Add semantic package search via pgvector embeddings
Package text search now combines several strategies: exact name match,
name prefix promotion, compound word splitting ("sqlite browser" finds
"sqlitebrowser") and semantic nearest neighbor search over description
embeddings computed by an external embedding service (all-MiniLM-L6-v2,
384 dims) stored with the pgvector extension. Classic PostgreSQL
full-text search remains as fallback when the vector service is
unreachable. Gibberish queries without lexical overlap with the package
data return empty results instead of random matches.
Embeddings can be backfilled with bin/rails debshots:compute_vectors.
Also drops the unused lograge gem from the Gemfile.
This commit is contained in:
parent
c7e8109bbd
commit
4948fe50e3
15 changed files with 662 additions and 125 deletions
218
db/schema.rb
generated
218
db/schema.rb
generated
|
|
@ -10,133 +10,131 @@
|
|||
#
|
||||
# It's strongly recommended that you check this file into your version control system.
|
||||
|
||||
ActiveRecord::Schema[8.0].define(version: 2023_11_26_173151) do
|
||||
# These are extensions that must be enabled to support this database
|
||||
enable_extension 'pg_catalog.plpgsql'
|
||||
ActiveRecord::Schema[8.1].define(version: 2026_08_21_210000) do
|
||||
# These are extensions that must be enabled in order to support this database
|
||||
enable_extension "pg_catalog.plpgsql"
|
||||
enable_extension "vector"
|
||||
|
||||
create_table 'action_mailbox_inbound_emails', force: :cascade do |t|
|
||||
t.integer 'status', default: 0, null: false
|
||||
t.string 'message_id', null: false
|
||||
t.string 'message_checksum', null: false
|
||||
t.datetime 'created_at', null: false
|
||||
t.datetime 'updated_at', null: false
|
||||
t.index ['message_id', 'message_checksum'],
|
||||
name: 'index_action_mailbox_inbound_emails_uniqueness', unique: true
|
||||
create_table "action_mailbox_inbound_emails", force: :cascade do |t|
|
||||
t.datetime "created_at", null: false
|
||||
t.string "message_checksum", null: false
|
||||
t.string "message_id", null: false
|
||||
t.integer "status", default: 0, null: false
|
||||
t.datetime "updated_at", null: false
|
||||
t.index ["message_id", "message_checksum"], name: "index_action_mailbox_inbound_emails_uniqueness", unique: true
|
||||
end
|
||||
|
||||
create_table 'action_text_rich_texts', force: :cascade do |t|
|
||||
t.string 'name', null: false
|
||||
t.text 'body'
|
||||
t.string 'record_type', null: false
|
||||
t.bigint 'record_id', null: false
|
||||
t.datetime 'created_at', null: false
|
||||
t.datetime 'updated_at', null: false
|
||||
t.index ['record_type', 'record_id', 'name'], name: 'index_action_text_rich_texts_uniqueness',
|
||||
unique: true
|
||||
create_table "action_text_rich_texts", force: :cascade do |t|
|
||||
t.text "body"
|
||||
t.datetime "created_at", null: false
|
||||
t.string "name", null: false
|
||||
t.bigint "record_id", null: false
|
||||
t.string "record_type", null: false
|
||||
t.datetime "updated_at", null: false
|
||||
t.index ["record_type", "record_id", "name"], name: "index_action_text_rich_texts_uniqueness", unique: true
|
||||
end
|
||||
|
||||
create_table 'active_storage_attachments', force: :cascade do |t|
|
||||
t.string 'name', null: false
|
||||
t.string 'record_type', null: false
|
||||
t.bigint 'record_id', null: false
|
||||
t.bigint 'blob_id', null: false
|
||||
t.datetime 'created_at', precision: nil, null: false
|
||||
t.index ['blob_id'], name: 'index_active_storage_attachments_on_blob_id'
|
||||
t.index ['record_type', 'record_id', 'name', 'blob_id'],
|
||||
name: 'index_active_storage_attachments_uniqueness', unique: true
|
||||
create_table "active_storage_attachments", force: :cascade do |t|
|
||||
t.bigint "blob_id", null: false
|
||||
t.datetime "created_at", precision: nil, null: false
|
||||
t.string "name", null: false
|
||||
t.bigint "record_id", null: false
|
||||
t.string "record_type", null: false
|
||||
t.index ["blob_id"], name: "index_active_storage_attachments_on_blob_id"
|
||||
t.index ["record_type", "record_id", "name", "blob_id"], name: "index_active_storage_attachments_uniqueness", unique: true
|
||||
end
|
||||
|
||||
