Paragraphs and passages that are each other's best match
Changed onA Urantia paragraph and a passage where each is the other's closest match in that text, under both text-embedding-3-large and text-embedding-3-small. These are the most stable links in the data. Ranked by similarity. Filter with corpus (a corpus name or bible).
Scores come from the nine world religions texts and the World English Bible. For each text, a paragraph's best match becomes a percentile within that text, after an adjustment for paragraph length. The texts are not independent votes: a paragraph that sounds devotional tends to score well in all of them. These are measures of closeness in meaning by an embedding model, not claims about the teachings.
Request
- Base URL: https://api.urantia.dev
- URL: https://api.urantia.dev/scriptures/insights/pairs
- Auth: none required
Query parameters
A corpus id, slug, or ref prefix, or bible
true leaves out the Bible, which has most of the mutual pairs
Leave out paragraphs shorter than this many characters. Headings and fragments score unreliably
Response
Mutual pairs
Changes
- info
endpoint added
- info