Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
1–10 of 53 posts
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#2Author here. Over the last few months, I have built and launched a free semantic search tool for GitHub called SemHub (https://semhub.dev/). In this blog post, I share what I’ve learned and why I’ve failed, so that other builders can learn from my experience. This blog post runs long and I have sign-posted each section. I have marked the sections that I consider the particularly insightful with an asterisk (*).
I have also summarized my key lessons here:
1. Default to pgvector, avoid premature optimization.
2. You probably can get away with shorter embeddings if you’re using Matryoshka embedding models.
3. Filtering with vector search may be harder than you expect.
4. If you love full stack TypeScript and use AWS, you’ll love SST. One day, I wish I can recommend Cloudflare in equally strong terms too.
5. Building is only half the battle. You have to solve a big enough problem and meet your users where they’re at.
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#3Author here. Over the last few months, I have built and launched a free semantic search tool for GitHub called SemHub ( https://semhub.dev/ ). In this blog post, I share what I’ve learned and why I’ve failed, so that other builders can learn from my experience. This blog post runs long and I have sign-posted each section. I have marked the sections that I consider the particularly insightful with an asterisk (*). I h…
With 5 you mean promoting the app? It is by far the biggest problem, yes. In many cases even bigger than building the app itself.
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#4Author here. Over the last few months, I have built and launched a free semantic search tool for GitHub called SemHub ( https://semhub.dev/ ). In this blog post, I share what I’ve learned and why I’ve failed, so that other builders can learn from my experience. This blog post runs long and I have sign-posted each section. I have marked the sections that I consider the particularly insightful with an asterisk (*). I h…
Having built a failed semantic search engine for life sciences (bioask when it existed), I think the last point should be the first. Not getting a product market fit very quickly killed mine.
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#5Author here. Over the last few months, I have built and launched a free semantic search tool for GitHub called SemHub ( https://semhub.dev/ ). In this blog post, I share what I’ve learned and why I’ve failed, so that other builders can learn from my experience. This blog post runs long and I have sign-posted each section. I have marked the sections that I consider the particularly insightful with an asterisk (*). I h…
SST: https://github.com/sst/sst - vaguely similar to CDK but can also manage some non-AWS resources and seems TypeScript-only
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#6Author here. Over the last few months, I have built and launched a free semantic search tool for GitHub called SemHub ( https://semhub.dev/ ). In this blog post, I share what I’ve learned and why I’ve failed, so that other builders can learn from my experience. This blog post runs long and I have sign-posted each section. I have marked the sections that I consider the particularly insightful with an asterisk (*). I h…
Thanks for writing this up!
> Filtering with vector search may be harder than you expect.
I've only ever used it for a small proof of concept, but Qdrant is great at categorical filtering with HNSW.
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#7Author here. Over the last few months, I have built and launched a free semantic search tool for GitHub called SemHub ( https://semhub.dev/ ). In this blog post, I share what I’ve learned and why I’ve failed, so that other builders can learn from my experience. This blog post runs long and I have sign-posted each section. I have marked the sections that I consider the particularly insightful with an asterisk (*). I h…
Fantastic writeup — thank you for taking the time to do this!
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#8Author here. Over the last few months, I have built and launched a free semantic search tool for GitHub called SemHub ( https://semhub.dev/ ). In this blog post, I share what I’ve learned and why I’ve failed, so that other builders can learn from my experience. This blog post runs long and I have sign-posted each section. I have marked the sections that I consider the particularly insightful with an asterisk (*). I h…
Hi, thanks for building a great tool and a great write-up! I was trying to add a number of repos under oslc/, oslc-op/, and eclipse-lyo/* orgs but no joy - internal server error. Hopefully, you will reconsider shutting down the project (just heard about it and am quite excited)!
I think a project like yours is going to be helpful to OSS library maintainers to see which features are used in downstream projects and which have issues. Especially, as in my case, when the project attemps to advance an open standard and just checking issues in the main repo will not give you the full picture. For this use case, I deployed my own instance to index all OSS repos implementing OSLC REST or using our Lyo SDK - https://oslc-sourcebot.berezovskyi.me/ . I think your tool is great in complementing the code search.
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#9That was a great write up.
If you don't mind me giving you some unsolicited product feedback: I think SemHub didn't do well because it's unclear what problem it's actually solving. Who actually wants your product? What's the use case? I use GitHub issues all the time, and I can't think of a reason I'd want semhub. If I need to find a particular issue on, say, TypeScript, I'll just google "github typescript issue [description]" and pull up the correct thing 9 times out of 10. And that's already a pretty rare percentage of the time I spend on GitHub.
Re: Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
#10[dead]