daemond

KAG aims to make full use of the advantages of Knowledge Graph and vector retrieval, and bi-directionally enhance large language models and knowledge graphs through four aspects to solve RAG challenges: (1) LLM-friendly knowledge representation, (2) Knowledge Graph and original text The mutual index between fragments, (3) a hybrid reasoning engine guided by logical forms, (4) knowledge alignment with semantic reasoning.

The author believes that SQL is the core competency of Data Engineering. Now that ChatGPT can translate natural language into good SQLs. So Data Engineering is going to be retired?

I am curious if wearing this device for a long time will cause dizziness.

Yes, the star number of VSCode surpassed Atom in April 2018, 2 months before GitHub was acquired. https://ossinsight.io/analyze/atom/atom?vs=microsoft%2Fvscod...

I think the fastest growing programming language deserves more attention, so I used one of the subheadings in the report.

OK, that makes sense. Thank you.

Maybe we should call it Quasi-real time. We get the data from the GitHub API[1], and GitHub delays the public events feed by five minutes. So the PR you see on the page actually occurred at least five minutes ago.

[1] https://docs.github.com/en/rest/activity/events#list-public-...

Sorry, you can only see the full page in landscape view on mobile now.

SD is so popular these days. It has been on the top of GitHub trending for a long time, last hour, last day, and even last week. https://ossinsight.io/#trending-repos

Is it because it represents that AI can do things that humans thought would never be replaced by AI before?

In fact, when I first opened HN, I couldn't read the comments very well. Because the font is too small, the layout is dense, and there are no pictures. But when I started reading the comments carefully, I was really surprised by so many people being active on it and so insightful most of the comments are.

Now I'm actually getting used to reading these text-only pages.

I agree with it that when the OSS is in the early stages. When the OSS has a large number of users, forms a community, and has commercial potential, things will change.

Awesome! I think Excel is the low code version of database.

I think the most important reason is that supabase is a good product. Marketing is just a plus.

From the Google trend[0] and the historical data of Kubernetes repo on GitHub[1], K8s has crossed the chasm to become the dominant choice for infrastructure. Whether it is the result of several companies working together, or from developers' choice. I think K8s will remain mainstream until there are big changes in the infrastructure world.

[0] https://trends.google.com/trends/explore?date=2014-06-01%202... [1] https://ossinsight.io/analyze/kubernetes/kubernetes

There are a lot of open source projects similar to astro. Here is a comparison of the popularity and product iteration trend of them. https://ossinsight.io/collections/static-site-generator You can see that astro's popularity is on the rise. I think it's worth keeping an eye on.

In terms of star growth, devdash looks like a project that becomes popular every once in a while. But the project iterated slowly, maybe the Maintainer doesn't care too much about it? https://ossinsight.io/analyze/Phantas0s/devdash

There are still people paying tribute to it by stars. https://ossinsight.io/analyze/firebug/firebug