Files
ruoyi-ai/docs/script/sql/update/2026-07-20-knowledge-fragment-fid.sql
ageerle 9a2f326e42 fix(rag): 合并后修正-升级脚本兼容 MySQL 8、重解析按 docId 清理旧向量
1. 升级脚本 2026-07-20-knowledge-fragment-fid.sql 使用了 MySQL 8 不支持的
   ADD COLUMN IF NOT EXISTS(MariaDB 语法),在存量库执行会直接语法报错。
   改为与脚本内索引守卫一致的 information_schema 判断 + PREPARE 方式,保持幂等。

2. parse() 重新解析时按 fragment.fid 删除旧向量:存量数据的 fid 为迁移脚本
   回填的 MD5 值,与向量库中实际存储的随机 fid 不一致,首次重解析无法命中
   旧向量,导致新旧向量重复累积。改为写入新向量前先按 docId 清理(三种
   向量库策略均支持),写入失败时仍补偿删除新 fid。

Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-21 14:33:28 +08:00

59 lines
3.2 KiB
SQL
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
-- RAG metadata migration (MySQL 8). Safe to execute repeatedly.
-- 注意MySQL 8 不支持 ALTER TABLE ... ADD COLUMN IF NOT EXISTS仅 MariaDB 支持),
-- 因此列的增量添加统一用 information_schema 守卫 + PREPARE 实现幂等。
SET @add_file_hash_col = IF(EXISTS(
SELECT 1 FROM information_schema.columns WHERE table_schema = DATABASE()
AND table_name = 'knowledge_attach' AND column_name = 'file_hash'),
'SELECT 1',
'ALTER TABLE `knowledge_attach` ADD COLUMN `file_hash` varchar(64) NULL DEFAULT NULL COMMENT ''文件SHA-256摘要'' AFTER `doc_id`');
PREPARE stmt FROM @add_file_hash_col; EXECUTE stmt; DEALLOCATE PREPARE stmt;
ALTER TABLE `knowledge_attach`
MODIFY COLUMN `doc_id` varchar(32) NULL DEFAULT NULL COMMENT '文档ID';
SET @add_file_hash = IF(EXISTS(
SELECT 1 FROM information_schema.statistics WHERE table_schema = DATABASE()
AND table_name = 'knowledge_attach' AND index_name = 'uk_knowledge_file_hash'),
'SELECT 1', 'ALTER TABLE `knowledge_attach` ADD UNIQUE INDEX `uk_knowledge_file_hash` (`knowledge_id`, `file_hash`)');
PREPARE stmt FROM @add_file_hash; EXECUTE stmt; DEALLOCATE PREPARE stmt;
SET @add_fid_col = IF(EXISTS(
SELECT 1 FROM information_schema.columns WHERE table_schema = DATABASE()
AND table_name = 'knowledge_fragment' AND column_name = 'fid'),
'SELECT 1',
'ALTER TABLE `knowledge_fragment` ADD COLUMN `fid` varchar(32) NULL DEFAULT NULL COMMENT ''向量库片段ID'' AFTER `id`');
PREPARE stmt FROM @add_fid_col; EXECUTE stmt; DEALLOCATE PREPARE stmt;
ALTER TABLE `knowledge_fragment`
MODIFY COLUMN `doc_id` varchar(32) NULL DEFAULT NULL COMMENT '文档ID';
UPDATE `knowledge_fragment`
SET `fid` = LOWER(MD5(CONCAT('knowledge_fragment:', `id`)))
WHERE `fid` IS NULL OR `fid` = '';
SET @drop_idx_fid = IF(EXISTS(
SELECT 1 FROM information_schema.statistics WHERE table_schema = DATABASE()
AND table_name = 'knowledge_fragment' AND index_name = 'idx_fid'),
'ALTER TABLE `knowledge_fragment` DROP INDEX `idx_fid`', 'SELECT 1');
PREPARE stmt FROM @drop_idx_fid; EXECUTE stmt; DEALLOCATE PREPARE stmt;
SET @add_uk_fid = IF(EXISTS(
SELECT 1 FROM information_schema.statistics WHERE table_schema = DATABASE()
AND table_name = 'knowledge_fragment' AND index_name = 'uk_fid'),
'SELECT 1', 'ALTER TABLE `knowledge_fragment` ADD UNIQUE INDEX `uk_fid` (`fid`)');
PREPARE stmt FROM @add_uk_fid; EXECUTE stmt; DEALLOCATE PREPARE stmt;
ALTER TABLE `knowledge_fragment` MODIFY COLUMN `fid` varchar(32) NOT NULL COMMENT '向量库片段ID';
SET @add_tenant_user = IF(EXISTS(
SELECT 1 FROM information_schema.statistics WHERE table_schema = DATABASE()
AND table_name = 'knowledge_info' AND index_name = 'idx_tenant_user'),
'SELECT 1', 'ALTER TABLE `knowledge_info` ADD INDEX `idx_tenant_user` (`tenant_id`, `user_id`)');
PREPARE stmt FROM @add_tenant_user; EXECUTE stmt; DEALLOCATE PREPARE stmt;
SET @add_tenant_share = IF(EXISTS(
SELECT 1 FROM information_schema.statistics WHERE table_schema = DATABASE()
AND table_name = 'knowledge_info' AND index_name = 'idx_tenant_share'),
'SELECT 1', 'ALTER TABLE `knowledge_info` ADD INDEX `idx_tenant_share` (`tenant_id`, `share`)');
PREPARE stmt FROM @add_tenant_share; EXECUTE stmt; DEALLOCATE PREPARE stmt;