Kevin Cocco

we're launching a small number (3) of templates for common cognitive architectures these are configurable (choose LLM/vector store of your choice) Starting with: - ReAct agent - RAG chatbot - data enrichment (research) agent What should we add next?

# scheduling workloads to run on humans Some computational workloads in human organizations are best "run on a CPU": take one single, highly competent person and assign them a task to complete in a single-threaded fashion, without synchronization. Usually the best fit when starting something new. Comparable to "building the skeleton" of a thing. Other workloads are best run on a GPU: take a larger number of (possibly more junior) people and assign tasks in parallel: massively multi-threaded, requiring synchronization overhead. Usually a good fit for later stages of a project, or parts that naturally afford parallelism, comparable to "fleshing out" a thing when the skeleton is there. There's some middle ground here - sometimes you can imagine a multi-threaded CPU execution of a small team collaborating. A good manager will understand the computational geometry of the project at hand and know when to delegate parts of it on the CPU or on the GPU. One notable place where the analogy breaks down a bit is that the worst thing that can happen when you misallocate computer resources is that your program will run slower. But in human organizations it can be much worse - not just slower, but the result can be of lower quality overall, more brittle, more disorganized, less consistent, uglier. The most common stumbling point here is trying to parallelize something that was supposed to run on the CPU. In the common tongue, this comes from the misunderstanding that something can go faster if you put more people on it, usually leading to outcomes where something is "designed by a committee" - not only is the thing actually slower, but the philosophy is inconsistent, the entropy is high, and the long-term outcomes much worse. The opposite problem is more rare and usually looks like someone doing something repetitive, uninteresting or tedious, where they could really benefit from more help. I think this is one accidental advantage of startups - they lack resources of large companies and run compute on powerful CPUs, winning in cases where that is the right thing to do. Larger companies, especially in cases where something is deemed of high strategic importance, will almost always reach for too much parallelism. TLDR: Think about your project, its computational geometry, its inherent parallelism, and which parts are a best fit for a CPU or a GPU.

@isccarrasco @py2neo @pypi @technige EOL x.com/technige/statu…

Does someone know what happened with @py2neo ??? it is not possible to install it from @pypi, it seems like it was removed from there, any idea @technige ?

Space enthusiasts! Join #IAC2023 here NOW for the LIVE FIRESIDE CHAT with Elon Musk 🚀🌠 twitter.com/i/broadcasts/1…

@squeebo_nft @mattshumer_ If you do work on this ping me, have been working on LLM to build knowledge graphs... OpenAI functions are impressive at pulling structured data from documents Here is graph example of triples(Sub, Pred, Obj) : kcocco.github.io/don_quijote_86…

@mattshumer_ I was discussing something similar with a colleague. Given that organizations have tons and tons of documents, I was wondering if we could use LLMs to compact it into facts, enabling them to find conflicts or find these facts across a comprehensive document (avoiding embedding)

I'm trying to figure out a way to get LLMs to edit massive documents, without resorting to chunking, full-scale rewriting, etc. Will share findings as I make progress here. Follow along:

@DivGarg9 @MultiON_AI Yes, please

Plan to onboard 1000 folks next week to @MultiON_AI 🤩, who wants access? Our waitlist is now reaching 30k, and folks with the most referral signups & interesting use cases will be prioritized You can also reply on this thread below to get included in the first batch 👇

@langchain @fpingham Nice presentations today! Regarding the discussion on quick way to extract proper nouns in prompt @francisco Maybe check out #en_core_web_trf" target="_blank" rel="nofollow noopener">spacy.io/models/en#en_c… Parse time for this prompt 7ms

Webinar on SQL QA starting in ~25 minutes! Here's the main text-to-SQL prompt we use in LangChain: smith.langchain.com/hub/rlm/text-t… @fpingham was one of the original authors of this - excited to dive into the origins and evolution! crowdcast.io/c/cohrkdisz3zu

@hwchase17 This should help my RAG on old Spanish text (Don Quixote,…). Will use summary function (or SeamlessM4T) to create English translation embeddings to index the Spanish chunks. This pattern opens a ton of fun options! Nice work! @hwchase17 & @langchain team

🌲Multi Vector Retriever The basic idea: you store multiple embedding vectors per document. How do you generate these embeddings? 👨‍👦Smaller chunks (this is ParentDocumentRetriever) 🌞Summary of document ❓Hypothetical questions 🖐️Manually specified text snippets Quick 🧵

An underrated aspect of LLMs is using them for structured data extraction Extracting knowledge triplets is a great use case! I gave it our most recent blog post about @MultiON_AI (blog.langchain.dev/multion-x-lang…) and it came up with the below - how did it do @DivGarg9 ??

@_AlexLawrence 7

FIBONACCI SPIRAL rafael-araujo.com

@charlesmcnall @WasatchSnow Ermine maybe? a-z-animals.com/animals/ermine/

There is a mink living under my neighbor’s deck. Anybody know if these pose much of a threat to dogs or anything?

These are 9 observations over the course of 10 months at @redbuttegarden. I love exploring seasonal change, phenology, with children, PSTs, and Ts. What do you notice and wonder about the images? #NGSS #SciEd #UTSEEd

The gift to all of us

A new kind of program analysis is emerging: AI code analysis. Here is the current state of analysis and where I think it’s headed:

The @SpaceX @Inspiration4x launch, endlessly flowing from the pad all the way to orbit. Composite of multiple tracking telescopes using new techniques to bring out the faintest colors and finest details--in 10K resolution. #EndlessInspiration

Exhale, everybody.

@draecomino $MCM quantum resistance

What's the blockchain with the highest ratio of technical innovation vs. marketing?

Very nice praise for The Long Tail, 15 years after its publication. "Five business books I wish I'd read earlier"