Skip to content
unlob

Finding sources worth following

Teams building recommendation, curation and discovery products.

The problem

  • Discovery by keyword returns what matches the words, which is not the same as what is worth reading.
  • Widening a result set usually means guessing at new queries, which reflects your vocabulary rather than the corpus's.
  • Popularity signals favour recency and volume over substance.

The approach

  • sort=centrality orders by position in the coverage graph — what the field references, rather than what matched the query.
  • similar widens from a seed passage through the embedding space, crossing languages as it goes.
  • related follows typed edges, so the expansion comes from documented relationships rather than similarity alone.
  • Community filtering keeps discovery inside one discourse when a term means different things in different fields.

The parameters that matter

ParameterValueWhy
sortcentralityFoundational rather than merely matching.
similar?id=a good seedWiden without inventing a query.
min_centrality0.3A floor on how well-connected results must be.
community[]one clusterStay inside a single discourse.
In practicebash
curl -H "x-api-key: $UNLOB_API_KEY" \
  "https://api.unlob.com/search?q=retrieval+evaluation&sort=centrality&limit=10"

curl -H "x-api-key: $UNLOB_API_KEY" "https://api.unlob.com/similar?id=p:8f2c9a&limit=10"

Where this is not the right tool

  • Centrality favours established sources, so it under-surfaces genuinely new material. Combine with prefer_recent when novelty matters.
  • Community assignment is automatic and occasionally splits a field that a person would treat as one.

Frequently asked questions

How is centrality different from relevance?

Relevance asks what matches your query. Centrality asks what the corpus treats as load-bearing, independent of the query. For discovery the second is usually the better ordering.

Does similar work across languages?

Yes. The embedding space holds 101 languages, so a German seed passage can surface its English counterparts directly.

Build it on the free tier

10,000 requests a month, no card. Every parameter above works on every plan.