speaker? Drop them here:
app.sli.do/eve...
Speakers:
Dr. Greg, Co-Founder & CEO
/ gregloughane
The Wiz, Co-Founder & CTO
/ csalexiuk
Join our community to start building, shipping, and sharing with us today!
/ discord
Apply for our new AI Engineering Bootcamp on Maven today!
bit.ly/aie1
How'd we do? Share your feedback and suggestions for future events.
forms.gle/6NNY...
Multi-Agent Workflows + RAG - LangGraph: colab.research.google.com/drive/1LnNdVupNBysYERIbspdqp0l65no4a3zr?usp=sharing
Event Slides: www.canva.com/design/DAGEpXkkCnA/cPlEdmdBw9V2g0vNt2Jr1Q/view?DAGEpXkkCnA&
Interesting perspectives on combining several AI agents to solve complicated problems. eager to investigate these frameworks. #Innovation #Technology #MultiAgentSystems #AI
Thanks for the video. The moment i saw your compromising with 3.5 for something I said, well..
For some reason the video did not have the document writer code creation steps, but it is all cleared out once I see the notebook 🙂 Great content, thanks!
Glad the resources helped out!
Best quality videos, content and discussion style ever. Dope af!
Thank you!
Awesome. the slides and colab notebook are very helpful, this is a cool explanation from Dr Greg and Dr Chris
Thanks!
@AI-Makerspace Wonderful event and valuable content. Question, though, the notebook always finishes with the Research Team and never advances to the Writing Team. Can you please point me to where (I'm guessing somewhere in the supervisor function) I can find the bug? Thank you.
You might need to be explicit in the prompt that you want to go to the writing team if you're running into that!
Love it. Hilarious intro. Hyper dope.
We've gone....beyond dope.
Thanks for the video
Thank you for the tutorial. Always a pleasure watching your videos.
I did almost the same thing using LangGraph Github.
I just don't get the image of saying "fancy RAG". Because for me RAG is retrieving, while an agent can even write in an empty file for example. Could you please elaborate?
Other than that, I would be very much interested in tutorials using another framework like CrewAI. Thank you very much guys ❤
We're simplifying a bit - and more saying "Agents are often used as fancy RAG these days, and there's a lot left to discovered - even if it's just slightly fancier RAG".
Writing to files, sending messages, etc - are ultimately still being worked on and improved, and are more "logical progressions" rather than uniquely agentic.
Top
😵😵😵