rails-paradedb 0.10.0 → 0.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 296e696bfa9711537e984df359c43be2481b53a91f75c880dc33ac36aacf4b1c
-  data.tar.gz: 78781d5fc912c5b57053818d7f3e76e2d01251fb7d31a586edd5d28b88426e69
+  metadata.gz: 61970bcefe75f0514836a81ab38dd8e39fe1c6f311d55f35366120d2285325b9
+  data.tar.gz: 6179c3b6d0814dcaae1179977548c4b47e6f6447110596293f242d668727d79a
 SHA512:
-  metadata.gz: 5b4fecd2d8620a91e782ea62df980ab6638fec2906ad5a380664e97b77a8d0e1b4b656aa330cc4b9e80a99e18f2223cd2d50da6cea98245c63c1c4fe88ca7450
-  data.tar.gz: a6c42abf6b75aad3ee2d3b58651cfde545ba86deef7e33df0593cafc94da529818dbe41f290286e0acc3eb9bc62071d4d2b06d7976cb8c44d5a94be7c9a37722
+  metadata.gz: 38471cccf3d392cd481dbb22cde9f35c37f09a555c4e6081c5484d9c5ad1920082172276447a2401a22c0dd46bcd1a0846f2dee26678f556f913373996a91da0
+  data.tar.gz: 6176c6252901db66d8f8dd72972f8053fc6a187d0d10391705dde18fabe16a4992d60655a351b3af8643e9ca4a57c2baff58a11a2dd93cb63a708750785034c6

data/CHANGELOG.md

@@ -2,7 +2,11 @@
 
 All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [0.11.0] - 2026-08-04
+
+### Added
+
+- Vector index build options `centroid_ratio`, `training_samples_per_centroid`, and `cluster_replication` in `ParadeDB::Index` `index_options` and `add_paradedb_index` (pg_search 0.25.0+). They are emitted in the `WITH (...)` clause and round-tripped through the schema dumper.
 
 [0.10.0] - 2026-08-04
 
@@ -170,7 +174,7 @@ All notable changes to this project will be documented in this file. The format
 - Schema dump/load round-trip for tokenizer configuration and index options
   (including `target_segment_count`)
 
-[Unreleased]: https://github.com/paradedb/rails-paradedb/compare/v0.10.0...HEAD
+[0.11.0]: https://github.com/paradedb/rails-paradedb/releases/tag/v0.11.0
 [0.10.0]: https://github.com/paradedb/rails-paradedb/releases/tag/v0.10.0
 [0.9.0]: https://github.com/paradedb/rails-paradedb/releases/tag/v0.9.0
 [0.8.0]: https://github.com/paradedb/rails-paradedb/releases/tag/v0.8.0

data/lib/parade_db/index.rb

@@ -83,6 +83,8 @@ module ParadeDB
     # Consumed by migration helpers; validates and normalizes the DSL class
     class DefinitionCompiler
       FIELD_OPTION_KEYS = %i[fast record normalizer expand_dots].freeze
+      INDEX_OPTION_KEYS = %i[target_segment_count centroid_ratio training_samples_per_centroid cluster_replication].freeze
+      POSITIVE_INTEGER_INDEX_OPTION_KEYS = %i[target_segment_count training_samples_per_centroid cluster_replication].freeze
 
       class Compiled
         attr_reader :table_name, :key_field, :index_name, :entries, :index_options, :field_options, :where
@@ -238,16 +240,26 @@ module ParadeDB
             memo[key.to_sym] = value
           end
 
-          unknown = normalized.keys - [:target_segment_count]
+          unknown = normalized.keys - INDEX_OPTION_KEYS
           unless unknown.empty?
             raise InvalidIndexDefinition,
                   "unknown index_options keys: #{unknown.map(&:inspect).join(', ')}"
           end
 
-          if normalized.key?(:target_segment_count)
-            target = normalized[:target_segment_count]
-            unless target.is_a?(Integer) && target.positive?
-              raise InvalidIndexDefinition, "index_options[:target_segment_count] must be an Integer > 0"
+          POSITIVE_INTEGER_INDEX_OPTION_KEYS.each do |key|
+            next unless normalized.key?(key)
+
+            value = normalized[key]
+            unless value.is_a?(Integer) && value.positive?
+              raise InvalidIndexDefinition, "index_options[#{key.inspect}] must be an Integer > 0"
+            end
+          end
+
+          if normalized.key?(:centroid_ratio)
+            ratio = normalized[:centroid_ratio]
+            unless ratio.is_a?(Numeric) && ratio >= 0.000001 && ratio <= 1.0
+              raise InvalidIndexDefinition,
+                    "index_options[:centroid_ratio] must be a Numeric between 0.000001 and 1.0"
             end
           end
 

data/lib/parade_db/migration_helpers.rb

@@ -100,9 +100,12 @@ module ParadeDB
       options << "key_field=#{quote(compiled.key_field.to_s)}"
 
       compiled.index_options.each do |key, value|
-        case key.to_sym
-        when :target_segment_count
-          options << "target_segment_count=#{Integer(value)}"
+        name = key.to_sym
+        case name
+        when :target_segment_count, :training_samples_per_centroid, :cluster_replication
+          options << "#{name}=#{Integer(value)}"
+        when :centroid_ratio
+          options << "centroid_ratio=#{Float(value)}"
         else
           raise ParadeDB::InvalidIndexDefinition, "unsupported index option #{key.inspect}"
         end
@@ -297,6 +300,7 @@ module ParadeDB
           c.relname  AS index_name,
           t.relname  AS table_name,
           pg_get_indexdef(c.oid) AS indexdef,
+          array_to_json(c.reloptions)::text AS reloptions,
           pg_get_expr(i.indpred, i.indrelid) AS where_clause
         FROM pg_class c
         JOIN pg_namespace n ON n.oid = c.relnamespace
@@ -319,7 +323,7 @@ module ParadeDB
       name = row["index_name"]
 
       key_field = extract_paradedb_key_field(indexdef)
-      index_options = extract_paradedb_index_options(indexdef)
+      index_options = extract_paradedb_index_options(row["reloptions"])
       fields_sql = extract_paradedb_fields_sql(indexdef)
       where = normalize_paradedb_where_clause(row["where_clause"])
 
@@ -369,27 +373,30 @@ module ParadeDB
       nil
     end
 
-    def extract_paradedb_index_options(indexdef)
-      with_sql, = extract_paradedb_with_components(indexdef)
-      options = {}
-      split_sql_arguments(with_sql).each do |argument|
-        key, value_sql = split_assignment(argument)
-        next if key.nil?
-        next if key == "key_field"
+    def extract_paradedb_index_options(reloptions)
+      paradedb_reloption_entries(reloptions).each_with_object({}) do |entry, options|
+        key, separator, value = entry.to_s.partition("=")
+        next if separator.empty?
 
         case key
-        when "target_segment_count"
-          parsed = parse_sql_literal(value_sql)
-          if parsed.is_a?(Integer)
-            options[:target_segment_count] = parsed
-          elsif parsed.is_a?(String) && parsed.match?(/\A\d+\z/)
-            options[:target_segment_count] = parsed.to_i
-          end
+        when "target_segment_count", "training_samples_per_centroid", "cluster_replication"
+          parsed = Integer(value, 10, exception: false)
+          options[key.to_sym] = parsed if parsed
+        when "centroid_ratio"
+          parsed = Float(value, exception: false)
+          options[:centroid_ratio] = parsed if parsed
         end
       end
-      options
-    rescue
-      {}
+    end
+
+    def paradedb_reloption_entries(reloptions)
+      case reloptions
+      when Array then reloptions
+      when String then Array(JSON.parse(reloptions))
+      else []
+      end
+    rescue JSON::ParserError
+      []
     end
 
     def extract_paradedb_fields_sql(indexdef)
@@ -410,27 +417,6 @@ module ParadeDB
       indexdef[start..pos - 2]
     end
 
-    def extract_paradedb_with_components(indexdef)
-      match = indexdef.match(/WITH\s*\(/im)
-      start = match.end(0)
-      depth = 1
-      pos = start
-      while pos < indexdef.length && depth > 0
-        case indexdef[pos]
-        when "(" then depth += 1
-        when ")" then depth -= 1
-        end
-        pos += 1
-      end
-      raise "Found invalid index definition `#{indexdef}`" if depth != 0
-
-      with_sql = indexdef[start..pos - 2]
-      trailing_sql = indexdef[pos..]&.strip
-      trailing_sql = nil if trailing_sql == ""
-
-      [with_sql, trailing_sql]
-    end
-
     def normalize_paradedb_where_clause(where)
       return nil if where.nil?
 

data/lib/parade_db/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ParadeDB
-  VERSION = "0.10.0"
+  VERSION = "0.11.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rails-paradedb
 version: !ruby/object:Gem::Version
-  version: 0.10.0
+  version: 0.11.0
 platform: ruby
 authors:
 - ParadeDB