Products

One engine, four products

A vector database written in Go, the search and recommendation services we build on it, and a simulation engine to test every change before release. Use them together, or take the database on its own.

Vector database

vecsai DB

A search-first vector database written in Go. Full-text, vector and hybrid queries from a single engine, configured in minutes.

  • Full-text, vector and hybrid search in one query
  • Written in Go, single binary, low memory footprint
  • Schema-based configuration, ready in minutes
Explore vecsai DB
vecsai DB · hybrid search
warm jacket for wet hikes
  • Alpine Shell JacketWaterproof · insulated · hiking0.94
  • Trailhead Down ParkaWarm · water-resistant0.91
  • Ridge 3-in-1 JacketRemovable fleece liner0.88
Filtered: in stockexample
Search as a service

vecsai Search

Semantic and keyword search for products, content and documents — personalised to each user and tuned with business rules.

  • Understands intent, synonyms and typos
  • Personalised ranking per user
  • Business rules: boost, bury, pin and filter
Explore vecsai Search
vecsai Search · personalised results
wireles hedphones

Showing results for wireless headphones

  • Wireless Over-Ear HeadphonesNoise cancelling · 30 h battery
  • Sport Wireless EarbudsViewed similar items
  • Studio Headphones, BluetoothMatches your brands
Ranked for this shopperexample
Recommendation engine

vecsai Recommend

Personalised recommendations from user behaviour and item content, served from our vector database in real time.

  • Updates with every interaction, in real time
  • Recommends new items from day one
  • Business rules you control
Explore vecsai Recommend
vecsai Recommend · home screen

Because you watched The Long Orbit

  • Deep Signal
  • Red Horizon
  • Quiet Station
  • Last Light

New this week for you

  • Northbound
  • Salt & Iron
  • The Archive
  • Glasswater
Updated after every playexample
Simulation engine

vecsai Sim

A simulation engine for OTT, e-commerce and social platforms. Test ranking, recommendation and catalogue changes on simulated users before release.

  • Built for OTT, e-commerce and social media
  • Compare current and proposed versions side by side
  • Works with vecsai or with your existing system
Explore vecsai Sim
vecsai Sim · baseline vs diversity_v2
Watch time per user+6.8%
baseline
variant
Click-through on home row+3.1%
baseline
variant
Catalogue coverage+18%
baseline
variant
New-user retention−0.4%
baseline
variant

Example report · 50,000 simulated viewers · 30 days

See vecsai on your own catalogue

Tell us about your platform and we will show you search, recommendations and simulation running on your data.

Request a demoExplore products