Ethan B. Holland

Over 51,300 manually organized AI links and counting

A fashion photoshoot of a runway look inspired by dish rags. A large screen displays the word "RAG" --ar 4:3 --style raw

(RAG) Retrieval-Augmented Generation News: Week Ending 06/07/2024

June 7, 2024

A fashion photoshoot of a runway look inspired by dish rags. A large screen displays the word “RAG” –ar 4:3 –style raw

Nvidia and Salesforce double down on AI startup Cohere in $450 million round, source says | Reuters

https://www.reuters.com/technology/nvidia-salesforce-double-down-ai-startup-cohere-450-million-round-source-says-2024-06-04

“We’re excited to launch our startup program to empower early-stage AI innovation solving real world business challenges! Apply here:

We’re excited to launch our startup program to empower early-stage AI innovation solving real world business challenges!

Apply here: https://t.co/kGSKAicWWC https://t.co/pJBm2tWyUa
— cohere (@cohere) June 6, 2024

“We’ve released a library of useful cookbooks to help you get started building powerful AI applications, like agents, with RAG and semantic search, with Cohere’s frontier models to tackle enterprise-grade workloads! Find them here:

We’ve released a library of useful cookbooks to help you get started building powerful AI applications, like agents, with RAG and semantic search, with Cohere’s frontier models to tackle enterprise-grade workloads!

Find them here: https://t.co/OPQTjq8GlN pic.twitter.com/Y37sgGJcuJ
— cohere (@cohere) June 5, 2024

“HippoRAG is able to obtain comparable performance to iterative RAG methods (IRCoT) while being 10-30x faster and 6-13x cheaper. 🤯 Paper – ‘HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models’ IRCoT is an approach for multi-step QA that interleaves

HippoRAG is able to obtain comparable performance to iterative RAG methods (IRCoT) while being 10-30x faster and 6-13x cheaper. 🤯

Paper – 'HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models'

IRCoT is an approach for multi-step QA that interleaves… pic.twitter.com/YPUpGfPQp8
— Rohan Paul (@rohanpaul_ai) June 6, 2024

“Here’s a full video tutorial on building enterprise RAG with Bedrock + @ragas_io 💫 We hosted Jithin from @ragas_io and Ayan from AWS on a comprehensive workshop: 1. Learn the basics of Bedrock models with Ayan, and agentic RAG design patterns from @jerryjliu0 2. Learn the

Here’s a full video tutorial on building enterprise RAG with Bedrock + @ragas_io 💫

We hosted Jithin from @ragas_io and Ayan from AWS on a comprehensive workshop:
1. Learn the basics of Bedrock models with Ayan, and agentic RAG design patterns from @jerryjliu0
2. Learn the… pic.twitter.com/nSaYjVot4k
— LlamaIndex 🦙 (@llama_index) June 5, 2024

“Prometheus-2: an open-source LLM to evaluate your RAG application! Using an LLM as a judge is a popular way to evaluate RAG applications, but folks worry about transparency, controllability, and affordability. While GPT-4 remains the most commonly used LLM as judge evaluator,

Prometheus-2: an open-source LLM to evaluate your RAG application!

Using an LLM as a judge is a popular way to evaluate RAG applications, but folks worry about transparency, controllability, and affordability. While GPT-4 remains the most commonly used LLM as judge evaluator,… pic.twitter.com/LXWiWTJc5B
— LlamaIndex 🦙 (@llama_index) June 5, 2024

This week’s executive overview and top links are here:

AI News #36: Week Ending 06/07/2024 with Executive Summary and Top 40 Links

The post you just read is an deep dive extension of my weekly newsletter, This Week In AI, an executive summary of the top things to know in AI. Each week, I create an accessible overview for laypeople to feel confident they are conversant with the week’s AI developments. I include a curated list of must-click links of the week, to offer everyone a hands-on opportunity to explore the most intriguing updates in artificial intelligence across various categories, including robotics, imagery, video, AR/VR, science, ethics, and more. Beyond the overview, I post these topic-based deeper dives (below). If you haven’t read this week’s overview, I recommend starting there.

Credits/Sources

Most of these weekly links come from just a few prolific oversharing sources. Please follow them, as they work hard to find the news each week and they make it a lot easier for me to compile.