Top all-time · #17643
Metarank
Company blog · blog.metarank.aiaidatastartups
Metarank is the company blog at blog.metarank.ai, writing about ai, data and startups. Since 2022, 4 different Hacker News readers have linked it 14 times, most often “Your ML setup is not unique: you don’t need more data scientists”. The last post was in 2023, but the archive is still widely read.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
The linked Metarank post is an introduction to vector similarity search. The comments do not discuss the writing itself, and the one comment points to a different tutorial on kNN search with Elasticsearch.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Your ML setup is not unique: you don’t need more data scientists3 people · 4 mentions · first linked 2022-09-16
What Hacker News says?
I wrote up a little tutorial on how to do the last two with elasticsearch and my kotlin kt-search library here a while ago: https://jillesvangurp.github.io/kt-search/manual/KnnSearch.h... You index into an index with a dense vector field And when you query, you generate embeddings for your query and run a knn vector similarity search. It uses some embeddings I generated with openai. You could use something like easy…
Comment linking /from-zero-to-semantic-search-embedding-model-592e16d94b61
on “Introduction to Vector Similarity Search”Submitted Why you should post your story to HN on the weekend (and it should be in Rust) as a story · 6 points
HN discussionSubmitted Your ML setup is not unique: you don’t need more data scientists as a story · 4 points
HN discussionSubmitted I know what you did with my open-source project as a story · 3 points
HN discussionSubmitted Search Results Diversification with Metarank as a story · 2 points
HN discussionSubmitted Why you should post your story to HN on the weekend (and it should be in Rust) as a story · 2 points
HN discussionSubmitted ML setup is not unique: you don’t need more data scientists as a story · 2 points
HN discussionSubmitted Your ML setup is not unique: you don’t need more data scientists as a story · 2 points
HN discussionSubmitted Solving a search cold-start problem with aggregated CTR as a story · 1 points
HN discussionSubmitted How we did not get into YC again as a story · 1 points
HN discussionSubmitted Your ML setup is not unique: you don’t need more data scientists as a story · 1 points
HN discussionSubmitted Automatic Feature Engineering with Metarank as a story · 1 points
HN discussionSubmitted Personalized Ranking API with Docker as a story · 1 points
HN discussionSubmitted Metarank RAM Usage Benchmark as a story · 1 points
HN discussion