[CODE4LIB] Convert MARCXML to SKOS XML file

Dear colleagues, Does anyone know of a good application or script that converts MARCXML to SKOS XML? I found the following two scripts on github. Anyone have experience or comments to share? https://github.com/scriptotek/mc2skos https://github.com/lcnetdev/marcauth-to-madsrdf Thanks so much

[CODE4LIB] Registration is open for Faceted Subject Access Interest Group (FSAIG) program, ALA CORE Interest Group Week, March 5th at 1pm CST

**Please excuse cross-posting** The CORE Faceted Subject Access Interest Group (FSAIG) is pleased to host three presentations during the CORE Interest Group Week 2024. The session is free to attend and open to the public. Date: March 5, 2024 (Tuesday) Time: 2:00-3:00 pm (EST)/1:00-2:00 pm

[CODE4LIB] interactive whiteboards?

Does anyone here have/support interactive whiteboards? I suppose "dumb" whiteboards with some kind of "smart" projector/camera would be comparable. Any comments and/or suggestions on brand or features to look for (or against)? Ideally, these would not require accounts although Microsoft 365 c

[CODE4LIB] Travel Scholarships: IIIF Annual Conference

Hello all, The IIIF Consortium is pleased to announce two travel scholarships to attend the 2024 IIIF Annual Conference in Los Angeles, CA. The scholarship will provide up to $2,000 in travel funds to recipients with the goal of fostering a conference environme

[CODE4LIB] genrative ai; fine-tuning and rag

Who out here in Code4Lib Land is practicing with either one or both of the following things: 1) fine-tuning large-language models, or 2) retrieval-augmented generation (RAG). If there is somebody out there, then I'd love to chat. When it comes to generative AI -- things like ChatGPT -- one of t

Re: [CODE4LIB] Call for Volunteers: Code4Lib Community Support Squad & Co-coordinator

Hello everyone, This is a friendly reminder that today is the last day to volunteer for the Community Support Squad at Code4Lib 2024. Please fill out the form if you are interested. https://forms.gle/cfCVvCcAsh4jgHNU6 Thank you! Best, Soojeong Soojeong Herring (she/her) Cataloging and Metadata

Re: [CODE4LIB] genrative ai; fine-tuning and rag

Eric - it sounds like we may be at about the same point: I am wanting to start working in the area of fine-tuning, specifically focusing on Chat-GPT generated data management plans that would then be revised by experts and used as a fine-tuning data corpus for (hopefully) improving the draft DMP

Re: [CODE4LIB] genrative ai; fine-tuning and rag

I took note of something recently from the Library Innovation Lab at Harvard Law School: WARC-GPT: An Open-Source Tool for Exploring Web Archives Using AI. It takes the contents of WARC files and feeds them into a Retrieval Augmented Generation tool. Been meaning to play with it as a way to enha

Re: [CODE4LIB] genrative ai; fine-tuning and rag

I think it's important to ask first what your aims are with a LLM. Personally I have never seen a valid use-case for ChatGPT or any of its varieties in libraries. These models are, ultimately, little more than glorified text compressors[1] that perform pattern-matching and which do not, and cannot

Re: [CODE4LIB] genrative ai; fine-tuning and rag

I and other LibraryThing developers have done a lot of this work in the process of making Talpa.ai, so here's my quick take: 1. Fine-tuning is a poor way to add knowledge to an LLM, especially at scale. It's mostly useful for controlling how LLM "thinking" is presented—for example ensuring clean,

Re: [CODE4LIB] genrative ai; fine-tuning and rag

Talpa is a fascinating project--thanks for working on it! I've been trying to spend more time with various LLMs lately in an attempt to be able to speak less foolishly about them (eh), but my eight-year-old child unwittingly provided the most interesting use case I've attempted so far: "In Which Bi

Re: [CODE4LIB] Custom Browser Message?

Wow. Thanks so much, Kaleb. I started looking into modifying that xhtml file, and found those waters I waded into to be quite deep. I only got so far, but I came across mention of code signing that one would come across, and how that security makes it difficult to make modifications. With my ti

Re: [CODE4LIB] Custom Browser Message?

p.s. One thing I neglected to mention is the need to determine the site addresses for content providers such as Syndetics, and to add them to the system's local hosts file; otherwise, there will be missing content and placeholders hither and yon. Dealing with Google is a challenge, as I can't very

Re: [CODE4LIB] genrative ai; fine-tuning and rag

Gary Price did a presentation for CDL last week, the bullet points of which are here: bit.ly/CDLgpt (warning, that's a bit of a firehose), Gary mentioned RAG a bit. Based on his suggestion, I've been trying out phind.com which uses RAG. Phind works as both an AI chat, as well as a search engine. I

Re: [CODE4LIB] genrative ai; fine-tuning and rag

Well said, Alex – couldn’t agree more. If content for these tools has been paid for and not stolen (or there’s an agreement for open access material to be relied on), then I have no problem with them. Patricia Farnan (she/her) | Application Administrator, Discovery Services University Library