How to actually choose a retrieval engine (daily search tip)

Published 28 days ago • 1 min read

How do teams choose vector databases / search engines?

People wrack their brains between Elasticsearch/OpenSearch/Solr/Vespa/Pinecone/Turbopuffer/Weaviate/…?

First things first - DO NOT start with a feature matrix. Start with the simple question:

What is my team most comfortable with? That’s the default. If everyone can go deep in one system, don’t overcomplicate the decision. It might be good enough to stop here.

NEXT - consider the high-level characteristics of the project. Use these as veto points for the original choice.

Pace of development - do you see that the project is actively being maintained and improved? If not, consider something else.
Scale - what scale does the project target? Does it match what you need? High scale, you want simple operations, executed predictably. Lower scale you’ll have richer features but won’t get predictable performance from those as you scale out. Choose the right fit.
Company capitalization - Who builds the technology? Will they exist in one year? If they don’t exist, who takes on the project?

FINALLY - think about how you make it easy to migrate OFF the technology. Don’t over-couple to one system / company. Avoid the advanced features unless they’re really killer. Build code that modularizes the dependency on the search backend so you can swap them out as needed.

-Doug

Events · Consulting · Training (use code search-tips)

You're subscribed to Doug Turnbull's daily search tips where I share tips, blog articles, events, and more. You can always manage your profile:

Community happenings: context engineering + your search career

Talks this week + other events. Hope you can make it and help keep this community awesome 😎 First - Leonie Monigatti will share how Context Engineering IS Agentic Search. Tuesday, 10:30AM ET What everyone is missing: when people talk aobut "context engineering", they really ought to be improving search. Leonie will cast aside myths about context engineering to show how agents build their own context via retrieval. And THAT, not prompting magic, decides whether your AI app is successful....

17 days ago • 1 min read

Pay attention to this this teeny-tiny late interaction (search tip)

Late interaction is having a moment. The team at LightOn - including superstar developer Antoine Chaffin - has demonstrated how a 150M(!) late interaction model beats much larger models - some up to 8B parameters. David beats Goliath! Better search only cost you less! Tested on what dataset? BrowseComp. BrowseComp asks difficult questions requiring detailed, complex research. Tasks you can imagine agents chugging away, searching, getting frustrated and lost. Here’s an example prompt / answer...

25 days ago • 1 min read

Are my search tips useful to you? [Feedback Requested]

Hey all, I've been doing these "daily search tips" since the end of last year. I enjoy putting them together, and have begun archiving them on my site. I'm curious if you find them valuable? If you can, could you please reply and say: Whether you're getting value One thing you like One thing you don't like (Of course I encourage unsubscribes if not useful, see below) Cheers, -Doug Events · Consulting · Training (use code search-tips) You're subscribed to Doug Turnbull's daily search tips...

29 days ago • 1 min read