feat(TRUEREF-0023): add sqlite-vec search pipeline
This commit is contained in:
@@ -4,6 +4,7 @@
|
||||
*/
|
||||
import Database from 'better-sqlite3';
|
||||
import { env } from '$env/dynamic/private';
|
||||
import { loadSqliteVec } from './sqlite-vec';
|
||||
|
||||
let _client: Database.Database | null = null;
|
||||
|
||||
@@ -14,6 +15,12 @@ export function getClient(): Database.Database {
|
||||
_client.pragma('journal_mode = WAL');
|
||||
_client.pragma('foreign_keys = ON');
|
||||
_client.pragma('busy_timeout = 5000');
|
||||
_client.pragma('synchronous = NORMAL');
|
||||
_client.pragma('cache_size = -65536');
|
||||
_client.pragma('temp_store = MEMORY');
|
||||
_client.pragma('mmap_size = 268435456');
|
||||
_client.pragma('wal_autocheckpoint = 1000');
|
||||
loadSqliteVec(_client);
|
||||
}
|
||||
return _client;
|
||||
}
|
||||
|
||||
@@ -5,6 +5,7 @@ import { readFileSync } from 'node:fs';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { join, dirname } from 'node:path';
|
||||
import * as schema from './schema';
|
||||
import { loadSqliteVec } from './sqlite-vec';
|
||||
import { env } from '$env/dynamic/private';
|
||||
|
||||
if (!env.DATABASE_URL) throw new Error('DATABASE_URL is not set');
|
||||
@@ -19,6 +20,12 @@ client.pragma('foreign_keys = ON');
|
||||
// Prevents SQLITE_BUSY errors when the indexing pipeline holds the write lock
|
||||
// and an HTTP request arrives simultaneously.
|
||||
client.pragma('busy_timeout = 5000');
|
||||
client.pragma('synchronous = NORMAL');
|
||||
client.pragma('cache_size = -65536');
|
||||
client.pragma('temp_store = MEMORY');
|
||||
client.pragma('mmap_size = 268435456');
|
||||
client.pragma('wal_autocheckpoint = 1000');
|
||||
loadSqliteVec(client);
|
||||
|
||||
export const db = drizzle(client, { schema });
|
||||
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
CREATE INDEX `idx_embeddings_profile` ON `snippet_embeddings` (`profile_id`,`snippet_id`);--> statement-breakpoint
|
||||
CREATE INDEX `idx_documents_repo_version` ON `documents` (`repository_id`,`version_id`);--> statement-breakpoint
|
||||
CREATE INDEX `idx_jobs_repo_status` ON `indexing_jobs` (`repository_id`,`status`);--> statement-breakpoint
|
||||
CREATE INDEX `idx_repositories_state` ON `repositories` (`state`);--> statement-breakpoint
|
||||
CREATE INDEX `idx_snippets_repo_version` ON `snippets` (`repository_id`,`version_id`);--> statement-breakpoint
|
||||
CREATE INDEX `idx_snippets_repo_type` ON `snippets` (`repository_id`,`type`);
|
||||
948
src/lib/server/db/migrations/meta/0006_snapshot.json
Normal file
948
src/lib/server/db/migrations/meta/0006_snapshot.json
Normal file
@@ -0,0 +1,948 @@
|
||||
{
|
||||
"version": "6",
|
||||
"dialect": "sqlite",
|
||||
"id": "b8998bda-f89b-41bc-b923-3f676d153c79",
|
||||
"prevId": "c326dcbe-1771-4a90-a566-0ebd1eca47ec",
|
||||
"tables": {
|
||||
"documents": {
|
||||
"name": "documents",
|
||||
"columns": {
|
||||
"id": {
|
||||
"name": "id",
|
||||
"type": "text",
|
||||
"primaryKey": true,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"repository_id": {
|
||||
"name": "repository_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"version_id": {
|
||||
"name": "version_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"file_path": {
|
||||
"name": "file_path",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"title": {
|
||||
"name": "title",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"language": {
|
||||
"name": "language",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"token_count": {
|
||||
"name": "token_count",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"checksum": {
|
||||
"name": "checksum",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"indexed_at": {
|
||||
"name": "indexed_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {
|
||||
"idx_documents_repo_version": {
|
||||
"name": "idx_documents_repo_version",
|
||||
"columns": [
|
||||
"repository_id",
|
||||
"version_id"
|
||||
],
|
||||
"isUnique": false
|
||||
}
|
||||
},
|
||||
"foreignKeys": {
|
||||
"documents_repository_id_repositories_id_fk": {
|
||||
"name": "documents_repository_id_repositories_id_fk",
|
||||
"tableFrom": "documents",
|
||||
"tableTo": "repositories",
|
||||
"columnsFrom": [
|
||||
"repository_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
},
|
||||
"documents_version_id_repository_versions_id_fk": {
|
||||
"name": "documents_version_id_repository_versions_id_fk",
|
||||
"tableFrom": "documents",
|
||||
"tableTo": "repository_versions",
|
||||
"columnsFrom": [
|
||||
"version_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
}
|
||||
},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
},
|
||||
"embedding_profiles": {
|
||||
"name": "embedding_profiles",
|
||||
"columns": {
|
||||
"id": {
|
||||
"name": "id",
|
||||
"type": "text",
|
||||
"primaryKey": true,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"provider_kind": {
|
||||
"name": "provider_kind",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"title": {
|
||||
"name": "title",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"enabled": {
|
||||
"name": "enabled",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false,
|
||||
"default": true
|
||||
},
|
||||
"is_default": {
|
||||
"name": "is_default",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false,
|
||||
"default": false
|
||||
},
|
||||
"model": {
|
||||
"name": "model",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"dimensions": {
|
||||
"name": "dimensions",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"config": {
|
||||
"name": "config",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"created_at": {
|
||||
"name": "created_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"updated_at": {
|
||||
"name": "updated_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {},
|
||||
"foreignKeys": {},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
},
|
||||
"indexing_jobs": {
|
||||
"name": "indexing_jobs",
|
||||
"columns": {
|
||||
"id": {
|
||||
"name": "id",
|
||||
"type": "text",
|
||||
"primaryKey": true,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"repository_id": {
|
||||
"name": "repository_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"version_id": {
|
||||
"name": "version_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"status": {
|
||||
"name": "status",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false,
|
||||
"default": "'queued'"
|
||||
},
|
||||
"progress": {
|
||||
"name": "progress",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"total_files": {
|
||||
"name": "total_files",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"processed_files": {
|
||||
"name": "processed_files",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"stage": {
|
||||
"name": "stage",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false,
|
||||
"default": "'queued'"
|
||||
},
|
||||
"stage_detail": {
|
||||
"name": "stage_detail",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"error": {
|
||||
"name": "error",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"started_at": {
|
||||
"name": "started_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"completed_at": {
|
||||
"name": "completed_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"created_at": {
|
||||
"name": "created_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {
|
||||
"idx_jobs_repo_status": {
|
||||
"name": "idx_jobs_repo_status",
|
||||
"columns": [
|
||||
"repository_id",
|
||||
"status"
|
||||
],
|
||||
"isUnique": false
|
||||
}
|
||||
},
|
||||
"foreignKeys": {
|
||||
"indexing_jobs_repository_id_repositories_id_fk": {
|
||||
"name": "indexing_jobs_repository_id_repositories_id_fk",
|
||||
"tableFrom": "indexing_jobs",
|
||||
"tableTo": "repositories",
|
||||
"columnsFrom": [
|
||||
"repository_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
}
|
||||
},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
},
|
||||
"repositories": {
|
||||
"name": "repositories",
|
||||
"columns": {
|
||||
"id": {
|
||||
"name": "id",
|
||||
"type": "text",
|
||||
"primaryKey": true,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"title": {
|
||||
"name": "title",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"description": {
|
||||
"name": "description",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"source_url": {
|
||||
"name": "source_url",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"branch": {
|
||||
"name": "branch",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": "'main'"
|
||||
},
|
||||
"state": {
|
||||
"name": "state",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false,
|
||||
