I was super-excited about vector search and embeddings in 2024 but my enthusiasm has faded somewhat in 2025 for a few reasons:
- LLMs with a grep or full-text search tool turn out to be great at fuzzy search already - they throw a bunch of OR conditions together and run further searches if they don't find what they want
- ChatGPT web search and Claude Code code search are my favorite AI-assisted search tools and neither bother with vectors
- Building and maintaining a large vector speech index is a pain. The vector are usually pretty big and you need to keep them in memory to get truly great performance. FTS and grep are way less hassle.
- Vector matches are weird. So you get back the top twenty results... those might be super relevant or they might be total garbage, it's on you to do a second pass to figure out if they're actually useful results or not.
I expected to spend much of 2025 building vector search engines, but ended up not finding them as valuable as I had thought.
What about re-ranking? In my limited experience, adding fast+cheap re-ranking with something like Cohere to the query results took an okay vector based search and made top 1-5 results much stronger
There’s a lot of previously intractable problems that are getting solved with these new embeddings models. I’ve been building a geocoder for the past few months and it’s been remarkable how close to google places I can get with just slightly enriched open street maps plus embedding vectors
That sounds really interesting. If you’re open to it, I’d be curious what the high-level architecture looks like (what gets embedded, how you rank results)?
I was super-excited about vector search and embeddings in 2024 but my enthusiasm has faded somewhat in 2025 for a few reasons:
- LLMs with a grep or full-text search tool turn out to be great at fuzzy search already - they throw a bunch of OR conditions together and run further searches if they don't find what they want
- ChatGPT web search and Claude Code code search are my favorite AI-assisted search tools and neither bother with vectors
- Building and maintaining a large vector speech index is a pain. The vector are usually pretty big and you need to keep them in memory to get truly great performance. FTS and grep are way less hassle.
- Vector matches are weird. So you get back the top twenty results... those might be super relevant or they might be total garbage, it's on you to do a second pass to figure out if they're actually useful results or not.
I expected to spend much of 2025 building vector search engines, but ended up not finding them as valuable as I had thought.
What about re-ranking? In my limited experience, adding fast+cheap re-ranking with something like Cohere to the query results took an okay vector based search and made top 1-5 results much stronger
Query expansion works better.
There’s a lot of previously intractable problems that are getting solved with these new embeddings models. I’ve been building a geocoder for the past few months and it’s been remarkable how close to google places I can get with just slightly enriched open street maps plus embedding vectors
That sounds really interesting. If you’re open to it, I’d be curious what the high-level architecture looks like (what gets embedded, how you rank results)?
Site has a neat feature where you can see the pointers of other people, marked by regional? notations, scrolling through the content.
It's amazing! Got so distracted, gotta switch to reader mode haha. Never seen anything like that.
that got annoying fast