Marian Olteanu

How do the costs compare of implementing a low-latency write-ahead-log (WAL) on S3 Express One Zone and one implemented as a State-Machine-Replication (SMR) system (such as Paxos/Raft/Kafka)? I built a cost model for both to find out. https://lnkd.in/dwczVutW

43

5 Comments

With the announcement of S3-native-streams (Freight clusters), here is a commentary on Confluent strategy regarding object storage, streaming and an open data architecture. https://lnkd.in/dTg6DKVy

49

6 Comments

Still one of my favorite research papers from 2024. Anyone who is working in document processing and integrating LLMs has wondered what the best document schema is to show prompt based LLMs. Plain text? JSON? Markdown? Love this paper because it shows what the best one is, as well as what the bad ones are: https://lnkd.in/eN-ChhwX

8

Check out the latest in our "Debuggability" blog series! This blog is authored by Kevin Downey Jason Johl and me and talks about how we built a Debuggability Paved Road at Intuit using Ephemeral Containers and Argo Workflows. We'd love to hear your thoughts on the topic. Also, what tools do you build as-a-platform to help debug service, compute and network issues in Kubernetes at scale? #intuit #kubernetes #debug

23

FlashInfer v0.2 is here, a lot of technical upgrades, great news for anyone are doing custom attention improvement or just benefit it implicitly from integration of LLM frameworks

39

Hey everyone, I am an investor and advisor to Katanemo.... They are reinventing the infrastructure primitives for GenAI and launched Arch - https://lnkd.in/gCrbbkEV - an intelligent prompt gateway. Give the project a look on Github, and star the project if it resonates

88

3 Comments

When you need to play with your data in Gen Ai, you need RAG and Chunking is one of the main component in the RAG framework while consuming or processing your data. Excellent post below describing how in different ways chunking in RAG can be implemented..

23

1 Comment

In the era of LLMs, "sexy" might not be the term, but bag-of-words solutions are still kicking! When the position of a word matters, consider using Positional Vectorizer over TFIDF. Check it out: https://lnkd.in/dDRYFrAX

14

1 Comment

Insightful how multi-agent AI can provide a better solution to many problems.

2

2 Comments

Sharing my experiment on creating a Streamlit based chatbot, that combines inputs from Agentic RAG using llamaindex (with openai and MistralAI), and langchain google genai (with Gemini-1.5-Flash), to extract information from images embedded within the PDF files. Was a nice experience to build this chatbot. Still many open questions, ways to improve the solution, in a production scenario..but nice to combine features from multiple libraries and come up with a solution. Please check it out! Thanks. #chatbot #gemini #openai #langchain #llamaindex https://lnkd.in/gPdtxhQF

19

Now we need to start thinking about bugs in #LLM. "Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps" https://lnkd.in/g-gnKbbp

1

Project update! My application tracking extension is now doing fuzzier matching and injecting new information into LinkedIn (and other sites) to keep me from doubling up on applications. Next up: local storage and bulk import/export operations...

12

2 Comments

Long-term memory is "just" a built-in document store that supports `get`, `put` and `search`. But that simplicity is for a reason. We see that memory is still application specific - and so want to give developers low-level building blocks to use In many ways, memory is similar to agents: - Both are highly hyped - Both are hard to define - For both, we see that application specific implementations (e.g. vertical) are winning

171

7 Comments

Automating browser-based workflows using LLMs is full of promising opportunities. Existing approaches tend to involve drawing marked bounding boxes around interactive elements and then asking the LLM to drive a web scrape using HTML elements. https://www.skyvern.com/ #LLM

1

Our little book from Accord Project maintainers is now on Amazon: "This book introduces computable contracts, also referred to as smart legal contracts. It emphasizes the integration of legal text with machine-readable data and executable logic as a solution to inefficiencies in contract management. It also explores the application of large language models (LLMs) and natural language processing (NLP) for computable contracts." https://lnkd.in/eZ8Fb_5F

43

4 Comments

Most popular LLM applications inherently have data privacy risks. In this blog post, I discuss these risks, and how to use Tonic Textual to alleviate them. https://lnkd.in/gnySvecq

13

First story on what we have been up to at Augment. Much more to come! https://lnkd.in/gC6gbADA

370

64 Comments