create_table 'active_storage_blobs', force: :cascade do |t|
|
||||
t.string 'key', null: false
|
||||
t.string 'filename', null: false
|
||||
t.string 'content_type'
|
||||
t.text 'metadata'
|
||||
t.bigint 'byte_size', null: false
|
||||
t.string 'checksum'
|
||||
t.datetime 'created_at', precision: nil, null: false
|
||||
t.string 'service_name', null: false
|
||||
t.index ['key'], name: 'index_active_storage_blobs_on_key', unique: true
|
||||
create_table "active_storage_blobs", force: :cascade do |t|
|
||||
t.bigint "byte_size", null: false
|
||||
t.string "checksum"
|
||||
t.string "content_type"
|
||||
t.datetime "created_at", precision: nil, null: false
|
||||
t.string "filename", null: false
|
||||
t.string "key", null: false
|
||||
t.text "metadata"
|
||||
t.string "service_name", null: false
|
||||
t.index ["key"], name: "index_active_storage_blobs_on_key", unique: true
|
||||
end
|
||||
|
||||
create_table 'active_storage_variant_records', force: :cascade do |t|
|
||||
t.bigint 'blob_id', null: false
|
||||
t.string 'variation_digest', null: false
|
||||
t.index ['blob_id', 'variation_digest'],
|
||||
name: 'index_active_storage_variant_records_uniqueness', unique: true
|
||||
create_table "active_storage_variant_records", force: :cascade do |t|
|
||||
t.bigint "blob_id", null: false
|
||||
t.string "variation_digest", null: false
|
||||
t.index ["blob_id", "variation_digest"], name: "index_active_storage_variant_records_uniqueness", unique: true
|
||||
end
|
||||
|
||||
create_table 'logs', id: :serial, force: :cascade do |t|
|
||||
t.string 'message'
|
||||
t.string 'level'
|
||||
t.string 'section'
|
||||
t.inet 'ip_address'
|
||||
t.datetime 'created_at', precision: nil, null: false
|
||||
t.datetime 'updated_at', precision: nil, null: false
|
||||
t.integer 'user_id'
|
||||
t.integer 'package_id'
|
||||
t.integer 'screenshot_id'
|
||||
create_table "logs", id: :serial, force: :cascade do |t|
|
||||
t.datetime "created_at", precision: nil, null: false
|
||||
t.inet "ip_address"
|
||||
t.string "level"
|
||||
t.string "message"
|
||||
t.integer "package_id"
|
||||
t.integer "screenshot_id"
|
||||
t.string "section"
|
||||
t.datetime "updated_at", precision: nil, null: false
|
||||
t.integer "user_id"
|
||||
end
|
||||
|
||||
create_table 'packages', id: :serial, force: :cascade do |t|
|
||||
t.string 'name', null: false
|
||||
t.string 'description', limit: 80
|
||||
t.string 'section', limit: 50
|
||||
t.string 'maintainer', limit: 100
|
||||
t.string 'maintainer_email', limit: 100
|
||||
t.string 'homepage', limit: 400
|
||||
t.string 'version', limit: 200
|
||||
t.text 'long_description'
|
||||
t.string 'origin', limit: 80
|
||||
t.datetime 'created_at', precision: nil
|
||||
t.datetime 'updated_at', precision: nil
|
||||
t.integer 'visits', default: 0
|
||||
t.index "(((setweight(to_tsvector('english'::regconfig, COALESCE((name)::text, ''::text)), 'A'::\"char\") || setweight(to_tsvector('english'::regconfig, COALESCE((description)::text, ''::text)), 'B'::\"char\")) || setweight(to_tsvector('english'::regconfig, COALESCE(long_description, ''::text)), 'C'::\"char\")))",
|
||||
name: 'packages_fts', using: :gin
|
||||
t.unique_constraint ['name'], name: 'packages_name_key'
|
||||
create_table "packages", id: :serial, force: :cascade do |t|
|
||||
t.datetime "created_at", precision: nil
|
||||
t.string "description", limit: 80
|
||||
t.vector "embedding", limit: 384
|
||||
t.string "homepage", limit: 400
|
||||
t.text "long_description"
|
||||
t.string "maintainer", limit: 100
|
||||
t.string "maintainer_email", limit: 100
|
||||
t.string "name", null: false
|
||||
t.string "origin", limit: 80
|
||||
t.string "section", limit: 50
|
||||
t.datetime "updated_at", precision: nil
|
||||
t.string "version", limit: 200
|
||||
t.integer "visits", default: 0
|
||||
t.index "(((setweight(to_tsvector('english'::regconfig, COALESCE((name)::text, ''::text)), 'A'::\"char\") || setweight(to_tsvector('english'::regconfig, COALESCE((description)::text, ''::text)), 'B'::\"char\")) || setweight(to_tsvector('english'::regconfig, COALESCE(long_description, ''::text)), 'C'::\"char\")))", name: "packages_fts", using: :gin
|
||||
t.index ["embedding"], name: "index_packages_on_embedding", opclass: :vector_cosine_ops, using: :hnsw
