a rag rests on top of a jet engine with the word "RAG" written on the side. --chaos 30 --ar 4:3 --style raw --personalize qko3v53 --v 6.1

(RAG) Retrieval-Augmented Generation News: Week Ending 07/05/2024

July 5, 2024

a rag rests on top of a jet engine with the word “RAG” written on the side. –chaos 30 –ar 4:3 –style raw –personalize qko3v53 –v 6.1

GraphRAG: Unlocking LLM discovery on narrative private data – Microsoft Research

GraphRAG: Unlocking LLM discovery on narrative private data

“GraphRAG is now on Github! I first heard of GraphRAG from @emileifrem at @aiDotEngineer a week ago, in the context of @neo4j , then had a random chat over lunch with a @alexchaomander who worked on it at Microsoft! I will dive deeper and talk about it on @thursdai_pod 👀” / X

GraphRAG is now on Github!

I first heard of GraphRAG from @emileifrem at @aiDotEngineer a week ago, in the context of @neo4j , then had a random chat over lunch with a @alexchaomander who worked on it at Microsoft!

I will dive deeper and talk about it on @thursdai_pod 👀… https://t.co/lyRqkzpJA4
— Alex Volkov (Thursd/AI) (@altryne) July 2, 2024

“pretty cool approach 1. use LLMs to extract a knowledge graph from your sources 2. cluster this graph into communities of related entities at diff levels of detail 3. for RAG, map over all communities to create “community answers” and reduce to create a final answer” / X

pretty cool approach

1. use LLMs to extract a knowledge graph from your sources
2. cluster this graph into communities of related entities at diff levels of detail
3. for RAG, map over all communities to create "community answers" and reduce to create a final answer https://t.co/PPDglOjTVw
— Travis Fischer (@transitive_bs) July 2, 2024

“🔍 RAG Pro Tip: Boosting LLM Context Usage Everyone talks about improving retrieval, but what about getting LLMs to actually use that context? IME LLMs use info from function calls far more effectively than info in their general context. Super short example 🧵” / X

🔍 RAG Pro Tip: Boosting LLM Context Usage

Everyone talks about improving retrieval, but what about getting LLMs to actually use that context?

IME LLMs use info from function calls far more effectively than info in their general context.

Super short example 🧵
— Adam Azzam (@AAAzzam) July 1, 2024

“The limitations of RAG are becoming very apparent. Retrieval is hard. Embeddings are kind of nice but don’t always work well. Still not clear how to keep your embedding store updated as the original information changes. Long context windows looked promising, but models don’t” / X

The limitations of RAG are becoming very apparent.

Retrieval is hard. Embeddings are kind of nice but don't always work well. Still not clear how to keep your embedding store updated as the original information changes.

Long context windows looked promising, but models don't…
— Santiago (@svpino) July 1, 2024

“🦛 HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models HippoRAG is a novel RAG framework inspired by the neurobiology of human long-term memory that enables LLMs to continuously integrate knowledge. Code:

🦛 HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

HippoRAG is a novel RAG framework inspired by the neurobiology of human long-term memory that enables LLMs to continuously integrate knowledge.

Code: https://t.co/kibxZ2nxRE pic.twitter.com/H4Xwn3gSuE
— LangChain (@LangChainAI) June 30, 2024

“🧠 Improving Memory for AI: How New Computer achieved 50% higher recall with LangSmith With their innovative agentic memory system, Dot, the @newcomputer team needed a new way (and not just standard RAG) to iterate quickly and improve memory retrieval. With LangSmith, New

🧠 Improving Memory for AI: How New Computer achieved 50% higher recall with LangSmith

With their innovative agentic memory system, Dot, the @newcomputer team needed a new way (and not just standard RAG) to iterate quickly and improve memory retrieval. With LangSmith, New… pic.twitter.com/l98HBLv44X
— LangChain (@LangChainAI) July 2, 2024

“Epic talk on RAG Basics by @jobergum from the LLM conf (links to YT, slides, etc in next tweet)

Epic talk on RAG Basics by@jobergum
from the LLM conf (links to YT, slides, etc in next tweet) pic.twitter.com/eKf2WS8Wi6
— Hamel Husain (@HamelHusain) July 1, 2024

Heads up! You’ve scrolled to the end of this category. There may have been just one or two links (above), so go back up and double check to be sure you didn’t quickly scroll down past it.

Be Sure To Read This Week’s Main Post:

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

AI News #40: Week Ending 07/05/2024 with Executive Summary and Top 65 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.