newscatcher VS CX_DB8

Built this news website for my portfolio using NewsApi.org but turns out its only got CORS enabled for localhost which I found out when I was about to publish my web page. Found and tried another API from newscatcherapi.com but it only gives me 50 API calls for the free plan which I ran out of very quickly.

I think you would benefit from a news data API like our newscatcher. We don't drill down to the state level (yet) but we do allow you to filter news by country, language, individual sources, date ranges, and you can also use a query like "fire" to search for relevant articles. And the data is returned as JSON objects, so it's pretty easy to work with.

Hi Jakub,

Nice. I want to talk to you about the news feed: it could be more than just the latest news (NLP enriched)

I'm a co-founder of https://newscatcherapi.com/

I'm so sick of top notch trading platforms to just provide a list of latest news while there could be so much more insights.

Well, if you'd want to discuss it: https://savvycal.com/newscatcher/chat

If all you care about is raw data, newscatcherapi.com is one of the best options. They already have over 60,0000 sources and readily add any sources you want to cover.

Share your startups here, and get some feedback from the HN community.

For the first time applicants: show your progress for the next batch in case you don't get accepted.

Startup: NewsCatcher

Website: https://newscatcherapi.com/

One-liner: We turn online news into machine-readable data

The Newscatcher API enables developers to find news articles from major news sources and blogs based on any topic, country, language, website, or keyword. The Newscatcher API features simple integration and niche-specific content.

Give newscatcher a try

We’re ~17k MRR right now. Being doing it for almost 2 years.

What made us take off is I and my cofounder running through our savings. I did it for ~15 months.

One thing I had to start doing earlier is not trying to get everyone buy our product (we sell news articles published online as a source of data for insight mining) [0]

I’ve lost so much time on people who’d never be able to use what we have unless we completely change our product.

And yeah, marketing is super important. And, it’s going to take some time.

[0] https://newscatcherapi.com

I was working on this stuff before it was cool, so in the sense of the precursor to LLMs (and sometimes supporting LLMs still) I've built many things:

1. Games you can play with word2vec or related models (could be drop in replaced with sentence transformer). It's crazy that this is 5 years old now: https://github.com/Hellisotherpeople/Language-games

2. "Constrained Text Generation Studio" - A research project I wrote when I was trying to solve LLM's inability to follow syntactic, phonetic, or semantic constraints: https://github.com/Hellisotherpeople/Constrained-Text-Genera...

3. DebateKG - A bunch of "Semantic Knowledge Graphs" built on my pet debate evidence dataset (LLM backed embeddings indexes synchronized with a graphDB and a sqlDB via txtai). Can create compelling policy debate cases https://github.com/Hellisotherpeople/DebateKG

4. My failed attempt at a good extractive summarizer. My life work is dedicated to one day solving the problems I tried to fix with this project: https://github.com/Hellisotherpeople/CX_DB8

I really missed out on this thread despite being likely one of the most important folks to post on it (I turned my time in Policy Debate into an NLP career - see DebateSum: https://huggingface.co/datasets/Hellisotherpeople/DebateSum and CX_DB8: https://github.com/Hellisotherpeople/CX_DB8)

For those who are interested in the intersection of AI and Debate Evidence, there's a lot more work being done right now. We have a follow-up dataset to DebateSum on its way to a paper at some conference called OpenCaseList: https://huggingface.co/datasets/Yusuf5/OpenCaselist which is basically DebateSum but 40x better in every way. This is also likely the largest and best quality argument mining dataset ever gathered.

Fun anecdote, when I tried to introduce automatic extractive summarization tools to the debate community, I had parent/judge/teacher groups who were FLIPPING out about this. They were not happy at the idea of automatic debating or computer assisted debating systems.

This has deep connections with my attempt to implement an effective queryable word-level grammatically correct extractive text summarizer (AKA: The way most people actually summarize documents) - https://github.com/Hellisotherpeople/CX_DB8

I will try to implement this with the necessary changes to actually make this work properly, where instead of generating a new answer, it simply highlights the most likely text spans.

Is there any path forward to make Haystack do word-level extractive summarization? e.g. like this: https://github.com/Hellisotherpeople/CX_DB8

or like this: https://huggingface.co/spaces/Hellisotherpeople/Unsupervised...

I am trying to find anything better than these two for this task. I feel like Haystack could be an option - but I am not sure.