|
||||
t.unique_constraint ["name"], name: "packages_name_key"
|
||||
end
|
||||
|
||||
create_table 'screenshots', id: :serial, force: :cascade do |t|
|
||||
t.integer 'package_id'
|
||||
t.string 'version', limit: 50
|
||||
t.datetime 'created_at', precision: nil
|
||||
t.string 'uploaderhash', limit: 72
|
||||
t.boolean 'approved', default: false, null: false
|
||||
t.text 'description'
|
||||
t.datetime 'updated_at', precision: nil
|
||||
t.string 'image_fingerprint'
|
||||
t.integer 'user_id', default: 0
|
||||
t.text 'simage_data'
|
||||
t.inet 'uploaderip'
|
||||
t.boolean 'hidden', default: false
|
||||
t.index ['id', 'approved'], name: 'id_approved'
|
||||
t.index ['id', 'uploaderhash'], name: 'id_uploaderhash'
|
||||
create_table "screenshots", id: :serial, force: :cascade do |t|
|
||||
t.boolean "approved", default: false, null: false
|
||||
t.datetime "created_at", precision: nil
|
||||
t.text "description"
|
||||
t.boolean "hidden", default: false
|
||||
t.string "image_fingerprint"
|
||||
t.integer "package_id"
|
||||
t.text "simage_data"
|
||||
t.datetime "updated_at", precision: nil
|
||||
t.string "uploaderhash", limit: 72
|
||||
t.inet "uploaderip"
|
||||
t.integer "user_id", default: 0
|
||||
t.string "version", limit: 50
|
||||
t.index ["id", "approved"], name: "id_approved"
|
||||
t.index ["id", "uploaderhash"], name: "id_uploaderhash"
|
||||
end
|
||||
|
||||
create_table 'users', id: :serial, force: :cascade do |t|
|
||||
t.text 'name'
|
||||
t.datetime 'created_at', precision: nil, null: false
|
||||
t.datetime 'updated_at', precision: nil, null: false
|
||||
t.string 'email', default: '', null: false
|
||||
t.string 'encrypted_password', default: '', null: false
|
||||
t.integer 'sign_in_count', default: 0, null: false
|
||||
t.datetime 'current_sign_in_at', precision: nil
|
||||
t.datetime 'last_sign_in_at', precision: nil
|
||||
t.inet 'current_sign_in_ip'
|
||||
t.inet 'last_sign_in_ip'
|
||||
t.integer 'failed_attempts', default: 0, null: false
|
||||
t.string 'unlock_token'
|
||||
t.datetime 'locked_at', precision: nil
|
||||
t.string 'provider'
|
||||
t.string 'uid'
|
||||
t.boolean 'admin_role', default: false
|
||||
t.boolean 'moderator_role', default: false
|
||||
t.boolean 'pseudo', default: false
|
||||
t.integer 'approved_screenshots', default: 0
|
||||
t.integer 'rejected_screenshots', default: 0
|
||||
t.index ['email', 'provider'], name: 'index_users_on_email_and_provider', unique: true
|
||||
create_table "users", id: :serial, force: :cascade do |t|
|
||||
t.boolean "admin_role", default: false
|
||||
t.integer "approved_screenshots", default: 0
|
||||
t.datetime "created_at", precision: nil, null: false
|
||||
t.datetime "current_sign_in_at", precision: nil
|
||||
t.inet "current_sign_in_ip"
|
||||
t.string "email", default: "", null: false
|
||||
t.string "encrypted_password", default: "", null: false
|
||||
t.integer "failed_attempts", default: 0, null: false
|
||||
t.datetime "last_sign_in_at", precision: nil
|
||||
t.inet "last_sign_in_ip"
|
||||
t.datetime "locked_at", precision: nil
|
||||
t.boolean "moderator_role", default: false
|
||||
t.text "name"
|
||||
t.string "provider"
|
||||
t.boolean "pseudo", default: false
|
||||
t.integer "rejected_screenshots", default: 0
|
||||
t.integer "sign_in_count", default: 0, null: false
|
||||
t.string "uid"
|
||||
t.string "unlock_token"
|
||||
t.datetime "updated_at", precision: nil, null: false
|
||||
t.index ["email", "provider"], name: "index_users_on_email_and_provider", unique: true
|
||||
end
|
||||
|
||||
add_foreign_key 'active_storage_attachments', 'active_storage_blobs', column: 'blob_id'
|
||||
add_foreign_key 'active_storage_variant_records', 'active_storage_blobs', column: 'blob_id'
|
||||
add_foreign_key 'screenshots', 'packages', name: 'screenshots_package_id_fkey'
|
||||
add_foreign_key "active_storage_attachments", "active_storage_blobs", column: "blob_id"
|
||||
add_foreign_key "active_storage_variant_records", "active_storage_blobs", column: "blob_id"
|
||||
add_foreign_key "screenshots", "packages", name: "screenshots_package_id_fkey"
|
||||
end
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue