txtai VS Vespa.ai

I tend to agree with this sentiment. Many junior devs and/or those in college want to contribute. Then they feel entitled to merge a PR that they worked hard on often without guidance. I'm all for working with people but projects have standards and not all ideas make sense. In many cases, especially with commercial open source, the project is the base of a companies identity. So it's not just for drive-by ideas to... - Source: Hacker News / 17 days ago

Bootstrapping only works if you have the runway to do it and you don't feel the need to grow fast. With NeuML (https://neuml.com), I've went the bootstrapping route. I've been able to build a fairly successful open source project (txtai 6K stars https://github.com/neuml/txtai) and a revenue positive company. It's a "live within your means" strategy. VC funding can have... - Source: Hacker News / 3 months ago

I agree that in many cases people are puffing their feathers to try to be something they're not (at least not yet). Some believe in the fake it until you make it mentality. With NeuML (https://neuml.com), the website is a simple HTML page. On social media, I'm honest about what NeuML is, that I'm in my 40s with a family and not striving to be the next Steve Jobs. I've been able to build a fairly successful open... - Source: Hacker News / 4 months ago

I'll add txtai (https://github.com/neuml/txtai) to the list. There is still plenty of room for innovation in this space. Just need to focus on the right projects that are innovating and not the ones (re)working on problems solved in 2020/2021. - Source: Hacker News / 4 months ago

Nice project! I've long used Tika for document parsing given it's maturity and wide number of formats supported. The XHTML output helps with chunking documents for RAG. Here's a couple examples: - https://neuml.hashnode.dev/build-rag-pipelines-with-txtai - https://neuml.hashnode.dev/extract-text-from-documents Disclaimer: I'm the primary author of txtai ( - Source: Hacker News / 4 months ago

If you're serious about scaling up, definitely consider Vespa (https://vespa.ai). At serious scale, Vespa will likely knock all the other options out of the park. - Source: Hacker News / about 1 month ago

Yahoo released their geographic data catalogue under open license and it still lives on as https://whosonfirst.org/ Afaik https://en.wikipedia.org/wiki/Apache_ZooKeeper started at Yahoo https://vespa.ai/ was Yahoo's search engine for news and other content product, now spinned off (https://techcrunch.com/2023/10/04/yahoo-spins-out-vespa-its-search-tech-into-an-independent-company/). - Source: Hacker News / 3 months ago

I think https://vespa.ai/ has the right approach in this space by focusing on being hybrid - vectors alone aren't great for production use cases, it's the combining of vectors+text that lets you use ranking to get meaningful result. (I'm an investor so I'm biased; but it's also the reason why I invested). - Source: Hacker News / 4 months ago

So what’s the catch? Why is this not everywhere? Because IR is not quite NLP — it hasn’t gone fully mainstream, and a lot of the IR frameworks are, quite frankly, a bit of a pain to work with in-production. Some solid efforts to bridge the gap like Vespa [1] are gathering steam, but it’s not quite there. [1] https://vespa.ai. - Source: Hacker News / 4 months ago

When it comes to search I cannot disagree more. https://vespa.ai is a purpose built search engine. If you start bolting search onto your database, your relevance will be terrible, you'll be rewriting a lot of table stakes tools/features from scratch, and your technical debt will skyrocket. - Source: Hacker News / 10 months ago