OLH
News

News and notes.

Updates and technical notes from Lovguiden, SupaChat and client work.

RSS feed
Latest · Search
  1. 01The setup
  2. 02Index what people search for, not the whole document
  3. 03Keyword arm: RUM instead of GIN
  4. 04Vector arm: HNSW on halfvec
  5. 05Filtered vector search needs a literal
9 min read

Hybrid search in Postgres without pg_search

Lovguiden searches 1.45 million chunks of Danish case law with keyword search, vector search and trigram matching in one SQL function on hosted Supabase. This is how it is built, and what we changed after a year in production.

ReadRelated: Lovguiden case study · Search
  1. Automation

    How Lovguiden's data sources repair themselves

    Public websites change without warning. Lovguiden's data collection is built to notice when that happens, let an AI agent diagnose the fault, and test the fix against the live source before it is applied.

    Related: Automation on Lovguiden
  2. Legal AI

    Why every AI reference is checked before it is shown

    Lovguiden's users are lawyers, accountants and public servants, whose work has consequences when it is wrong. The AI assistant is built around one rule: if it can't be sourced, it isn't said.

    Related: Lovguiden case study · Lovguiden AI
  3. MCP

    Danish law inside Claude and ChatGPT

    Lovguiden's MCP server gives AI tools direct access to Danish legislation, case law and parliamentary data through 35 tools. A REST API serves companies that build their own products on the same data.

    Related: Lovguiden case study · MCP & API
  4. Open source

    SupaChat gets its own website

    SupaChat, the open-source AI chat starter built on the same foundations as Lovguiden, now has a home at supa-chat.dev, with a live demo and an overview of everything included.

    Related: SupaChat case study
Contact

The same approach, for other businesses.

A short description of the task is enough to start the conversation.

Send an emailoh@opkurser.dk
Three lines are enough
  1. 01
    The task
    The recurring work that takes too long.
  2. 02
    How it is handled today
    Who does it, and with which tools or sources.
  3. 03
    How often
    Daily, weekly, or every time a document arrives.

The email button opens a draft with these three prompts in place.