Rapid Retrieval: Architecting Real-Time RAG with Bytewax
Are you looking to build an LLM app but unsure which technologies to choose? Let the organizer, Yujian Tang, who explored over 80 companies in his April review, guide you through the landscape of AI tools at the 2024 Mid Year Gen AI Zoo!
Technology Selection: Learn how to choose the right technologies for your LLM stack. Connect with Innovators: Engage with the creators of the AI tools.
What to Expect:
Who will be our speaker ā”ļø
Networking
Make sure to join the Discord channel for all event communications:
ā Ask questions;
š¬ Engage in discussions;
š Stay informed about all the details.
Rapid Retrieval: Architecting Real-Time RAG with Bytewax
Zander will be talking about the requirement and importance of real-time data for Generative AI applications.
Why is streaming so critical for Generative AI applications?
Data is continuously being generated at an incomprehensible rate .5ZB per day.
Large language models will converge in their capabilities and differentiation will happen in the real-time data layer.
Streaming and stream processing is critical as part of the architecture to support this
If you missed the 2024 Mid-Year Gen AI Zoo online event, you can watch the full :grin: 5-hour recording here:
The Full Agenda*
8:00 - 8:05 - Introduction and Community Overview
8:05 - 9:35- Lightning talks
8:05 - 8:20 - Creating Aligned, Domain-Specific Evals with HoneyHive - Mohak Sharma, HoneyHive
8:20 - 8:35 - Rapid Retrieval: Architecting Real-Time RAG with Bytewax - Zander Matheson, Bytewax
8:35 - 8:50 - Building Workflows with Function Calling LLMs, Aravind Putrevu, Fireworks
8:50 - 9:05 - Evaluating Different RAG Approaches, Viraj Ratnalikar, n8n
9:05 - 9:20 - Multimodal RAG, Frank Liu, Zilliz
9:20 - 9:35 - Privacy-preserving augmented RAG approach, Fabiana Clemente, YData
9:40 - 10:20 - Keynote: How to Pick Your LLM Stack
10:20 - 10:30 - Break
10:30 - 2:15 - Tech talks
10:30 - 11:00 - TBA, Philip Vollet, Weaviate
11:00 - 11:30 - Manage, Visualize and Search Video Data on Your Laptop, Dr. Danny Bickson, Visual Layer
11:30 - 12:00 - Accelerating LLM Workflows with NVIDIA and Open-Source Integrations, Jay Rodge, NVIDIA
12:00 - 12:30 - Building LLM Evals That Work IRL - Aparna Dhinakaran, Arize
12:30 - 12:45 - Break
12:45 - 1:15 - Matrix Multiplication Free LLMs, Jason Eshraghian, UCSC
1:15 - 1:45 - A Database for Multimodal AI, Vishakha Gupta, ApertureData
Networking in: https://discord.gg/JZKkhvR74Q
Zander Matheson
CEO, FOUNDER