refactor: 重构文档处理流程和任务管理

This commit is contained in:
2026-04-09 09:11:43 +08:00
parent b6896f3fb4
commit 7f894745e9
34 changed files with 1216 additions and 1056 deletions

View File

@@ -114,6 +114,7 @@ COMMENT ON COLUMN rag_knowledge_document.file_path IS '文件存储路径如M
COMMENT ON COLUMN rag_knowledge_document.metadata IS '文件元数据,结构:{"author":"作者","tags":["标签1","标签2"],"custom":{"key":"值"}}';
--------------------pgsql创建rag_knowledge_document表语句---------------------------
--------------------pgsql创建rag_knowledge_keyword表语句---------------------------
-- 关键词表(文档关键词+权重)
CREATE TABLE IF NOT EXISTS rag_knowledge_keyword (
@@ -161,6 +162,49 @@ COMMENT ON COLUMN rag_knowledge_keyword.weight IS '权重';
--------------------pgsql创建rag_knowledge_keyword表语句---------------------------
--------------------pgsql创建rag_knowledge_task表语句---------------------------
-- 知识库任务表
CREATE TABLE IF NOT EXISTS rag_knowledge_task (
-- 基础字段(完全对齐项目规范)
id BIGINT PRIMARY KEY, -- 主键ID非自增
tenant_id BIGINT NOT NULL DEFAULT 0, -- 租户ID int8
creator VARCHAR(64) NOT NULL,
created_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
updater VARCHAR(64) NOT NULL,
updated_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
deleted_at timestamp(6),
-- 业务字段
task_id BIGINT NOT NULL, -- 任务ID
task_type VARCHAR(32) NOT NULL, -- 任务类型
status VARCHAR(32) NOT NULL, -- 任务状态
executor VARCHAR(128) DEFAULT '', -- 执行器
remark TEXT DEFAULT '' -- 备注
);
-- 索引(高频查询)
CREATE INDEX idx_rkt_tenant_id ON rag_knowledge_task(tenant_id);
CREATE INDEX idx_rkt_task_id ON rag_knowledge_task(task_id);
CREATE INDEX idx_rkt_task_type ON rag_knowledge_task(task_type);
CREATE INDEX idx_rkt_status ON rag_knowledge_task(status);
CREATE INDEX idx_rkt_deleted_at ON rag_knowledge_task(deleted_at);
-- 表和字段注释
COMMENT ON TABLE rag_knowledge_task IS '知识库任务表';
COMMENT ON COLUMN rag_knowledge_task.id IS '主键ID非自增';
COMMENT ON COLUMN rag_knowledge_task.tenant_id IS '租户ID';
COMMENT ON COLUMN rag_knowledge_task.creator IS '创建人';
COMMENT ON COLUMN rag_knowledge_task.created_at IS '创建时间';
COMMENT ON COLUMN rag_knowledge_task.updater IS '更新人';
COMMENT ON COLUMN rag_knowledge_task.updated_at IS '更新时间';
COMMENT ON COLUMN rag_knowledge_task.deleted_at IS '删除时间(软删)';
COMMENT ON COLUMN rag_knowledge_task.task_id IS '任务ID';
COMMENT ON COLUMN rag_knowledge_task.task_type IS '任务类型';
COMMENT ON COLUMN rag_knowledge_task.status IS '任务状态';
COMMENT ON COLUMN rag_knowledge_task.executor IS '执行器';
COMMENT ON COLUMN rag_knowledge_task.remark IS '备注';
--------------------pgsql创建rag_knowledge_task表语句---------------------------
--------------------pgsql创建rag_vector_dataset_index表语句---------------------------