"default": "'pending'"
|
||||
},
|
||||
"total_snippets": {
|
||||
"name": "total_snippets",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"total_tokens": {
|
||||
"name": "total_tokens",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"trust_score": {
|
||||
"name": "trust_score",
|
||||
"type": "real",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"benchmark_score": {
|
||||
"name": "benchmark_score",
|
||||
"type": "real",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"stars": {
|
||||
"name": "stars",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"github_token": {
|
||||
"name": "github_token",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"last_indexed_at": {
|
||||
"name": "last_indexed_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"created_at": {
|
||||
"name": "created_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"updated_at": {
|
||||
"name": "updated_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {
|
||||
"idx_repositories_state": {
|
||||
"name": "idx_repositories_state",
|
||||
"columns": [
|
||||
"state"
|
||||
],
|
||||
"isUnique": false
|
||||
}
|
||||
},
|
||||
"foreignKeys": {},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
},
|
||||
"repository_configs": {
|
||||
"name": "repository_configs",
|
||||
"columns": {
|
||||
"repository_id": {
|
||||
"name": "repository_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"version_id": {
|
||||
"name": "version_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"project_title": {
|
||||
"name": "project_title",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"description": {
|
||||
"name": "description",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"folders": {
|
||||
"name": "folders",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"exclude_folders": {
|
||||
"name": "exclude_folders",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"exclude_files": {
|
||||
"name": "exclude_files",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"rules": {
|
||||
"name": "rules",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"previous_versions": {
|
||||
"name": "previous_versions",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"updated_at": {
|
||||
"name": "updated_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {
|
||||
"uniq_repo_config_base": {
|
||||
"name": "uniq_repo_config_base",
|
||||
"columns": [
|
||||
"repository_id"
|
||||
],
|
||||
"isUnique": true,
|
||||
"where": "\"repository_configs\".\"version_id\" IS NULL"
|
||||
},
|
||||
"uniq_repo_config_version": {
|
||||
"name": "uniq_repo_config_version",
|
||||
"columns": [
|
||||
"repository_id",
|
||||
"version_id"
|
||||
],
|
||||
"isUnique": true,
|
||||
"where": "\"repository_configs\".\"version_id\" IS NOT NULL"
|
||||
}
|
||||
},
|
||||
"foreignKeys": {
|
||||
"repository_configs_repository_id_repositories_id_fk": {
|
||||
"name": "repository_configs_repository_id_repositories_id_fk",
|
||||
"tableFrom": "repository_configs",
|
||||
"tableTo": "repositories",
|
||||
"columnsFrom": [
|
||||
"repository_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
}
|
||||
},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
},
|
||||
"repository_versions": {
|
||||
"name": "repository_versions",
|
||||
"columns": {
|
||||
"id": {
|
||||
"name": "id",
|
||||
"type": "text",
|
||||
"primaryKey": true,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"repository_id": {
|
||||
"name": "repository_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"tag": {
|
||||
"name": "tag",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"title": {
|
||||
"name": "title",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"commit_hash": {
|
||||
"name": "commit_hash",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"state": {
|
||||
"name": "state",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false,
|
||||
"default": "'pending'"
|
||||
},
|
||||
"total_snippets": {
|
||||
"name": "total_snippets",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"indexed_at": {
|
||||
"name": "indexed_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"created_at": {
|
||||
"name": "created_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {},
|
||||
"foreignKeys": {
|
||||
"repository_versions_repository_id_repositories_id_fk": {
|
||||
