Alternatives
Products that do what SearchArray – Text Search in Pandas does
I've long worked with lexical Lucene based search engines like Solr and Elasticsearch. Anytime I need to experiment with relevance ranking in these systems, I'm exhausted by needing to set them up. It's not conducive to productivity work with something so disjoint from normal data tooling. Further - the underlying ranking is buried in needless mystique (you know a boolean should query, sums the scores, right?). You shouldn't need to read a book (like Relevant Search ;) ) to unpack mystique that's really basic math. Why not just let people build ranking systems with vectorized math in a…
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9AS
2013 · insightdatascience.com
- 10
- 11
- 12
- 13
- 14
- 15
- 16SR
2016 · searchkit.co
- 17AR
Hey all, we've seen increasing interest for leveraging GPT's capability but basing it off of your own data so we launched a new feature "Ask Relevance" a little while ago and our users have loved it. There have been some great tutorials on how you can do this and we thought we'd share our approach with the community as we believe it's very accessible. Under the hood, it's using vector search to extract relevant content from the dataset and then using that to feed it into GPT. The post features a video where you can see it in action answering specific questions about the Relevance AI…
2023 · relevanceai.com
- 18EL
For those who don't know, Learning to Rank, is a means of using a machine learning model to optimize relevance of search results. The Elasticsearch Learning to Rank plugin creates the infrastructure for feature storage (aka templated Elastic queries), feature logging, and then uploading models trained offline for ranking with those features. This plugin is a few years old, but as one of the core maintainers, I'm eager to open the pool of contributors to this codebase used a lot by the Elastic community. I realize Elasticsearch plugins are a dark art. But if your team uses Elasticsearch for…
2019
- 19MO
A small demo for a Metarank open-source project I'm maintaining.
2023 · demo.metarank.ai
- 20AS
We built a search engine that shows you the most engaging stories/topics being shared across Twitter, Facebook, Linkedin, and Google+. We crawled over 15 million articles the past 3 months, retrieved the total number of Facebook likes, tweets, Google+’s etc and built a search index around it. Here's what our infrastructure looks like: Rails/Redis: We use the Sidekiq gem as a message queue. We have hundreds of workers that do the crawling, data mining, and number crunching. ElasticSearch: We built the search index using ElasticSearch, with the data imported from our Postgres…
2013 · buzzsumo.com
- 21SE
Hi HN, I’m working on an Israeli search engine with a focus on deeper search across Israeli, academic, and scientific content. One feature I recently added is that users can adjust their own search boost factors. For example, they can give more or less weight to title, domain, URL, language, document type, or page content. Search remains anonymous and ad-free. I’m interested in feedback from people who care about search, indexing, crawling, privacy, and ranking transparency: Would you find this kind of user-adjustable search ranking useful? https://websearch.co.il
Jun 2026 · websearch.co.il
- 22SV
Hi HN, I'm Daniel from Superlinked! We have built an open-source framework that improves vector search relevance and usefulness by combining structured metadata with unstructured data in your embeddings. We included self-hostable API server that sits between your data sources and vector database. Docs: https://docs.superlinked.com/ We're launching our cloud offering soon where you can use Superlinked to orchestrate high-performance retrieval for RAG, Search & Recommendation apps in your own cloud. Looking for feedback and happy to answer questions!
2024 · github.com
- 23TA
Hello HN! I'm Peter, one of the folks who helped create Tidepool. We last shared Tidepool with HN about 7 months ago https://news.ycombinator.com/item?id=36957762 Since then, the AI field has moved incredibly quickly and we’ve iterated a lot on our product! The core problem we are trying to solve is: there's a lot of useful business insights you can get from text data, but it's hard to do analytics on it. - SQL is built for tabular / structured data, but when it comes to text, the best you can do is do keyword search. - In the pre-LLM world, you might resort to training a…
2024 · tidepool.so
- 24QW
2019 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →