Show HN: An Embedding-Based Search Service over ShowHN, AskHN, GitHub, More

Posted by eneuman on Wednesday October 25, 2023 @07:53AM
from the show-hn dept.

Hey folks, Elias here. Excited to unveil my latest project.

Why I Built This: Traditional keyword search isn't cutting it. I've used LLM-embeddings to provide more nuanced, relevant results.

How It Works: LLM-embedding similarity on curated datasets for semantically similar results. No need to iterate over keywords any more.

Current Datasets:

- YC Companies - Show HN Posts, - Ask HN Posts - ProductHunt Startups - Github Top 200k Repos

Use Cases:

- Validate a product idea's existence - Check if someone already Asked HN something - Have fun - search random terms and see what pops up

Want to see other datasets? Got one in mind? What would you use it for? (I'm even thinking of adding all PG's tweets - so feel free to be creative.)

Eager for your feedback and ideas. Hope you find this useful and fun!

( 4 comments | 2 points | on HN )

Re:Show HN: An Embedding-Based Search Service over ShowHN, A... by omarfarooq on Wednesday October 25, 2023 @08:46AM (#38012193)

This is will be really useful for research within the ingested domains! Awesome.

[ Parent | on HN ]

Re:Show HN: An Embedding-Based Search Service over ShowHN, A... by eneuman on Wednesday October 25, 2023 @08:48AM (#38012215)

Thank you for the feedback!

If there are any other domains you'd like to see, let me know :)

[ Parent | on HN ]

Re:Show HN: An Embedding-Based Search Service over ShowHN, A... by omarfarooq on Wednesday October 25, 2023 @09:14AM (#38012429)

I'm thinking Crunchbase would give you a comprehensive view into Silicon Valley (and adjacent) company data, but the data is behind an API.

[ Parent | on HN ]

Re:Show HN: An Embedding-Based Search Service over ShowHN, A... by simonw on Wednesday October 25, 2023 @09:37AM (#38012628)

The vector search is using https://lancedb.com/ and OpenAI embeddings.

[ Parent | on HN ]