"name": "repository_versions_repository_id_repositories_id_fk",
|
||||
"tableFrom": "repository_versions",
|
||||
"tableTo": "repositories",
|
||||
"columnsFrom": [
|
||||
"repository_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
}
|
||||
},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
},
|
||||
"settings": {
|
||||
"name": "settings",
|
||||
"columns": {
|
||||
"key": {
|
||||
"name": "key",
|
||||
"type": "text",
|
||||
"primaryKey": true,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"value": {
|
||||
"name": "value",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"updated_at": {
|
||||
"name": "updated_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {},
|
||||
"foreignKeys": {},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
},
|
||||
"snippet_embeddings": {
|
||||
"name": "snippet_embeddings",
|
||||
"columns": {
|
||||
"snippet_id": {
|
||||
"name": "snippet_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"profile_id": {
|
||||
"name": "profile_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"model": {
|
||||
"name": "model",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"dimensions": {
|
||||
"name": "dimensions",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"embedding": {
|
||||
"name": "embedding",
|
||||
"type": "blob",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"created_at": {
|
||||
"name": "created_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {
|
||||
"idx_embeddings_profile": {
|
||||
"name": "idx_embeddings_profile",
|
||||
"columns": [
|
||||
"profile_id",
|
||||
"snippet_id"
|
||||
],
|
||||
"isUnique": false
|
||||
}
|
||||
},
|
||||
"foreignKeys": {
|
||||
"snippet_embeddings_snippet_id_snippets_id_fk": {
|
||||
"name": "snippet_embeddings_snippet_id_snippets_id_fk",
|
||||
"tableFrom": "snippet_embeddings",
|
||||
"tableTo": "snippets",
|
||||
"columnsFrom": [
|
||||
"snippet_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
},
|
||||
"snippet_embeddings_profile_id_embedding_profiles_id_fk": {
|
||||
"name": "snippet_embeddings_profile_id_embedding_profiles_id_fk",
|
||||
"tableFrom": "snippet_embeddings",
|
||||
"tableTo": "embedding_profiles",
|
||||
"columnsFrom": [
|
||||
"profile_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
}
|
||||
},
|
||||
"compositePrimaryKeys": {
|
||||
"snippet_embeddings_snippet_id_profile_id_pk": {
|
||||
"columns": [
|
||||
"snippet_id",
|
||||
"profile_id"
|
||||
],
|
||||
"name": "snippet_embeddings_snippet_id_profile_id_pk"
|
||||
}
|
||||
},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
},
|
||||
"snippets": {
|
||||
"name": "snippets",
|
||||
"columns": {
|
||||
"id": {
|
||||
"name": "id",
|
||||
"type": "text",
|
||||
"primaryKey": true,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"document_id": {
|
||||
"name": "document_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"repository_id": {
|
||||
"name": "repository_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"version_id": {
|
||||
"name": "version_id",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"type": {
|
||||
"name": "type",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"title": {
|
||||
"name": "title",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
},
|
||||
"language": {
|
||||
"name": "language",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"breadcrumb": {
|
||||
"name": "breadcrumb",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false
|
||||
},
|
||||
"token_count": {
|
||||
"name": "token_count",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": false,
|
||||
"autoincrement": false,
|
||||
"default": 0
|
||||
},
|
||||
"created_at": {
|
||||
"name": "created_at",
|
||||
"type": "integer",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"autoincrement": false
|
||||
}
|
||||
},
|
||||
"indexes": {
|
||||
"idx_snippets_repo_version": {
|
||||
"name": "idx_snippets_repo_version",
|
||||
"columns": [
|
||||
"repository_id",
|
||||
"version_id"
|
||||
],
|
||||
"isUnique": false
|
||||
},
|
||||
"idx_snippets_repo_type": {
|
||||
"name": "idx_snippets_repo_type",
|
||||
"columns": [
|
||||
"repository_id",
|
||||
"type"
|
||||
],
|
||||
"isUnique": false
|
||||
}
|
||||
},
|
||||
"foreignKeys": {
|
||||
"snippets_document_id_documents_id_fk": {
|
||||
"name": "snippets_document_id_documents_id_fk",
|
||||
"tableFrom": "snippets",
