Default searcher using Arcana's built-in pgvector search.
Uses Arcana.search/2 to perform semantic similarity search against
the configured PostgreSQL database with pgvector.
Usage
# With Arcana.Pipeline (this is the default)
ctx
|> Pipeline.search()
|> Pipeline.answer()
# Explicitly specifying the searcher
ctx
|> Pipeline.search(searcher: Arcana.Searcher.Arcana)
|> Pipeline.answer()Options
:repo- The Ecto repo (required):collection- Collection name to search:limit- Maximum chunks to return (default: 5):threshold- Minimum similarity threshold (default: 0.5)