|
||||
"tableTo": "documents",
|
||||
"columnsFrom": [
|
||||
"document_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
},
|
||||
"snippets_repository_id_repositories_id_fk": {
|
||||
"name": "snippets_repository_id_repositories_id_fk",
|
||||
"tableFrom": "snippets",
|
||||
"tableTo": "repositories",
|
||||
"columnsFrom": [
|
||||
"repository_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
},
|
||||
"snippets_version_id_repository_versions_id_fk": {
|
||||
"name": "snippets_version_id_repository_versions_id_fk",
|
||||
"tableFrom": "snippets",
|
||||
"tableTo": "repository_versions",
|
||||
"columnsFrom": [
|
||||
"version_id"
|
||||
],
|
||||
"columnsTo": [
|
||||
"id"
|
||||
],
|
||||
"onDelete": "cascade",
|
||||
"onUpdate": "no action"
|
||||
}
|
||||
},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {},
|
||||
"checkConstraints": {}
|
||||
}
|
||||
},
|
||||
"views": {},
|
||||
"enums": {},
|
||||
"_meta": {
|
||||
"schemas": {},
|
||||
"tables": {},
|
||||
"columns": {}
|
||||
},
|
||||
"internal": {
|
||||
"indexes": {}
|
||||
}
|
||||
}
|
||||
@@ -43,6 +43,13 @@
|
||||
"when": 1774890536284,
|
||||
"tag": "0005_fix_stage_defaults",
|
||||
"breakpoints": true
|
||||
},
|
||||
{
|
||||
"idx": 6,
|
||||
"version": "6",
|
||||
"when": 1775038799913,
|
||||
"tag": "0006_yielding_centennial",
|
||||
"breakpoints": true
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -6,6 +6,7 @@ import { readFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { eq } from 'drizzle-orm';
|
||||
import * as schema from './schema';
|
||||
import { loadSqliteVec, sqliteVecRowidTableName, sqliteVecTableName } from './sqlite-vec';
|
||||
import {
|
||||
repositories,
|
||||
repositoryVersions,
|
||||
@@ -24,6 +25,7 @@ import {
|
||||
function createTestDb() {
|
||||
const client = new Database(':memory:');
|
||||
client.pragma('foreign_keys = ON');
|
||||
loadSqliteVec(client);
|
||||
|
||||
const db = drizzle(client, { schema });
|
||||
|
||||
@@ -266,10 +268,11 @@ describe('snippets table', () => {
|
||||
|
||||
describe('snippet_embeddings table', () => {
|
||||
let db: ReturnType<typeof createTestDb>['db'];
|
||||
let client: Database.Database;
|
||||
let snippetId: string;
|
||||
|
||||
beforeEach(() => {
|
||||
({ db } = createTestDb());
|
||||
({ db, client } = createTestDb());
|
||||
db.insert(repositories).values(makeRepo()).run();
|
||||
const docId = crypto.randomUUID();
|
||||
db.insert(documents)
|
||||
@@ -344,6 +347,30 @@ describe('snippet_embeddings table', () => {
|
||||
const result = db.select().from(snippetEmbeddings).all();
|
||||
expect(result).toHaveLength(0);
|
||||
});
|
||||
|
||||
it('keeps the relational schema free of vec_embedding and retains the profile index', () => {
|
||||
const columns = client
|
||||
.prepare("PRAGMA table_info('snippet_embeddings')")
|
||||
.all() as Array<{ name: string }>;
|
||||
expect(columns.map((column) => column.name)).not.toContain('vec_embedding');
|
||||
|
||||
const indexes = client
|
||||
.prepare("PRAGMA index_list('snippet_embeddings')")
|
||||
.all() as Array<{ name: string }>;
|
||||
expect(indexes.map((index) => index.name)).toContain('idx_embeddings_profile');
|
||||
});
|
||||
|
||||
it('loads sqlite-vec idempotently and derives deterministic per-profile table names', () => {
|
||||
expect(() => loadSqliteVec(client)).not.toThrow();
|
||||
const tableName = sqliteVecTableName('local-default');
|
||||
const rowidTableName = sqliteVecRowidTableName('local-default');
|
||||
|
||||
expect(tableName).toMatch(/^snippet_embeddings_vec_local_default_[0-9a-f]{8}$/);
|
||||
expect(rowidTableName).toMatch(/^snippet_embeddings_vec_rowids_local_default_[0-9a-f]{8}$/);
|
||||
expect(sqliteVecTableName('local-default')).toBe(tableName);
|
||||
expect(sqliteVecRowidTableName('local-default')).toBe(rowidTableName);
|
||||
expect(sqliteVecTableName('local-default')).not.toBe(sqliteVecTableName('openai/custom'));
|
||||
});
|
||||
});
|
||||
|
||||
describe('indexing_jobs table', () => {
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
import { sql } from 'drizzle-orm';
|
||||
import {
|
||||
blob,
|
||||
index,
|
||||
integer,
|
||||
primaryKey,
|
||||
real,
|
||||
@@ -34,7 +35,7 @@ export const repositories = sqliteTable('repositories', {
|
||||
lastIndexedAt: integer('last_indexed_at', { mode: 'timestamp' }),
|
||||
createdAt: integer('created_at', { mode: 'timestamp' }).notNull(),
|
||||
updatedAt: integer('updated_at', { mode: 'timestamp' }).notNull()
|
||||
});
|
||||
}, (t) => [index('idx_repositories_state').on(t.state)]);
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// repository_versions
|
||||
@@ -72,7 +73,7 @@ export const documents = sqliteTable('documents', {
|
||||
tokenCount: integer('token_count').default(0),
|
||||
checksum: text('checksum').notNull(), // SHA-256 of file content
|
||||
indexedAt: integer('indexed_at', { mode: 'timestamp' }).notNull()
|
||||
});
|
||||
}, (t) => [index('idx_documents_repo_version').on(t.repositoryId, t.versionId)]);
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// snippets
|
||||
@@ -93,7 +94,10 @@ export const snippets = sqliteTable('snippets', {
|
||||
breadcrumb: text('breadcrumb'), // e.g. "Installation > Getting Started"
|
||||
tokenCount: integer('token_count').default(0),
|
||||
createdAt: integer('created_at', { mode: 'timestamp' }).notNull()
|
||||
});
|
||||
}, (t) => [
|
||||
index('idx_snippets_repo_version').on(t.repositoryId, t.versionId),
|
||||
index('idx_snippets_repo_type').on(t.repositoryId, t.type),
|
||||
]);
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// embedding_profiles
|
||||
@@ -128,7 +132,10 @@ export const snippetEmbeddings = sqliteTable(
|
||||
embedding: blob('embedding').notNull(), // Float32Array as binary blob
|
||||
createdAt: integer('created_at').notNull()
|
||||
},
|
||||
(table) => [primaryKey({ columns: [table.snippetId, table.profileId] })]
|
||||
(table) => [
|
||||
primaryKey({ columns: [table.snippetId, table.profileId] }),
|
||||
index('idx_embeddings_profile').on(table.profileId, table.snippetId),
|
||||
]
|
||||
);
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
@@ -154,7 +161,7 @@ export const indexingJobs = sqliteTable('indexing_jobs', {
|
||||
startedAt: integer('started_at', { mode: 'timestamp' }),
|
||||
completedAt: integer('completed_at', { mode: 'timestamp' }),
|
||||
createdAt: integer('created_at', { mode: 'timestamp' }).notNull()
|
||||
});
|
||||
}, (t) => [index('idx_jobs_repo_status').on(t.repositoryId, t.status)]);
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// repository_configs
|
||||
|
||||
49
src/lib/server/db/sqlite-vec.ts
Normal file
49
src/lib/server/db/sqlite-vec.ts
Normal file
@@ -0,0 +1,49 @@
|
||||
import type Database from 'better-sqlite3';
|
||||
import * as sqliteVec from 'sqlite-vec';
|
||||
|
||||
const loadedConnections = new WeakSet<Database.Database>();
|
||||
|
||||
function stableHash(value: string): string {
|
||||
let hash = 2166136261;
|
||||
|
||||
for (let index = 0; index < value.length; index += 1) {
|
||||
hash ^= value.charCodeAt(index);
|
||||
hash = Math.imul(hash, 16777619);
|
||||
}
|
||||
|
||||
return (hash >>> 0).toString(16).padStart(8, '0');
|
||||
}
|
||||
|
||||
function sanitizeIdentifierPart(value: string): string {
|
||||
const sanitized = value
|
||||
.toLowerCase()
|
||||
.replace(/[^a-z0-9]+/g, '_')
|
||||
.replace(/^_+|_+$/g, '');
|
||||
|
||||
return sanitized.length > 0 ? sanitized.slice(0, 32) : 'profile';
|
||||
}
|
||||
|
||||
export function sqliteVecTableSuffix(profileId: string): string {
|
||||
return `${sanitizeIdentifierPart(profileId)}_${stableHash(profileId)}`;
|
||||
}
|
||||
|
||||
export function sqliteVecTableName(profileId: string): string {
|
||||
return `snippet_embeddings_vec_${sqliteVecTableSuffix(profileId)}`;
|
||||
}
|
||||
|
||||
export function sqliteVecRowidTableName(profileId: string): string {
|
||||
return `snippet_embeddings_vec_rowids_${sqliteVecTableSuffix(profileId)}`;
|
||||
}
|
||||
|
||||
export function quoteSqliteIdentifier(identifier: string): string {
|
||||
return `"${identifier.replace(/"/g, '""')}"`;
|
||||
}
|
||||
|
||||
export function loadSqliteVec(db: Database.Database): void {
|
||||
if (loadedConnections.has(db)) {
|
||||
return;
|
||||
}
|
||||
|
||||
sqliteVec.load(db);
|
||||
loadedConnections.add(db);
|
||||
}
|
||||
2
src/lib/server/db/vectors.sql
Normal file
2
src/lib/server/db/vectors.sql
Normal file
@@ -0,0 +1,2 @@
|
||||
-- Relational vec_embedding bootstrap removed in iteration 2.
|
||||
-- Downstream sqlite-vec vec0 tables are created on demand in application code.
|
||||
Reference in New Issue
Block a user