mirror of
https://gitcode.com/ageerle/ruoyi-ai.git
synced 2026-04-27 18:46:41 +00:00
Compare commits
14 Commits
v3.0.0
...
07bdc5e585
| Author | SHA1 | Date | |
|---|---|---|---|
|
07bdc5e585 | ||
|
e1b8a5f011 | ||
|
|
80ca76ea37 | ||
|
2c6ff66830 | ||
|
|
4f79a66559 | ||
|
|
22883b4334 | ||
|
|
081da6d18d | ||
|
|
74eb5b2530 | ||
|
|
b0328fe0ef | ||
|
2ee0aae57e | ||
|
|
d9c3de660a | ||
|
|
c4f7c1f5d0 | ||
|
b9097b4989 | ||
|
5d14eb20af |
@@ -31,8 +31,8 @@
|
||||
|
||||
| 模块 | 现有能力
|
||||
|:----------:|---
|
||||
| **模型管理** | 多模型接入(OpenAI/DeepSeek/通义/智谱)、多模态理解、Coze/DIFY/FastGPT平台集成
|
||||
| **知识管理** | 本地RAG + 向量库(Milvus/Weaviate/Qdrant) + 文档解析
|
||||
| **模型管理** | 多模型接入(OpenAI/DeepSeek/通义/智谱/MiniMax)、多模态理解、Coze/DIFY/FastGPT平台集成
|
||||
| **知识管理** | 本地RAG + 向量库(Milvus/Weaviate/Qdrant) + 文档解析
|
||||
| **工具管理** | Mcp协议集成、Skills能力 + 可扩展工具生态
|
||||
| **流程编排** | 可视化工作流设计器、节点拖拽编排、SSE流式执行,目前已经支持模型调用,邮件发送,人工审核等节点
|
||||
| **多智能体** | 基于Langchain4j的Agent框架、Supervisor模式编排,支持多种决策模型
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
|
||||
| Module | Current Capabilities |
|
||||
|:---:|---|
|
||||
| **Model Management** | Multi-model integration (OpenAI/DeepSeek/Tongyi/Zhipu), multi-modal understanding, Coze/DIFY/FastGPT platform integration |
|
||||
| **Model Management** | Multi-model integration (OpenAI/DeepSeek/Tongyi/Zhipu/MiniMax), multi-modal understanding, Coze/DIFY/FastGPT platform integration |
|
||||
| **Knowledge Base** | Local RAG + Vector DB (Milvus/Weaviate/Qdrant) + Document parsing |
|
||||
| **Tool Management** | MCP protocol integration, Skills capability + Extensible tool ecosystem |
|
||||
| **Workflow Orchestration** | Visual workflow designer, drag-and-drop node orchestration, SSE streaming execution, currently supports model calls, email sending, manual review nodes |
|
||||
|
||||
@@ -65,7 +65,7 @@ services:
|
||||
- "28080:8080"
|
||||
environment:
|
||||
QUERY_DEFAULTS_LIMIT: 25
|
||||
AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: true
|
||||
AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: "true"
|
||||
PERSISTENCE_DATA_PATH: /var/lib/weaviate
|
||||
DEFAULT_VECTORIZER_MODULE: none
|
||||
ENABLE_MODULES: text2vec-cohere,text2vec-huggingface,text2vec-palm,text2vec-openai,generative-openai,generative-cohere,generative-palm,ref2vec-centroid,reranker-cohere,qna-openai
|
||||
|
||||
@@ -72,8 +72,9 @@ CREATE TABLE `chat_model` (
|
||||
-- ----------------------------
|
||||
-- Records of chat_model
|
||||
-- ----------------------------
|
||||
INSERT INTO `chat_model` VALUES (2000585866022060033, 'chat', 'deepseek/deepseek-v3.2', 'ppio', 'deepseek', NULL, 'Y', 'https://api.ppinfra.com/openai', 'sk_xx', 103, 1, '2025-12-15 23:16:54', 1, '2026-03-15 19:18:48', 'DeepSeek-V3.2 是一款在高效推理、复杂推理能力与智能体场景中表现突出的领先模型。其基于 DeepSeek Sparse Attention（DSA）稀疏注意力机制，在显著降低计算开销的同时优化长上下文性能；通过可扩展强化学习框架，整体能力达到 GPT-5 同级，高算力版本 V3.2-Speciale 更在推理表现上接近 Gemini-3.0-Pro；同时，模型依托大型智能体任务合成管线，具备更强的工具调用与多步骤决策能力，并在 2025 年 IMO 与 IOI 中取得金牌级表现。作为 MaaS 平台，我们已对 DeepSeek-V3.2 完成深度适配，通过动态调度、批处理加速、低延迟推理与企业级 SLA 保障，进一步增强其在企业生产环境中的稳定性、性价比与可控性，适用于搜索、问答、智能体、代码、数据处理等多类高价值场景。', 0);
|
||||
INSERT INTO `chat_model` VALUES (2007528268536287233, 'vector', 'baai/bge-m3', 'ppio', 'bge-m3', 1024, 'N', 'https://api.ppinfra.com/openai', 'sk_xx', 103, 1, '2026-01-04 03:03:32', 1, '2026-03-15 19:18:51', 'BGE-M3 是一款具备多维度能力的文本嵌入模型，可同时实现密集检索、多向量检索和稀疏检索三大核心功能。该模型设计上兼容超过100种语言，并支持从短句到长达8192词元的长文本等多种输入形式。在跨语言检索任务中，BGE-M3展现出显著优势，其性能在MIRACL、MKQA等国际基准测试中位居前列。此外，针对长文档检索场景，该模型在MLDR、NarritiveQA等数据集上的表现同样达到行业领先水平。', 0);
|
||||
INSERT INTO `chat_model` VALUES (2000585866022060033, 'chat', 'zai-org/glm-5', 'ppio', 'zai-org/glm-5', NULL, 'Y', 'https://api.ppio.com/openai', 'sk_xx', 103, 1, '2025-12-15 23:16:54', 1, '2026-03-15 19:18:48', 'DeepSeek-V3.2 是一款在高效推理、复杂推理能力与智能体场景中表现突出的领先模型。其基于 DeepSeek Sparse Attention（DSA）稀疏注意力机制，在显著降低计算开销的同时优化长上下文性能；通过可扩展强化学习框架，整体能力达到 GPT-5 同级，高算力版本 V3.2-Speciale 更在推理表现上接近 Gemini-3.0-Pro；同时，模型依托大型智能体任务合成管线，具备更强的工具调用与多步骤决策能力，并在 2025 年 IMO 与 IOI 中取得金牌级表现。作为 MaaS 平台，我们已对 DeepSeek-V3.2 完成深度适配，通过动态调度、批处理加速、低延迟推理与企业级 SLA 保障，进一步增强其在企业生产环境中的稳定性、性价比与可控性，适用于搜索、问答、智能体、代码、数据处理等多类高价值场景。', 0);
|
||||
INSERT INTO `chat_model` VALUES (2007528268536287233, 'vector', 'baai/bge-m3', 'ppio', 'bge-m3', 1024, 'N', 'https://api.ppio.com/openai', 'sk_xx', 103, 1, '2026-01-04 03:03:32', 1, '2026-03-15 19:18:51', 'BGE-M3 是一款具备多维度能力的文本嵌入模型，可同时实现密集检索、多向量检索和稀疏检索三大核心功能。该模型设计上兼容超过100种语言，并支持从短句到长达8192词元的长文本等多种输入形式。在跨语言检索任务中，BGE-M3展现出显著优势，其性能在MIRACL、MKQA等国际基准测试中位居前列。此外，针对长文档检索场景，该模型在MLDR、NarritiveQA等数据集上的表现同样达到行业领先水平。', 0);
|
||||
INSERT INTO `chat_model` VALUES (2045735140488847361, 'chat', 'deepseek-chat', 'custom_api', 'deepseek-chat', NULL, NULL, 'https://api.deepseek.com', 'sk_xx', 103, 1, '2026-04-19 13:24:00', 1, '2026-04-19 13:24:00', 'deepseek对话模型', 0);
|
||||
|
||||
-- ----------------------------
|
||||
-- Table structure for chat_provider
|
||||
@@ -95,22 +96,26 @@ CREATE TABLE `chat_provider` (
|
||||
`update_time` datetime NULL DEFAULT NULL COMMENT '更新时间',
|
||||
`remark` varchar(500) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '备注',
|
||||
`version` int NULL DEFAULT NULL COMMENT '版本',
|
||||
`del_flag` char(1) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT '0' COMMENT '删除标志（0代表存在 1代表删除）',
|
||||
`del_flag` char(1) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT '0' COMMENT '删除标志',
|
||||
`update_ip` varchar(128) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '更新IP',
|
||||
`tenant_id` bigint NOT NULL DEFAULT 0 COMMENT '租户Id',
|
||||
PRIMARY KEY (`id`) USING BTREE,
|
||||
UNIQUE INDEX `unique_provider_code`(`provider_code` ASC, `tenant_id` ASC) USING BTREE,
|
||||
UNIQUE INDEX `unique_provider_code`(`provider_code` ASC, `tenant_id` ASC, `del_flag` ASC) USING BTREE,
|
||||
INDEX `idx_status`(`status` ASC) USING BTREE
|
||||
) ENGINE = InnoDB AUTO_INCREMENT = 2008460994477690882 CHARACTER SET = utf8mb4 COLLATE = utf8mb4_0900_ai_ci COMMENT = '厂商管理表' ROW_FORMAT = DYNAMIC;
|
||||
) ENGINE = InnoDB AUTO_INCREMENT = 2045727230803255298 CHARACTER SET = utf8mb4 COLLATE = utf8mb4_0900_ai_ci COMMENT = '厂商管理表' ROW_FORMAT = DYNAMIC;
|
||||
|
||||
-- ----------------------------
|
||||
-- Records of chat_provider
|
||||
-- ----------------------------
|
||||
INSERT INTO `chat_provider` VALUES (1, 'OpenAI', 'openai', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/01091be272334383a1efd9bc22b73ee6.png', 'OpenAI官方API服务商', 'https://api.openai.com', '0', 1, NULL, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:46:59', 'OpenAI厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (2, '阿里云百炼', 'qianwen', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/de2aa7e649de44f3ba5c6380ac6acd04.png', '阿里云百炼大模型服务', 'https://dashscope.aliyuncs.com', '0', 2, NULL, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:49:13', '阿里云厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (3, '智谱AI', 'zhipu', 'https://ruoyi-ai-1254149996.cos.ap-guangzhou.myqcloud.com/2025/12/15/a43e98fb7b3b4861b8caa6184e6fa40a.png', '智谱AI大模型服务', 'https://open.bigmodel.cn', '0', 3, NULL, '2025-12-14 21:48:11', '1', '1', '2026-02-06 00:49:14', '智谱AI厂商', NULL, '1', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (5, 'ollama', 'ollama', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/afecabebc8014d80b0f06b4796a74c5d.png', 'ollama大模型', 'http://127.0.0.1:11434', '0', 5, NULL, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:48:48', 'ollama厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (2000585060904435714, 'PPIO', 'ppio', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/049bb6a507174f73bba4b8d8b9e55b8a.png', 'api聚合厂商', 'https://api.ppinfra.com/openai', '0', 5, 103, '2025-12-15 23:13:42', '1', '1', '2026-02-25 20:49:01', 'api聚合厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (1, 'OpenAI', 'openai', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/01091be272334383a1efd9bc22b73ee6.png', 'OpenAI官方API服务商', 'https://api.openai.com', '0', 1, 103, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:46:59', 'OpenAI厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (11, '深度求索', 'deepseek', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/5ba8c30f153246898a4d7dc7b846de8d.png', 'DeepSeek官方API', 'https://api.deepseek.com', '0', 0, 103, '2026-04-19 12:52:34', '1', '1', '2026-04-19 13:13:25', 'DeepSeek官方API', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (12, '智谱AI', 'zhipu', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/da071783c9284fdd9ed1ce1b57b3c75c.png', '智谱AI大模型服务', 'https://open.bigmodel.cn', '0', 4, 103, '2025-12-14 21:48:11', '1', '1', '2026-04-19 13:14:00', '智谱AI厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (13, '小米MIMO', 'xiaomi', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/18dd39365ce244e3ae5e030da036760e.png', '小米官方API', 'https://api.xiaomimimo.com/anthropic/v1/messages', '0', 3, 103, '2026-04-19 12:48:24', '1', '1', '2026-04-19 13:14:22', '小米官方API', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (14, '阿里云百炼', 'qianwen', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/de2aa7e649de44f3ba5c6380ac6acd04.png', '阿里云百炼大模型服务', 'https://dashscope.aliyuncs.com', '0', 2, 103, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:49:13', '阿里云厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (15, 'PPIO', 'ppio', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/049bb6a507174f73bba4b8d8b9e55b8a.png', 'api聚合厂商', 'https://api.ppinfra.com/openai', '0', 5, 103, '2025-12-15 23:13:42', '1', '1', '2026-02-25 20:49:01', 'api聚合厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (16, 'MiniMax', 'minimax', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/fdc712e90e0e4d78b05862ad230884e5.png', 'MiniMax大模型服务，支持M2.7、M2.5等模型', 'https://api.minimax.io/v1', '0', 6, 103, '2026-04-19 12:50:12', '1', '1', '2026-04-19 13:14:59', 'MiniMax厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (17, 'ollama', 'ollama', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/afecabebc8014d80b0f06b4796a74c5d.png', 'ollama大模型', 'http://127.0.0.1:11434', '0', 7, 103, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:48:48', 'ollama厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (18, '自定义厂商', 'custom_api', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/c1a8e122510f4e2f90deb36958af710b.png', 'OPENAI兼容格式', '自定义', '0', 8, 103, '2026-04-19 12:35:57', '1', '1', '2026-04-19 13:17:20', 'OPENAI兼容格式', NULL, '0', NULL, 0);
|
||||
|
||||
-- ----------------------------
|
||||
-- Table structure for chat_session
|
||||
|
||||
92
docs/script/sql/update/updat-0419.sql
Normal file
92
docs/script/sql/update/updat-0419.sql
Normal file
@@ -0,0 +1,92 @@
|
||||
/*
|
||||
Navicat Premium Dump SQL
|
||||
|
||||
Source Server : localhost-mysql
|
||||
Source Server Type : MySQL
|
||||
Source Server Version : 80045 (8.0.45)
|
||||
Source Host : localhost:3306
|
||||
Source Schema : ruoyi-ai
|
||||
|
||||
Target Server Type : MySQL
|
||||
Target Server Version : 80045 (8.0.45)
|
||||
File Encoding : 65001
|
||||
|
||||
Date: 19/04/2026 13:36:41
|
||||
*/
|
||||
|
||||
SET NAMES utf8mb4;
|
||||
SET FOREIGN_KEY_CHECKS = 0;
|
||||
|
||||
-- ----------------------------
|
||||
-- Table structure for chat_model
|
||||
-- ----------------------------
|
||||
DROP TABLE IF EXISTS `chat_model`;
|
||||
CREATE TABLE `chat_model` (
|
||||
`id` bigint NOT NULL COMMENT '主键',
|
||||
`category` varchar(20) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '模型分类',
|
||||
`model_name` varchar(50) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '模型名称',
|
||||
`provider_code` varchar(20) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '模型供应商',
|
||||
`model_describe` varchar(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '模型描述',
|
||||
`model_dimension` int NULL DEFAULT NULL COMMENT '模型维度',
|
||||
`model_show` char(1) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '是否显示',
|
||||
`api_host` varchar(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '请求地址',
|
||||
`api_key` varchar(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '密钥',
|
||||
`create_dept` bigint NULL DEFAULT NULL COMMENT '创建部门',
|
||||
`create_by` bigint NULL DEFAULT NULL COMMENT '创建者',
|
||||
`create_time` datetime NULL DEFAULT NULL COMMENT '创建时间',
|
||||
`update_by` bigint NULL DEFAULT NULL COMMENT '更新者',
|
||||
`update_time` datetime NULL DEFAULT NULL COMMENT '更新时间',
|
||||
`remark` varchar(500) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '备注',
|
||||
`tenant_id` bigint NOT NULL DEFAULT 0 COMMENT '租户Id',
|
||||
PRIMARY KEY (`id`) USING BTREE
|
||||
) ENGINE = InnoDB CHARACTER SET = utf8mb4 COLLATE = utf8mb4_0900_ai_ci COMMENT = '模型管理' ROW_FORMAT = DYNAMIC;
|
||||
|
||||
-- ----------------------------
|
||||
-- Records of chat_model
|
||||
-- ----------------------------
|
||||
INSERT INTO `chat_model` VALUES (2000585866022060033, 'chat', 'zai-org/glm-5', 'ppio', 'zai-org/glm-5', NULL, 'Y', 'https://api.ppio.com/openai', 'sk_xx', 103, 1, '2025-12-15 23:16:54', 1, '2026-03-15 19:18:48', 'DeepSeek-V3.2 是一款在高效推理、复杂推理能力与智能体场景中表现突出的领先模型。其基于 DeepSeek Sparse Attention（DSA）稀疏注意力机制，在显著降低计算开销的同时优化长上下文性能；通过可扩展强化学习框架，整体能力达到 GPT-5 同级，高算力版本 V3.2-Speciale 更在推理表现上接近 Gemini-3.0-Pro；同时，模型依托大型智能体任务合成管线，具备更强的工具调用与多步骤决策能力，并在 2025 年 IMO 与 IOI 中取得金牌级表现。作为 MaaS 平台，我们已对 DeepSeek-V3.2 完成深度适配，通过动态调度、批处理加速、低延迟推理与企业级 SLA 保障，进一步增强其在企业生产环境中的稳定性、性价比与可控性，适用于搜索、问答、智能体、代码、数据处理等多类高价值场景。', 0);
|
||||
INSERT INTO `chat_model` VALUES (2007528268536287233, 'vector', 'baai/bge-m3', 'ppio', 'bge-m3', 1024, 'N', 'https://api.ppio.com/openai', 'sk_xx', 103, 1, '2026-01-04 03:03:32', 1, '2026-03-15 19:18:51', 'BGE-M3 是一款具备多维度能力的文本嵌入模型，可同时实现密集检索、多向量检索和稀疏检索三大核心功能。该模型设计上兼容超过100种语言，并支持从短句到长达8192词元的长文本等多种输入形式。在跨语言检索任务中，BGE-M3展现出显著优势，其性能在MIRACL、MKQA等国际基准测试中位居前列。此外，针对长文档检索场景，该模型在MLDR、NarritiveQA等数据集上的表现同样达到行业领先水平。', 0);
|
||||
INSERT INTO `chat_model` VALUES (2045735140488847361, 'chat', 'deepseek-chat', 'custom_api', 'deepseek-chat', NULL, NULL, 'https://api.deepseek.com', 'sk_xx', 103, 1, '2026-04-19 13:24:00', 1, '2026-04-19 13:24:00', 'deepseek对话模型', 0);
|
||||
|
||||
-- ----------------------------
|
||||
-- Table structure for chat_provider
|
||||
-- ----------------------------
|
||||
DROP TABLE IF EXISTS `chat_provider`;
|
||||
CREATE TABLE `chat_provider` (
|
||||
`id` bigint NOT NULL AUTO_INCREMENT COMMENT '主键',
|
||||
`provider_name` varchar(100) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NOT NULL COMMENT '厂商名称',
|
||||
`provider_code` varchar(50) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NOT NULL COMMENT '厂商编码',
|
||||
`provider_icon` varchar(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '厂商图标',
|
||||
`provider_desc` varchar(500) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '厂商描述',
|
||||
`api_host` varchar(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT 'API地址',
|
||||
`status` char(1) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT '0' COMMENT '状态（0正常 1停用）',
|
||||
`sort_order` int NULL DEFAULT 0 COMMENT '排序',
|
||||
`create_dept` bigint NULL DEFAULT NULL COMMENT '创建部门',
|
||||
`create_time` datetime NULL DEFAULT NULL COMMENT '创建时间',
|
||||
`create_by` varchar(64) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT '' COMMENT '创建者',
|
||||
`update_by` varchar(64) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT '' COMMENT '更新者',
|
||||
`update_time` datetime NULL DEFAULT NULL COMMENT '更新时间',
|
||||
`remark` varchar(500) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '备注',
|
||||
`version` int NULL DEFAULT NULL COMMENT '版本',
|
||||
`del_flag` char(1) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT '0' COMMENT '删除标志',
|
||||
`update_ip` varchar(128) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '更新IP',
|
||||
`tenant_id` bigint NOT NULL DEFAULT 0 COMMENT '租户Id',
|
||||
PRIMARY KEY (`id`) USING BTREE,
|
||||
UNIQUE INDEX `unique_provider_code`(`provider_code` ASC, `tenant_id` ASC, `del_flag` ASC) USING BTREE,
|
||||
INDEX `idx_status`(`status` ASC) USING BTREE
|
||||
) ENGINE = InnoDB AUTO_INCREMENT = 2045727230803255298 CHARACTER SET = utf8mb4 COLLATE = utf8mb4_0900_ai_ci COMMENT = '厂商管理表' ROW_FORMAT = DYNAMIC;
|
||||
|
||||
-- ----------------------------
|
||||
-- Records of chat_provider
|
||||
-- ----------------------------
|
||||
INSERT INTO `chat_provider` VALUES (1, 'OpenAI', 'openai', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/01091be272334383a1efd9bc22b73ee6.png', 'OpenAI官方API服务商', 'https://api.openai.com', '0', 1, 103, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:46:59', 'OpenAI厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (11, '深度求索', 'deepseek', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/5ba8c30f153246898a4d7dc7b846de8d.png', 'DeepSeek官方API', 'https://api.deepseek.com', '0', 0, 103, '2026-04-19 12:52:34', '1', '1', '2026-04-19 13:13:25', 'DeepSeek官方API', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (12, '智谱AI', 'zhipu', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/da071783c9284fdd9ed1ce1b57b3c75c.png', '智谱AI大模型服务', 'https://open.bigmodel.cn', '0', 4, 103, '2025-12-14 21:48:11', '1', '1', '2026-04-19 13:14:00', '智谱AI厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (13, '小米MIMO', 'xiaomi', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/18dd39365ce244e3ae5e030da036760e.png', '小米官方API', 'https://api.xiaomimimo.com/anthropic/v1/messages', '0', 3, 103, '2026-04-19 12:48:24', '1', '1', '2026-04-19 13:14:22', '小米官方API', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (14, '阿里云百炼', 'qianwen', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/de2aa7e649de44f3ba5c6380ac6acd04.png', '阿里云百炼大模型服务', 'https://dashscope.aliyuncs.com', '0', 2, 103, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:49:13', '阿里云厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (15, 'PPIO', 'ppio', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/049bb6a507174f73bba4b8d8b9e55b8a.png', 'api聚合厂商', 'https://api.ppinfra.com/openai', '0', 5, 103, '2025-12-15 23:13:42', '1', '1', '2026-02-25 20:49:01', 'api聚合厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (16, 'MiniMax', 'minimax', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/fdc712e90e0e4d78b05862ad230884e5.png', 'MiniMax大模型服务，支持M2.7、M2.5等模型', 'https://api.minimax.io/v1', '0', 6, 103, '2026-04-19 12:50:12', '1', '1', '2026-04-19 13:14:59', 'MiniMax厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (17, 'ollama', 'ollama', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/02/25/afecabebc8014d80b0f06b4796a74c5d.png', 'ollama大模型', 'http://127.0.0.1:11434', '0', 7, 103, '2025-12-14 21:48:11', '1', '1', '2026-02-25 20:48:48', 'ollama厂商', NULL, '0', NULL, 0);
|
||||
INSERT INTO `chat_provider` VALUES (18, '自定义厂商', 'custom_api', 'https://ruoyiai-1254149996.cos.ap-guangzhou.myqcloud.com/2026/04/19/c1a8e122510f4e2f90deb36958af710b.png', 'OPENAI兼容格式', '自定义', '0', 8, 103, '2026-04-19 12:35:57', '1', '1', '2026-04-19 13:17:20', 'OPENAI兼容格式', NULL, '0', NULL, 0);
|
||||
|
||||
SET FOREIGN_KEY_CHECKS = 1;
|
||||
46
docs/script/sql/update/updat-0420.sql
Normal file
46
docs/script/sql/update/updat-0420.sql
Normal file
@@ -0,0 +1,46 @@
|
||||
/*
|
||||
Navicat Premium Dump SQL
|
||||
|
||||
Source Server : localhost-mysql
|
||||
Source Server Type : MySQL
|
||||
Source Server Version : 80045 (8.0.45)
|
||||
Source Host : localhost:3306
|
||||
Source Schema : ruoyi-ai
|
||||
|
||||
Target Server Type : MySQL
|
||||
Target Server Version : 80045 (8.0.45)
|
||||
File Encoding : 65001
|
||||
|
||||
Date: 20/04/2026 15:30:00
|
||||
*/
|
||||
|
||||
SET NAMES utf8mb4;
|
||||
SET FOREIGN_KEY_CHECKS = 0;
|
||||
|
||||
-- ----------------------------
|
||||
-- 新增：重排序模型（chat_model）
|
||||
-- ----------------------------
|
||||
INSERT INTO `chat_model`
|
||||
(id, category, model_name, provider_code, model_describe, model_dimension, model_show, api_host, api_key, create_dept, create_by, create_time, update_by, update_time, remark, tenant_id)
|
||||
VALUES(2045071617578237953, 'rerank', 'rerank', 'zhipu', '智谱重排序', NULL, 'Y', 'https://open.bigmodel.cn', 'e9xx', 103, 1, '2026-04-17 17:27:24', 1, '2026-04-20 15:21:48', '智谱重排序', 0);
|
||||
|
||||
INSERT INTO `chat_model`
|
||||
(id, category, model_name, provider_code, model_describe, model_dimension, model_show, api_host, api_key, create_dept, create_by, create_time, update_by, update_time, remark, tenant_id)
|
||||
VALUES(2046119803482902530, 'rerank', 'qwen3-rerank', 'qianwen', '千问3重排序', NULL, NULL, 'https://dashscope.aliyuncs.com', 'sk-xx', 103, 1, '2026-04-20 14:52:31', 1, '2026-04-20 15:03:13', '千问3文本重排序', 0);
|
||||
|
||||
-- ----------------------------
|
||||
-- 新增：字典类型 - 重排序模型分类
|
||||
-- ----------------------------
|
||||
INSERT INTO `sys_dict_data`
|
||||
(dict_code, tenant_id, dict_sort, dict_label, dict_value, dict_type, css_class, list_class, is_default, create_dept, create_by, create_time, update_by, update_time, remark)
|
||||
VALUES(2045070879435259905, '000000', 4, '重排序', 'rerank', 'chat_model_category', NULL, '#000000', 'N', 103, 1, '2026-04-17 17:24:28', 1, '2026-04-19 01:02:20', '重排序模型');
|
||||
|
||||
-- ----------------------------
|
||||
-- 修改表：knowledge_info 增加重排序相关字段
|
||||
-- ----------------------------
|
||||
ALTER TABLE `knowledge_info` ADD COLUMN `enable_rerank` tinyint DEFAULT 0 NULL COMMENT '是否启用重排序（0否 1是）';
|
||||
ALTER TABLE `knowledge_info` ADD COLUMN `rerank_score_threshold` double NULL COMMENT '重排序相关性分数阈值';
|
||||
ALTER TABLE `knowledge_info` ADD COLUMN `rerank_top_n` int NULL COMMENT '重排序后返回的文档数量';
|
||||
ALTER TABLE `knowledge_info` ADD COLUMN `rerank_model` varchar(100) NULL COMMENT '重排序模型名称';
|
||||
|
||||
SET FOREIGN_KEY_CHECKS = 1;
|
||||
@@ -265,7 +265,7 @@ demo:
|
||||
# 是否开启演示模式（开启后所有写操作将被拦截）
|
||||
enabled: false
|
||||
# 提示消息
|
||||
message: "演示模式，不允许进行写操作"
|
||||
message: "演示模式，不允许操作"
|
||||
# 排除的路径（这些路径不受演示模式限制）
|
||||
excludes:
|
||||
- /login
|
||||
@@ -276,7 +276,9 @@ demo:
|
||||
- /chat/send
|
||||
- /system/session/**
|
||||
- /system/message/**
|
||||
|
||||
- /system/attach/**
|
||||
- /system/fragment/**
|
||||
- /system/info/**
|
||||
--- # warm-flow工作流配置
|
||||
warm-flow:
|
||||
# 是否开启工作流，默认true
|
||||
|
||||
@@ -174,6 +174,23 @@
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<!-- Test dependencies -->
|
||||
<dependency>
|
||||
<groupId>org.junit.jupiter</groupId>
|
||||
<artifactId>junit-jupiter</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.mockito</groupId>
|
||||
<artifactId>mockito-core</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.mockito</groupId>
|
||||
<artifactId>mockito-junit-jupiter</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
</dependencies>
|
||||
|
||||
</project>
|
||||
|
||||
@@ -9,6 +9,7 @@ import cn.dev33.satoken.annotation.SaCheckPermission;
|
||||
import org.ruoyi.common.chat.service.chat.IChatModelService;
|
||||
import org.ruoyi.common.chat.domain.bo.chat.ChatModelBo;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.enums.ChatModeType;
|
||||
import org.ruoyi.enums.ModelType;
|
||||
import org.springframework.web.bind.annotation.*;
|
||||
import org.springframework.validation.annotation.Validated;
|
||||
@@ -23,6 +24,8 @@ import org.ruoyi.common.log.enums.BusinessType;
|
||||
import org.ruoyi.common.excel.utils.ExcelUtil;
|
||||
import org.ruoyi.common.mybatis.core.page.TableDataInfo;
|
||||
|
||||
import java.util.LinkedHashMap;
|
||||
|
||||
/**
|
||||
* 模型管理
|
||||
*
|
||||
@@ -55,6 +58,21 @@ public class ChatModelController extends BaseController {
|
||||
return R.ok(chatModelService.queryList(bo));
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取模型供应商枚举
|
||||
*/
|
||||
@GetMapping("/providerOptions")
|
||||
public R<List<LinkedHashMap<String, String>>> providerOptions() {
|
||||
List<LinkedHashMap<String, String>> options = new java.util.ArrayList<>();
|
||||
for (ChatModeType type : ChatModeType.values()) {
|
||||
LinkedHashMap<String, String> item = new LinkedHashMap<>();
|
||||
item.put("label", type.getDescription());
|
||||
item.put("value", type.getCode());
|
||||
options.add(item);
|
||||
}
|
||||
return R.ok(options);
|
||||
}
|
||||
|
||||
/**
|
||||
* 导出模型管理列表
|
||||
*/
|
||||
|
||||
@@ -1,105 +0,0 @@
|
||||
package org.ruoyi.controller.knowledge;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import jakarta.servlet.http.HttpServletResponse;
|
||||
import jakarta.validation.constraints.*;
|
||||
import cn.dev33.satoken.annotation.SaCheckPermission;
|
||||
import org.ruoyi.domain.bo.knowledge.KnowledgeGraphInstanceBo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeGraphInstanceVo;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeGraphInstanceService;
|
||||
import org.springframework.web.bind.annotation.*;
|
||||
import org.springframework.validation.annotation.Validated;
|
||||
import org.ruoyi.common.idempotent.annotation.RepeatSubmit;
|
||||
import org.ruoyi.common.log.annotation.Log;
|
||||
import org.ruoyi.common.web.core.BaseController;
|
||||
import org.ruoyi.common.mybatis.core.page.PageQuery;
|
||||
import org.ruoyi.common.core.domain.R;
|
||||
import org.ruoyi.common.core.validate.AddGroup;
|
||||
import org.ruoyi.common.core.validate.EditGroup;
|
||||
import org.ruoyi.common.log.enums.BusinessType;
|
||||
import org.ruoyi.common.excel.utils.ExcelUtil;
|
||||
import org.ruoyi.common.mybatis.core.page.TableDataInfo;
|
||||
|
||||
/**
|
||||
* 知识图谱实例
|
||||
*
|
||||
* @author ageerle
|
||||
* @date 2025-12-17
|
||||
*/
|
||||
@Validated
|
||||
@RequiredArgsConstructor
|
||||
@RestController
|
||||
@RequestMapping("/system/graphInstance")
|
||||
public class KnowledgeGraphInstanceController extends BaseController {
|
||||
|
||||
private final IKnowledgeGraphInstanceService knowledgeGraphInstanceService;
|
||||
|
||||
/**
|
||||
* 查询知识图谱实例列表
|
||||
*/
|
||||
@SaCheckPermission("system:graphInstance:list")
|
||||
@GetMapping("/list")
|
||||
public TableDataInfo<KnowledgeGraphInstanceVo> list(KnowledgeGraphInstanceBo bo, PageQuery pageQuery) {
|
||||
return knowledgeGraphInstanceService.queryPageList(bo, pageQuery);
|
||||
}
|
||||
|
||||
/**
|
||||
* 导出知识图谱实例列表
|
||||
*/
|
||||
@SaCheckPermission("system:graphInstance:export")
|
||||
@Log(title = "知识图谱实例", businessType = BusinessType.EXPORT)
|
||||
@PostMapping("/export")
|
||||
public void export(KnowledgeGraphInstanceBo bo, HttpServletResponse response) {
|
||||
List<KnowledgeGraphInstanceVo> list = knowledgeGraphInstanceService.queryList(bo);
|
||||
ExcelUtil.exportExcel(list, "知识图谱实例", KnowledgeGraphInstanceVo.class, response);
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取知识图谱实例详细信息
|
||||
*
|
||||
* @param id 主键
|
||||
*/
|
||||
@SaCheckPermission("system:graphInstance:query")
|
||||
@GetMapping("/{id}")
|
||||
public R<KnowledgeGraphInstanceVo> getInfo(@NotNull(message = "主键不能为空")
|
||||
@PathVariable Long id) {
|
||||
return R.ok(knowledgeGraphInstanceService.queryById(id));
|
||||
}
|
||||
|
||||
/**
|
||||
* 新增知识图谱实例
|
||||
*/
|
||||
@SaCheckPermission("system:graphInstance:add")
|
||||
@Log(title = "知识图谱实例", businessType = BusinessType.INSERT)
|
||||
@RepeatSubmit()
|
||||
@PostMapping()
|
||||
public R<Void> add(@Validated(AddGroup.class) @RequestBody KnowledgeGraphInstanceBo bo) {
|
||||
return toAjax(knowledgeGraphInstanceService.insertByBo(bo));
|
||||
}
|
||||
|
||||
/**
|
||||
* 修改知识图谱实例
|
||||
*/
|
||||
@SaCheckPermission("system:graphInstance:edit")
|
||||
@Log(title = "知识图谱实例", businessType = BusinessType.UPDATE)
|
||||
@RepeatSubmit()
|
||||
@PutMapping()
|
||||
public R<Void> edit(@Validated(EditGroup.class) @RequestBody KnowledgeGraphInstanceBo bo) {
|
||||
return toAjax(knowledgeGraphInstanceService.updateByBo(bo));
|
||||
}
|
||||
|
||||
/**
|
||||
* 删除知识图谱实例
|
||||
*
|
||||
* @param ids 主键串
|
||||
*/
|
||||
@SaCheckPermission("system:graphInstance:remove")
|
||||
@Log(title = "知识图谱实例", businessType = BusinessType.DELETE)
|
||||
@DeleteMapping("/{ids}")
|
||||
public R<Void> remove(@NotEmpty(message = "主键不能为空")
|
||||
@PathVariable Long[] ids) {
|
||||
return toAjax(knowledgeGraphInstanceService.deleteWithValidByIds(List.of(ids), true));
|
||||
}
|
||||
}
|
||||
@@ -1,105 +0,0 @@
|
||||
package org.ruoyi.controller.knowledge;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import jakarta.servlet.http.HttpServletResponse;
|
||||
import jakarta.validation.constraints.*;
|
||||
import cn.dev33.satoken.annotation.SaCheckPermission;
|
||||
import org.ruoyi.domain.bo.knowledge.KnowledgeGraphSegmentBo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeGraphSegmentVo;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeGraphSegmentService;
|
||||
import org.springframework.web.bind.annotation.*;
|
||||
import org.springframework.validation.annotation.Validated;
|
||||
import org.ruoyi.common.idempotent.annotation.RepeatSubmit;
|
||||
import org.ruoyi.common.log.annotation.Log;
|
||||
import org.ruoyi.common.web.core.BaseController;
|
||||
import org.ruoyi.common.mybatis.core.page.PageQuery;
|
||||
import org.ruoyi.common.core.domain.R;
|
||||
import org.ruoyi.common.core.validate.AddGroup;
|
||||
import org.ruoyi.common.core.validate.EditGroup;
|
||||
import org.ruoyi.common.log.enums.BusinessType;
|
||||
import org.ruoyi.common.excel.utils.ExcelUtil;
|
||||
import org.ruoyi.common.mybatis.core.page.TableDataInfo;
|
||||
|
||||
/**
|
||||
* 知识图谱片段
|
||||
*
|
||||
* @author ageerle
|
||||
* @date 2025-12-17
|
||||
*/
|
||||
@Validated
|
||||
@RequiredArgsConstructor
|
||||
@RestController
|
||||
@RequestMapping("/system/graphSegment")
|
||||
public class KnowledgeGraphSegmentController extends BaseController {
|
||||
|
||||
private final IKnowledgeGraphSegmentService knowledgeGraphSegmentService;
|
||||
|
||||
/**
|
||||
* 查询知识图谱片段列表
|
||||
*/
|
||||
@SaCheckPermission("system:graphSegment:list")
|
||||
@GetMapping("/list")
|
||||
public TableDataInfo<KnowledgeGraphSegmentVo> list(KnowledgeGraphSegmentBo bo, PageQuery pageQuery) {
|
||||
return knowledgeGraphSegmentService.queryPageList(bo, pageQuery);
|
||||
}
|
||||
|
||||
/**
|
||||
* 导出知识图谱片段列表
|
||||
*/
|
||||
@SaCheckPermission("system:graphSegment:export")
|
||||
@Log(title = "知识图谱片段", businessType = BusinessType.EXPORT)
|
||||
@PostMapping("/export")
|
||||
public void export(KnowledgeGraphSegmentBo bo, HttpServletResponse response) {
|
||||
List<KnowledgeGraphSegmentVo> list = knowledgeGraphSegmentService.queryList(bo);
|
||||
ExcelUtil.exportExcel(list, "知识图谱片段", KnowledgeGraphSegmentVo.class, response);
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取知识图谱片段详细信息
|
||||
*
|
||||
* @param id 主键
|
||||
*/
|
||||
@SaCheckPermission("system:graphSegment:query")
|
||||
@GetMapping("/{id}")
|
||||
public R<KnowledgeGraphSegmentVo> getInfo(@NotNull(message = "主键不能为空")
|
||||
@PathVariable Long id) {
|
||||
return R.ok(knowledgeGraphSegmentService.queryById(id));
|
||||
}
|
||||
|
||||
/**
|
||||
* 新增知识图谱片段
|
||||
*/
|
||||
@SaCheckPermission("system:graphSegment:add")
|
||||
@Log(title = "知识图谱片段", businessType = BusinessType.INSERT)
|
||||
@RepeatSubmit()
|
||||
@PostMapping()
|
||||
public R<Void> add(@Validated(AddGroup.class) @RequestBody KnowledgeGraphSegmentBo bo) {
|
||||
return toAjax(knowledgeGraphSegmentService.insertByBo(bo));
|
||||
}
|
||||
|
||||
/**
|
||||
* 修改知识图谱片段
|
||||
*/
|
||||
@SaCheckPermission("system:graphSegment:edit")
|
||||
@Log(title = "知识图谱片段", businessType = BusinessType.UPDATE)
|
||||
@RepeatSubmit()
|
||||
@PutMapping()
|
||||
public R<Void> edit(@Validated(EditGroup.class) @RequestBody KnowledgeGraphSegmentBo bo) {
|
||||
return toAjax(knowledgeGraphSegmentService.updateByBo(bo));
|
||||
}
|
||||
|
||||
/**
|
||||
* 删除知识图谱片段
|
||||
*
|
||||
* @param ids 主键串
|
||||
*/
|
||||
@SaCheckPermission("system:graphSegment:remove")
|
||||
@Log(title = "知识图谱片段", businessType = BusinessType.DELETE)
|
||||
@DeleteMapping("/{ids}")
|
||||
public R<Void> remove(@NotEmpty(message = "主键不能为空")
|
||||
@PathVariable Long[] ids) {
|
||||
return toAjax(knowledgeGraphSegmentService.deleteWithValidByIds(List.of(ids), true));
|
||||
}
|
||||
}
|
||||
@@ -77,10 +77,33 @@ public class KnowledgeInfoBo extends BaseEntity {
|
||||
*/
|
||||
private String embeddingModel;
|
||||
|
||||
/**
|
||||
* 是否启用重排序（0 否 1是）
|
||||
*/
|
||||
private Integer enableRerank;
|
||||
|
||||
/**
|
||||
* 重排序模型名称
|
||||
*/
|
||||
private String rerankModel;
|
||||
|
||||
/**
|
||||
* 重排序后返回的文档数量
|
||||
*/
|
||||
private Integer rerankTopN;
|
||||
|
||||
/**
|
||||
* 重排序相关性分数阈值
|
||||
*/
|
||||
private Double rerankScoreThreshold;
|
||||
|
||||
|
||||
/**
|
||||
* 备注
|
||||
*/
|
||||
private String remark;
|
||||
|
||||
|
||||
|
||||
|
||||
}
|
||||
|
||||
@@ -0,0 +1,44 @@
|
||||
package org.ruoyi.domain.bo.rerank;
|
||||
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.Builder;
|
||||
import lombok.Data;
|
||||
import lombok.NoArgsConstructor;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 重排序请求参数
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
@Data
|
||||
@Builder
|
||||
@NoArgsConstructor
|
||||
@AllArgsConstructor
|
||||
public class RerankRequest {
|
||||
|
||||
/**
|
||||
* 查询文本
|
||||
*/
|
||||
private String query;
|
||||
|
||||
/**
|
||||
* 候选文档列表
|
||||
*/
|
||||
private List<String> documents;
|
||||
|
||||
/**
|
||||
* 返回的文档数量（topN）
|
||||
* 如果不指定，默认返回所有文档
|
||||
*/
|
||||
private Integer topN;
|
||||
|
||||
/**
|
||||
* 是否返回原始文档内容
|
||||
* 默认为 true
|
||||
*/
|
||||
@Builder.Default
|
||||
private Boolean returnDocuments = true;
|
||||
}
|
||||
@@ -0,0 +1,72 @@
|
||||
package org.ruoyi.domain.bo.rerank;
|
||||
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.Builder;
|
||||
import lombok.Data;
|
||||
import lombok.NoArgsConstructor;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 重排序结果
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
@Data
|
||||
@Builder
|
||||
@NoArgsConstructor
|
||||
@AllArgsConstructor
|
||||
public class RerankResult {
|
||||
|
||||
/**
|
||||
* 重排序后的文档结果列表
|
||||
*/
|
||||
private List<RerankDocument> documents;
|
||||
|
||||
/**
|
||||
* 原始请求中的文档总数
|
||||
*/
|
||||
private Integer totalDocuments;
|
||||
|
||||
/**
|
||||
* 重排序耗时（毫秒）
|
||||
*/
|
||||
private Long durationMs;
|
||||
|
||||
/**
|
||||
* 单个重排序文档结果
|
||||
*/
|
||||
@Data
|
||||
@Builder
|
||||
@NoArgsConstructor
|
||||
@AllArgsConstructor
|
||||
public static class RerankDocument {
|
||||
|
||||
/**
|
||||
* 文档在原始列表中的索引位置
|
||||
*/
|
||||
private Integer index;
|
||||
|
||||
/**
|
||||
* 相关性分数（通常 0-1 之间，越高越相关）
|
||||
*/
|
||||
private Double relevanceScore;
|
||||
|
||||
/**
|
||||
* 文档内容
|
||||
*/
|
||||
private String document;
|
||||
}
|
||||
|
||||
/**
|
||||
* 创建空结果
|
||||
*/
|
||||
public static RerankResult empty() {
|
||||
return RerankResult.builder()
|
||||
.documents(List.of())
|
||||
.totalDocuments(0)
|
||||
.durationMs(0L)
|
||||
.build();
|
||||
}
|
||||
}
|
||||
@@ -51,4 +51,30 @@ public class QueryVectorBo {
|
||||
*/
|
||||
private String baseUrl;
|
||||
|
||||
|
||||
// ========== 重排序相关参数 ==========
|
||||
|
||||
/**
|
||||
* 是否启用重排序
|
||||
* 默认为 false
|
||||
*/
|
||||
private Boolean enableRerank = false;
|
||||
|
||||
/**
|
||||
* 重排序模型名称
|
||||
*/
|
||||
private String rerankModelName;
|
||||
|
||||
/**
|
||||
* 重排序后返回的文档数量（topN）
|
||||
* 如果不指定，默认与 maxResults 相同
|
||||
*/
|
||||
private Integer rerankTopN;
|
||||
|
||||
/**
|
||||
* 重排序相关性分数阈值
|
||||
* 低于此阈值的文档将被过滤
|
||||
*/
|
||||
private Double rerankScoreThreshold;
|
||||
|
||||
}
|
||||
|
||||
@@ -0,0 +1,55 @@
|
||||
package org.ruoyi.domain.dto.request;
|
||||
|
||||
import com.fasterxml.jackson.annotation.JsonInclude;
|
||||
import com.fasterxml.jackson.annotation.JsonProperty;
|
||||
import com.fasterxml.jackson.core.JsonProcessingException;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 阿里百炼重排序请求DTO（OpenAI兼容格式）
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-20
|
||||
*/
|
||||
@JsonInclude(JsonInclude.Include.NON_NULL)
|
||||
public record AliBaiLianRerankRequest(
|
||||
String model,
|
||||
List<String> documents,
|
||||
String query,
|
||||
@JsonProperty("top_n")
|
||||
Integer topN,
|
||||
String instruct,
|
||||
@JsonProperty("return_documents")
|
||||
Boolean returnDocuments
|
||||
) {
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
/**
|
||||
* 创建文本重排序请求
|
||||
*/
|
||||
public static AliBaiLianRerankRequest create(String modelName, String query,
|
||||
List<String> documents, Integer topN,
|
||||
Boolean returnDocuments) {
|
||||
return new AliBaiLianRerankRequest(
|
||||
modelName,
|
||||
documents,
|
||||
query,
|
||||
topN != null ? topN : documents.size(),
|
||||
null,
|
||||
returnDocuments != null ? returnDocuments : true
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* 转换为JSON字符串
|
||||
*/
|
||||
public String toJson() {
|
||||
try {
|
||||
return OBJECT_MAPPER.writeValueAsString(this);
|
||||
} catch (JsonProcessingException e) {
|
||||
throw new IllegalArgumentException("序列化阿里百炼重排序请求失败", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,48 @@
|
||||
package org.ruoyi.domain.dto.request;
|
||||
|
||||
import com.fasterxml.jackson.core.JsonProcessingException;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 智谱AI重排序请求DTO
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
public record ZhipuRerankRequest(
|
||||
String model,
|
||||
String query,
|
||||
List<String> documents,
|
||||
Integer top_n,
|
||||
Boolean return_documents
|
||||
) {
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
/**
|
||||
* 创建智谱重排序请求
|
||||
*/
|
||||
public static ZhipuRerankRequest create(String modelName, String query,
|
||||
List<String> documents, Integer topN,
|
||||
Boolean returnDocuments) {
|
||||
return new ZhipuRerankRequest(
|
||||
modelName,
|
||||
query,
|
||||
documents,
|
||||
topN != null ? topN : documents.size(),
|
||||
returnDocuments != null ? returnDocuments : true
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* 转换为JSON字符串
|
||||
*/
|
||||
public String toJson() {
|
||||
try {
|
||||
return OBJECT_MAPPER.writeValueAsString(this);
|
||||
} catch (JsonProcessingException e) {
|
||||
throw new IllegalArgumentException("序列化智谱重排序请求失败", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,81 @@
|
||||
package org.ruoyi.domain.dto.response;
|
||||
|
||||
import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
|
||||
import com.fasterxml.jackson.annotation.JsonProperty;
|
||||
import org.ruoyi.domain.bo.rerank.RerankResult;
|
||||
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
/**
|
||||
* 阿里百炼重排序响应DTO（OpenAI兼容格式）
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-20
|
||||
*/
|
||||
@JsonIgnoreProperties(ignoreUnknown = true)
|
||||
public record AliBaiLianRerankResponse(
|
||||
String id,
|
||||
String object,
|
||||
List<ResultItem> results,
|
||||
UsageInfo usage
|
||||
) {
|
||||
/**
|
||||
* 单个重排序结果项
|
||||
*/
|
||||
@JsonIgnoreProperties(ignoreUnknown = true)
|
||||
public record ResultItem(
|
||||
Integer index,
|
||||
@JsonProperty("relevance_score")
|
||||
Double relevanceScore,
|
||||
Object document
|
||||
) {
|
||||
/**
|
||||
* 获取文档文本内容
|
||||
*/
|
||||
public String getDocumentText() {
|
||||
if (document == null) return null;
|
||||
if (document instanceof String) return (String) document;
|
||||
if (document instanceof Map) {
|
||||
Object text = ((Map<?, ?>) document).get("text");
|
||||
return text != null ? text.toString() : null;
|
||||
}
|
||||
return document.toString();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Token使用信息
|
||||
*/
|
||||
@JsonIgnoreProperties(ignoreUnknown = true)
|
||||
public record UsageInfo(
|
||||
@JsonProperty("total_tokens")
|
||||
Integer totalTokens,
|
||||
@JsonProperty("prompt_tokens")
|
||||
Integer promptTokens
|
||||
) {}
|
||||
|
||||
/**
|
||||
* 转换为通用RerankResult
|
||||
*/
|
||||
public RerankResult toRerankResult(int totalDocs, long durationMs) {
|
||||
if (results == null || results.isEmpty()) {
|
||||
return RerankResult.empty();
|
||||
}
|
||||
|
||||
List<RerankResult.RerankDocument> documents = results.stream()
|
||||
.map(item -> RerankResult.RerankDocument.builder()
|
||||
.index(item.index())
|
||||
.relevanceScore(item.relevanceScore())
|
||||
.document(item.getDocumentText())
|
||||
.build())
|
||||
.collect(Collectors.toList());
|
||||
|
||||
return RerankResult.builder()
|
||||
.documents(documents)
|
||||
.totalDocuments(totalDocs)
|
||||
.durationMs(durationMs)
|
||||
.build();
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,68 @@
|
||||
package org.ruoyi.domain.dto.response;
|
||||
|
||||
import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
|
||||
import com.fasterxml.jackson.annotation.JsonProperty;
|
||||
import org.ruoyi.domain.bo.rerank.RerankResult;
|
||||
|
||||
import java.util.List;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
/**
|
||||
* 智谱AI重排序响应DTO
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
@JsonIgnoreProperties(ignoreUnknown = true)
|
||||
public record ZhipuRerankResponse(
|
||||
String model,
|
||||
String object,
|
||||
List<ResultItem> results,
|
||||
UsageInfo usage
|
||||
) {
|
||||
/**
|
||||
* 单个重排序结果项
|
||||
*/
|
||||
public record ResultItem(
|
||||
Integer index,
|
||||
@JsonProperty("relevance_score")
|
||||
Double relevanceScore,
|
||||
String document
|
||||
) {}
|
||||
|
||||
/**
|
||||
* Token使用信息
|
||||
*/
|
||||
@JsonIgnoreProperties(ignoreUnknown = true)
|
||||
public record UsageInfo(
|
||||
@JsonProperty("total_tokens")
|
||||
Integer totalTokens,
|
||||
@JsonProperty("input_tokens")
|
||||
Integer inputTokens,
|
||||
@JsonProperty("output_tokens")
|
||||
Integer outputTokens
|
||||
) {}
|
||||
|
||||
/**
|
||||
* 转换为通用RerankResult
|
||||
*/
|
||||
public RerankResult toRerankResult(int totalDocs, long durationMs) {
|
||||
if (results == null || results.isEmpty()) {
|
||||
return RerankResult.empty();
|
||||
}
|
||||
|
||||
List<RerankResult.RerankDocument> documents = results.stream()
|
||||
.map(item -> RerankResult.RerankDocument.builder()
|
||||
.index(item.index())
|
||||
.relevanceScore(item.relevanceScore())
|
||||
.document(item.document())
|
||||
.build())
|
||||
.collect(Collectors.toList());
|
||||
|
||||
return RerankResult.builder()
|
||||
.documents(documents)
|
||||
.totalDocuments(totalDocs)
|
||||
.durationMs(durationMs)
|
||||
.build();
|
||||
}
|
||||
}
|
||||
@@ -78,6 +78,26 @@ public class KnowledgeInfo extends BaseEntity {
|
||||
*/
|
||||
private String embeddingModel;
|
||||
|
||||
/**
|
||||
* 是否启用重排序（0 否 1是）
|
||||
*/
|
||||
private Integer enableRerank;
|
||||
|
||||
/**
|
||||
* 重排序模型名称
|
||||
*/
|
||||
private String rerankModel;
|
||||
|
||||
/**
|
||||
* 重排序后返回的文档数量
|
||||
*/
|
||||
private Integer rerankTopN;
|
||||
|
||||
/**
|
||||
* 重排序相关性分数阈值
|
||||
*/
|
||||
private Double rerankScoreThreshold;
|
||||
|
||||
/**
|
||||
* 备注
|
||||
*/
|
||||
|
||||
@@ -94,6 +94,30 @@ public class KnowledgeInfoVo implements Serializable {
|
||||
@ExcelProperty(value = "向量模型")
|
||||
private String embeddingModel;
|
||||
|
||||
/**
|
||||
* 是否启用重排序（0 否 1是）
|
||||
*/
|
||||
@ExcelProperty(value = "是否启用重排序")
|
||||
private Integer enableRerank;
|
||||
|
||||
/**
|
||||
* 重排序模型名称
|
||||
*/
|
||||
@ExcelProperty(value = "重排序模型")
|
||||
private String rerankModel;
|
||||
|
||||
/**
|
||||
* 重排序后返回的文档数量
|
||||
*/
|
||||
@ExcelProperty(value = "重排序返回数量")
|
||||
private Integer rerankTopN;
|
||||
|
||||
/**
|
||||
* 重排序相关性分数阈值
|
||||
*/
|
||||
@ExcelProperty(value = "重排序分数阈值")
|
||||
private Double rerankScoreThreshold;
|
||||
|
||||
/**
|
||||
* 备注
|
||||
*/
|
||||
|
||||
@@ -15,7 +15,10 @@ public enum ChatModeType {
|
||||
DEEP_SEEK("deepseek", "深度求索"),
|
||||
QIAN_WEN("qianwen", "通义千问"),
|
||||
OPEN_AI("openai", "openai"),
|
||||
PPIO("ppio", "ppio");
|
||||
PPIO("ppio", "ppio"),
|
||||
CUSTOM_API("custom_api", "自定义API"),
|
||||
MINIMAX("minimax", "MiniMax"),
|
||||
XIAOMI("xiaomi", "小米MiMo");
|
||||
private final String code;
|
||||
private final String description;
|
||||
|
||||
|
||||
@@ -0,0 +1,106 @@
|
||||
package org.ruoyi.factory;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.common.chat.service.chat.IChatModelService;
|
||||
import org.ruoyi.service.rerank.RerankModelService;
|
||||
import org.springframework.beans.factory.NoSuchBeanDefinitionException;
|
||||
import org.springframework.context.ApplicationContext;
|
||||
import org.springframework.stereotype.Service;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
import java.util.concurrent.ConcurrentHashMap;
|
||||
|
||||
/**
|
||||
* 重排序模型工厂服务类
|
||||
* 参考设计模式：EmbeddingModelFactory
|
||||
* 负责创建和管理重排序模型实例
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
@Service
|
||||
@RequiredArgsConstructor
|
||||
@Slf4j
|
||||
public class RerankModelFactory {
|
||||
|
||||
private final ApplicationContext applicationContext;
|
||||
|
||||
private final IChatModelService chatModelService;
|
||||
|
||||
/**
|
||||
* 模型缓存，使用ConcurrentHashMap保证线程安全
|
||||
*/
|
||||
private final Map<String, RerankModelService> modelCache = new ConcurrentHashMap<>();
|
||||
|
||||
/**
|
||||
* 创建重排序模型实例
|
||||
* 如果模型已存在于缓存中，则直接返回；否则创建新的实例
|
||||
*
|
||||
* @param rerankModelName 重排序模型名称
|
||||
*/
|
||||
public RerankModelService createModel(String rerankModelName) {
|
||||
return modelCache.computeIfAbsent(rerankModelName, name -> {
|
||||
ChatModelVo modelConfig = chatModelService.selectModelByName(rerankModelName);
|
||||
|
||||
if (modelConfig == null) {
|
||||
throw new IllegalArgumentException("未找到重排序模型配置，name=" + name);
|
||||
}
|
||||
return createModelInstance(modelConfig.getProviderCode(), modelConfig);
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* 刷新模型缓存
|
||||
* 根据给定的模型ID从缓存中移除对应的模型
|
||||
*
|
||||
* @param modelId 模型的唯一标识ID
|
||||
*/
|
||||
public void refreshModel(Long modelId) {
|
||||
modelCache.remove(modelId);
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取所有支持模型工厂的列表
|
||||
*
|
||||
* @return 支持的模型工厂名称列表
|
||||
*/
|
||||
public List<String> getSupportedFactories() {
|
||||
return new ArrayList<>(applicationContext.getBeansOfType(RerankModelService.class)
|
||||
.keySet());
|
||||
}
|
||||
|
||||
/**
|
||||
* 创建具体的模型实例
|
||||
* 根据提供的工厂名称和配置信息创建并配置模型实例
|
||||
*
|
||||
* @param factory 工厂名称，用于标识模型类型（providerCode）
|
||||
* @param config 模型配置信息
|
||||
* @return RerankModelService 配置好的模型实例
|
||||
* @throws IllegalArgumentException 当无法获取指定的模型实例时抛出
|
||||
*/
|
||||
private RerankModelService createModelInstance(String factory, ChatModelVo config) {
|
||||
try {
|
||||
// 优先尝试使用 providerCode + "Rerank" 作为 Bean 名称
|
||||
// 例如：zhipu -> zhipuRerank，jina -> jinaRerank
|
||||
String rerankBeanName = factory + "Rerank";
|
||||
RerankModelService model = applicationContext.getBean(rerankBeanName, RerankModelService.class);
|
||||
model.configure(config);
|
||||
log.info("成功创建重排序模型: factory={}, modelName={}", rerankBeanName, config.getModelName());
|
||||
return model;
|
||||
} catch (NoSuchBeanDefinitionException e) {
|
||||
// 如果找不到，尝试使用原始的 providerCode
|
||||
try {
|
||||
RerankModelService model = applicationContext.getBean(factory, RerankModelService.class);
|
||||
model.configure(config);
|
||||
log.info("成功创建重排序模型: factory={}, modelName={}", factory, config.getModelName());
|
||||
return model;
|
||||
} catch (NoSuchBeanDefinitionException ex) {
|
||||
throw new IllegalArgumentException("获取不到重排序模型: " + factory + " 或 " + factory + "Rerank", ex);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,9 +1,13 @@
|
||||
package org.ruoyi.service.chat;
|
||||
|
||||
import dev.langchain4j.model.chat.ChatModel;
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import dev.langchain4j.model.openai.OpenAiChatModel;
|
||||
import org.ruoyi.common.chat.domain.dto.request.ChatRequest;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
|
||||
import java.time.Duration;
|
||||
|
||||
/**
|
||||
* 聊天消息Service接口
|
||||
*
|
||||
@@ -21,6 +25,23 @@ public interface AbstractChatService {
|
||||
*/
|
||||
StreamingChatModel buildStreamingChatModel(ChatModelVo chatModelVo, ChatRequest chatRequest);
|
||||
|
||||
/**
|
||||
* 创建同步聊天模型（供 Agent/SupervisorAgent 使用）
|
||||
* 默认实现使用 OpenAI 兼容协议，适用于 OpenAI、DeepSeek、PPIO 等兼容接口的 provider。
|
||||
* ZhiPu、QianWen、Ollama 等需覆盖此方法使用各自 SDK。
|
||||
*
|
||||
* @param chatModelVo 模型配置
|
||||
* @return 同步聊天模型实例
|
||||
*/
|
||||
default ChatModel buildChatModel(ChatModelVo chatModelVo) {
|
||||
return OpenAiChatModel.builder()
|
||||
.baseUrl(chatModelVo.getApiHost())
|
||||
.apiKey(chatModelVo.getApiKey())
|
||||
.modelName(chatModelVo.getModelName())
|
||||
.timeout(Duration.ofSeconds(120))
|
||||
.build();
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取服务提供商名称
|
||||
*/
|
||||
|
||||
@@ -54,6 +54,7 @@ import org.ruoyi.service.chat.AbstractChatService;
|
||||
import org.ruoyi.service.chat.IChatMessageService;
|
||||
import org.ruoyi.service.chat.impl.memory.PersistentChatMemoryStore;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeInfoService;
|
||||
import org.ruoyi.service.retrieval.KnowledgeRetrievalService;
|
||||
import org.ruoyi.service.vector.VectorStoreService;
|
||||
import org.springframework.stereotype.Service;
|
||||
import org.springframework.web.servlet.mvc.method.annotation.SseEmitter;
|
||||
@@ -89,6 +90,8 @@ public class ChatServiceFacade implements IChatService {
|
||||
|
||||
private final VectorStoreService vectorStoreService;
|
||||
|
||||
private final KnowledgeRetrievalService knowledgeRetrievalService;
|
||||
|
||||
private final SseEmitterManager sseEmitterManager;
|
||||
|
||||
private final IChatMessageService chatMessageService;
|
||||
@@ -452,8 +455,8 @@ public class ChatServiceFacade implements IChatService {
|
||||
// 构建向量查询参数
|
||||
QueryVectorBo queryVectorBo = buildQueryVectorBo(chatRequest, knowledgeInfoVo, chatModel);
|
||||
|
||||
// 获取向量查询结果（知识库内容作为系统上下文，放在历史消息之后）
|
||||
List<String> nearestList = vectorStoreService.getQueryVector(queryVectorBo);
|
||||
// 使用知识库检索服务（支持重排序）
|
||||
List<String> nearestList = knowledgeRetrievalService.retrieveTexts(queryVectorBo);
|
||||
for (String prompt : nearestList) {
|
||||
// 知识库内容作为系统上下文添加
|
||||
messages.add(new AiMessage(prompt));
|
||||
@@ -480,6 +483,13 @@ public class ChatServiceFacade implements IChatService {
|
||||
queryVectorBo.setVectorModelName(knowledgeInfoVo.getVectorModel());
|
||||
queryVectorBo.setEmbeddingModelName(knowledgeInfoVo.getEmbeddingModel());
|
||||
queryVectorBo.setMaxResults(knowledgeInfoVo.getRetrieveLimit());
|
||||
|
||||
// 设置重排序参数
|
||||
queryVectorBo.setEnableRerank(knowledgeInfoVo.getEnableRerank() != null && knowledgeInfoVo.getEnableRerank() == 1);
|
||||
queryVectorBo.setRerankModelName(knowledgeInfoVo.getRerankModel());
|
||||
queryVectorBo.setRerankTopN(knowledgeInfoVo.getRerankTopN());
|
||||
queryVectorBo.setRerankScoreThreshold(knowledgeInfoVo.getRerankScoreThreshold());
|
||||
|
||||
return queryVectorBo;
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,72 @@
|
||||
package org.ruoyi.service.chat.impl.provider;
|
||||
|
||||
import cn.hutool.core.util.StrUtil;
|
||||
import dev.langchain4j.model.chat.ChatModel;
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import dev.langchain4j.model.openai.OpenAiChatModel;
|
||||
import dev.langchain4j.model.openai.OpenAiStreamingChatModel;
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.common.chat.domain.dto.request.ChatRequest;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.enums.ChatModeType;
|
||||
import org.ruoyi.observability.MyChatModelListener;
|
||||
import org.ruoyi.service.chat.AbstractChatService;
|
||||
import org.springframework.stereotype.Service;
|
||||
|
||||
import java.time.Duration;
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 自定义 API 服务调用
|
||||
*
|
||||
* 适用于 OpenAI 兼容接口或仅通过通用 HTTP 协议接入的第三方大模型服务。
|
||||
* 通过模型配置中的 apiHost / apiKey / modelName 即可复用，不需要再写死具体供应商。
|
||||
*
|
||||
* @author better
|
||||
*/
|
||||
@Service
|
||||
@Slf4j
|
||||
@RequiredArgsConstructor
|
||||
public class CustomApiServiceImpl implements AbstractChatService {
|
||||
|
||||
private static final Duration DEFAULT_TIMEOUT = Duration.ofSeconds(180);
|
||||
|
||||
@Override
|
||||
public StreamingChatModel buildStreamingChatModel(ChatModelVo chatModelVo, ChatRequest chatRequest) {
|
||||
return OpenAiStreamingChatModel.builder()
|
||||
.baseUrl(normalizeBaseUrl(chatModelVo.getApiHost()))
|
||||
.apiKey(defaultIfBlank(chatModelVo.getApiKey(), "EMPTY"))
|
||||
.modelName(chatModelVo.getModelName())
|
||||
.timeout(DEFAULT_TIMEOUT)
|
||||
.listeners(List.of(new MyChatModelListener()))
|
||||
.returnThinking(chatRequest.getEnableThinking())
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public ChatModel buildChatModel(ChatModelVo chatModelVo) {
|
||||
return OpenAiChatModel.builder()
|
||||
.baseUrl(normalizeBaseUrl(chatModelVo.getApiHost()))
|
||||
.apiKey(defaultIfBlank(chatModelVo.getApiKey(), "EMPTY"))
|
||||
.modelName(chatModelVo.getModelName())
|
||||
.timeout(DEFAULT_TIMEOUT)
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getProviderName() {
|
||||
return ChatModeType.CUSTOM_API.getCode();
|
||||
}
|
||||
|
||||
private String normalizeBaseUrl(String baseUrl) {
|
||||
if (StrUtil.isBlank(baseUrl)) {
|
||||
throw new IllegalArgumentException("自定义API的请求地址(apiHost)不能为空");
|
||||
}
|
||||
return baseUrl.endsWith("/") ? baseUrl.substring(0, baseUrl.length() - 1) : baseUrl;
|
||||
}
|
||||
|
||||
private String defaultIfBlank(String value, String defaultValue) {
|
||||
return StrUtil.isBlank(value) ? defaultValue : value;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,47 @@
|
||||
package org.ruoyi.service.chat.impl.provider;
|
||||
|
||||
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import dev.langchain4j.model.openai.OpenAiStreamingChatModel;
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.common.chat.domain.dto.request.ChatRequest;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.enums.ChatModeType;
|
||||
import org.ruoyi.observability.MyChatModelListener;
|
||||
import org.ruoyi.service.chat.AbstractChatService;
|
||||
import org.springframework.stereotype.Service;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
|
||||
/**
|
||||
* 小米MiMo服务调用
|
||||
* <p>
|
||||
* 小米提供OpenAI兼容的API接口，支持MiMo等模型。
|
||||
*
|
||||
* @author ageerle
|
||||
* @date 2026/4/19
|
||||
*/
|
||||
@Service
|
||||
@Slf4j
|
||||
@RequiredArgsConstructor
|
||||
public class MiMoServiceImpl implements AbstractChatService {
|
||||
|
||||
@Override
|
||||
public StreamingChatModel buildStreamingChatModel(ChatModelVo chatModelVo, ChatRequest chatRequest) {
|
||||
return OpenAiStreamingChatModel.builder()
|
||||
.baseUrl(chatModelVo.getApiHost())
|
||||
.apiKey(chatModelVo.getApiKey())
|
||||
.modelName(chatModelVo.getModelName())
|
||||
.listeners(List.of(new MyChatModelListener()))
|
||||
.returnThinking(chatRequest.getEnableThinking())
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getProviderName() {
|
||||
return ChatModeType.XIAOMI.getCode();
|
||||
}
|
||||
|
||||
}
|
||||
@@ -0,0 +1,44 @@
|
||||
package org.ruoyi.service.chat.impl.provider;
|
||||
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import dev.langchain4j.model.openai.OpenAiStreamingChatModel;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.common.chat.domain.dto.request.ChatRequest;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.enums.ChatModeType;
|
||||
import org.ruoyi.observability.MyChatModelListener;
|
||||
import org.ruoyi.service.chat.AbstractChatService;
|
||||
import org.springframework.stereotype.Service;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* MiniMax服务调用
|
||||
* <p>
|
||||
* MiniMax提供OpenAI兼容的API接口，支持MiniMax-M2.7、MiniMax-M2.5等模型。
|
||||
* API地址：https://api.minimax.io/v1
|
||||
*
|
||||
* @author octopus
|
||||
* @date 2026/3/21
|
||||
*/
|
||||
@Service
|
||||
@Slf4j
|
||||
public class MinimaxServiceImpl implements AbstractChatService {
|
||||
|
||||
@Override
|
||||
public StreamingChatModel buildStreamingChatModel(ChatModelVo chatModelVo, ChatRequest chatRequest) {
|
||||
return OpenAiStreamingChatModel.builder()
|
||||
.baseUrl(chatModelVo.getApiHost())
|
||||
.apiKey(chatModelVo.getApiKey())
|
||||
.modelName(chatModelVo.getModelName())
|
||||
.listeners(List.of(new MyChatModelListener()))
|
||||
.returnThinking(chatRequest.getEnableThinking())
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getProviderName() {
|
||||
return ChatModeType.MINIMAX.getCode();
|
||||
}
|
||||
|
||||
}
|
||||
@@ -1,7 +1,9 @@
|
||||
package org.ruoyi.service.chat.impl.provider;
|
||||
|
||||
|
||||
import dev.langchain4j.model.chat.ChatModel;
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import dev.langchain4j.model.ollama.OllamaChatModel;
|
||||
import dev.langchain4j.model.ollama.OllamaStreamingChatModel;
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
@@ -37,6 +39,14 @@ public class OllamaServiceImpl implements AbstractChatService {
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public ChatModel buildChatModel(ChatModelVo chatModelVo) {
|
||||
return OllamaChatModel.builder()
|
||||
.baseUrl(chatModelVo.getApiHost())
|
||||
.modelName(chatModelVo.getModelName())
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getProviderName() {
|
||||
return ChatModeType.OLLAMA.getCode();
|
||||
|
||||
@@ -1,7 +1,9 @@
|
||||
package org.ruoyi.service.chat.impl.provider;
|
||||
|
||||
|
||||
import dev.langchain4j.community.model.dashscope.QwenChatModel;
|
||||
import dev.langchain4j.community.model.dashscope.QwenStreamingChatModel;
|
||||
import dev.langchain4j.model.chat.ChatModel;
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
@@ -38,6 +40,14 @@ public class QianWenChatServiceImpl implements AbstractChatService {
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public ChatModel buildChatModel(ChatModelVo chatModelVo) {
|
||||
return QwenChatModel.builder()
|
||||
.apiKey(chatModelVo.getApiKey())
|
||||
.modelName(chatModelVo.getModelName())
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getProviderName() {
|
||||
return ChatModeType.QIAN_WEN.getCode();
|
||||
|
||||
@@ -1,7 +1,9 @@
|
||||
package org.ruoyi.service.chat.impl.provider;
|
||||
|
||||
|
||||
import dev.langchain4j.community.model.zhipu.ZhipuAiChatModel;
|
||||
import dev.langchain4j.community.model.zhipu.ZhipuAiStreamingChatModel;
|
||||
import dev.langchain4j.model.chat.ChatModel;
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
@@ -35,6 +37,14 @@ public class ZhiPuChatServiceImpl implements AbstractChatService {
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public ChatModel buildChatModel(ChatModelVo chatModelVo) {
|
||||
return ZhipuAiChatModel.builder()
|
||||
.apiKey(chatModelVo.getApiKey())
|
||||
.model(chatModelVo.getModelName())
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getProviderName() {
|
||||
return ChatModeType.ZHI_PU.getCode();
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
package org.ruoyi.service.embed.impl;
|
||||
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
/**
|
||||
* MiniMax嵌入模型（兼容OpenAI接口）
|
||||
* <p>
|
||||
* 支持embo-01模型，1536维度向量。
|
||||
* API地址：https://api.minimax.io/v1
|
||||
*
|
||||
* @author octopus
|
||||
* @date 2026/3/21
|
||||
*/
|
||||
@Component("minimax")
|
||||
public class MinimaxEmbeddingProvider extends OpenAiEmbeddingProvider {
|
||||
|
||||
}
|
||||
@@ -0,0 +1,48 @@
|
||||
package org.ruoyi.service.embed.impl;
|
||||
|
||||
|
||||
|
||||
import dev.langchain4j.community.model.zhipu.ZhipuAiEmbeddingModel;
|
||||
import dev.langchain4j.data.embedding.Embedding;
|
||||
import dev.langchain4j.data.segment.TextSegment;
|
||||
import dev.langchain4j.model.embedding.EmbeddingModel;
|
||||
import dev.langchain4j.model.output.Response;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.enums.ModalityType;
|
||||
import org.ruoyi.service.embed.BaseEmbedModelService;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.util.List;
|
||||
import java.util.Set;
|
||||
|
||||
/**
|
||||
* @Author:yang
|
||||
* @Date:
|
||||
* @Description: 智谱AI嵌入模型
|
||||
*/
|
||||
@Component("zhipu")
|
||||
public class ZhipuAiEmbeddingProvider implements BaseEmbedModelService {
|
||||
protected ChatModelVo chatModelVo;
|
||||
|
||||
@Override
|
||||
public void configure(ChatModelVo config) {
|
||||
this.chatModelVo = config;
|
||||
}
|
||||
|
||||
@Override
|
||||
public Set<ModalityType> getSupportedModalities() {
|
||||
return Set.of(ModalityType.TEXT);
|
||||
}
|
||||
|
||||
@Override
|
||||
public Response<List<Embedding>> embedAll(List<TextSegment> textSegments) {
|
||||
EmbeddingModel model = ZhipuAiEmbeddingModel.builder()
|
||||
.baseUrl(chatModelVo.getApiHost())
|
||||
.apiKey(chatModelVo.getApiKey())
|
||||
.model(chatModelVo.getModelName())
|
||||
.dimensions(chatModelVo.getModelDimension())
|
||||
.build();
|
||||
|
||||
return model.embedAll(textSegments);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,70 @@
|
||||
package org.ruoyi.service.rerank;
|
||||
|
||||
import dev.langchain4j.data.segment.TextSegment;
|
||||
import dev.langchain4j.model.output.Response;
|
||||
import dev.langchain4j.model.scoring.ScoringModel;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.domain.bo.rerank.RerankRequest;
|
||||
import org.ruoyi.domain.bo.rerank.RerankResult;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 重排序模型服务接口
|
||||
* 继承 langchain4j 的 ScoringModel 接口
|
||||
* 参考设计模式：BaseEmbedModelService
|
||||
*
|
||||
* @author Yzm
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
public interface RerankModelService extends ScoringModel {
|
||||
|
||||
/**
|
||||
* 根据配置信息配置重排序模型
|
||||
*
|
||||
* @param config 包含模型配置信息的 ChatModelVo 对象
|
||||
*/
|
||||
void configure(ChatModelVo config);
|
||||
|
||||
/**
|
||||
* 执行重排序（批量文档）
|
||||
* 这是业务层使用的便捷方法
|
||||
*
|
||||
* @param rerankRequest 重排序请求，包含查询文本和候选文档列表
|
||||
* @return 重排序结果，包含排序后的文档和相关性分数
|
||||
*/
|
||||
RerankResult rerank(RerankRequest rerankRequest);
|
||||
|
||||
/**
|
||||
* 实现 ScoringModel 接口的 scoreAll 方法
|
||||
* 将 ScoringModel 的调用转换为重排序调用
|
||||
*/
|
||||
@Override
|
||||
default Response<List<Double>> scoreAll(List<TextSegment> segments, String query) {
|
||||
// 将 TextSegment 转换为文档字符串列表
|
||||
List<String> documents = segments.stream()
|
||||
.map(TextSegment::text)
|
||||
.toList();
|
||||
|
||||
RerankRequest request = RerankRequest.builder()
|
||||
.query(query)
|
||||
.documents(documents)
|
||||
.topN(documents.size())
|
||||
.returnDocuments(false)
|
||||
.build();
|
||||
|
||||
RerankResult result = rerank(request);
|
||||
|
||||
// 提取分数列表，按原始顺序排列
|
||||
List<Double> scores = new java.util.ArrayList<>(
|
||||
java.util.Collections.nCopies(documents.size(), 0.0));
|
||||
|
||||
for (RerankResult.RerankDocument doc : result.getDocuments()) {
|
||||
if (doc.getIndex() != null && doc.getIndex() < documents.size()) {
|
||||
scores.set(doc.getIndex(), doc.getRelevanceScore());
|
||||
}
|
||||
}
|
||||
|
||||
return Response.from(scores);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
package org.ruoyi.service.rerank.impl;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import okhttp3.*;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.domain.bo.rerank.RerankRequest;
|
||||
import org.ruoyi.domain.bo.rerank.RerankResult;
|
||||
import org.ruoyi.domain.dto.request.AliBaiLianRerankRequest;
|
||||
import org.ruoyi.domain.dto.response.AliBaiLianRerankResponse;
|
||||
import org.ruoyi.service.rerank.RerankModelService;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.util.concurrent.TimeUnit;
|
||||
|
||||
/**
|
||||
* 阿里百炼重排序模型实现
|
||||
* 参考设计模式：AliBaiLianMultiEmbeddingProvider
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-20
|
||||
*/
|
||||
@Slf4j
|
||||
@Component("qianwenRerank")
|
||||
public class AliBaiLianRerankModelService implements RerankModelService {
|
||||
|
||||
private final OkHttpClient okHttpClient;
|
||||
private final ObjectMapper objectMapper = new ObjectMapper();
|
||||
private ChatModelVo chatModelVo;
|
||||
|
||||
public AliBaiLianRerankModelService() {
|
||||
this.okHttpClient = new OkHttpClient.Builder()
|
||||
.connectTimeout(30, TimeUnit.SECONDS)
|
||||
.readTimeout(60, TimeUnit.SECONDS)
|
||||
.writeTimeout(30, TimeUnit.SECONDS)
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public void configure(ChatModelVo config) {
|
||||
this.chatModelVo = config;
|
||||
}
|
||||
|
||||
@Override
|
||||
public RerankResult rerank(RerankRequest rerankRequest) {
|
||||
long startTime = System.currentTimeMillis();
|
||||
|
||||
try {
|
||||
// 构建请求
|
||||
AliBaiLianRerankRequest request = buildRequest(rerankRequest);
|
||||
AliBaiLianRerankResponse response = executeRequest(request);
|
||||
|
||||
return response.toRerankResult(
|
||||
rerankRequest.getDocuments().size(),
|
||||
System.currentTimeMillis() - startTime
|
||||
);
|
||||
|
||||
} catch (Exception e) {
|
||||
log.error("阿里百炼重排序失败: {}", e.getMessage(), e);
|
||||
throw new RuntimeException("重排序服务调用失败: " + e.getMessage(), e);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 构建请求对象
|
||||
*/
|
||||
private AliBaiLianRerankRequest buildRequest(RerankRequest rerankRequest) {
|
||||
return AliBaiLianRerankRequest.create(
|
||||
chatModelVo.getModelName(),
|
||||
rerankRequest.getQuery(),
|
||||
rerankRequest.getDocuments(),
|
||||
rerankRequest.getTopN(),
|
||||
rerankRequest.getReturnDocuments()
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* 执行HTTP请求并解析响应
|
||||
*/
|
||||
private AliBaiLianRerankResponse executeRequest(AliBaiLianRerankRequest request) throws IOException {
|
||||
String jsonBody = request.toJson();
|
||||
RequestBody body = RequestBody.create(jsonBody, MediaType.get("application/json"));
|
||||
|
||||
// 阿里百炼重排序 OpenAI兼容端点
|
||||
String url = chatModelVo.getApiHost() + "/compatible-api/v1/reranks";
|
||||
Request httpRequest = new Request.Builder()
|
||||
.url(url)
|
||||
.addHeader("Authorization", "Bearer " + chatModelVo.getApiKey())
|
||||
.addHeader("Content-Type", "application/json")
|
||||
.post(body)
|
||||
.build();
|
||||
|
||||
try (Response response = okHttpClient.newCall(httpRequest).execute()) {
|
||||
if (!response.isSuccessful()) {
|
||||
String err = response.body() != null ? response.body().string() : "无错误信息";
|
||||
throw new IllegalArgumentException("阿里百炼API调用失败: " + response.code() + " - " + err);
|
||||
}
|
||||
|
||||
ResponseBody responseBody = response.body();
|
||||
if (responseBody == null) {
|
||||
throw new IllegalArgumentException("响应体为空");
|
||||
}
|
||||
|
||||
return parseResponse(responseBody.string());
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 解析响应
|
||||
*/
|
||||
private AliBaiLianRerankResponse parseResponse(String responseBody) throws IOException {
|
||||
return objectMapper.readValue(responseBody, AliBaiLianRerankResponse.class);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,163 @@
|
||||
package org.ruoyi.service.rerank.impl;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import io.jsonwebtoken.Jwts;
|
||||
import io.jsonwebtoken.security.MacAlgorithm;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import okhttp3.*;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.domain.bo.rerank.RerankRequest;
|
||||
import org.ruoyi.domain.bo.rerank.RerankResult;
|
||||
import org.ruoyi.domain.dto.request.ZhipuRerankRequest;
|
||||
import org.ruoyi.domain.dto.response.ZhipuRerankResponse;
|
||||
import org.ruoyi.service.rerank.RerankModelService;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import javax.crypto.spec.SecretKeySpec;
|
||||
import java.io.IOException;
|
||||
import java.lang.reflect.Constructor;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.util.concurrent.TimeUnit;
|
||||
|
||||
/**
|
||||
* 智谱AI 重排序模型实现
|
||||
* 参考设计模式：AliBaiLianMultiEmbeddingProvider
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
@Slf4j
|
||||
@Component("zhipuRerank")
|
||||
public class ZhiPuRerankModelService implements RerankModelService {
|
||||
|
||||
private final OkHttpClient okHttpClient;
|
||||
private final ObjectMapper objectMapper = new ObjectMapper();
|
||||
private ChatModelVo chatModelVo;
|
||||
|
||||
public ZhiPuRerankModelService() {
|
||||
this.okHttpClient = new OkHttpClient.Builder()
|
||||
.connectTimeout(30, TimeUnit.SECONDS)
|
||||
.readTimeout(60, TimeUnit.SECONDS)
|
||||
.writeTimeout(30, TimeUnit.SECONDS)
|
||||
.build();
|
||||
}
|
||||
|
||||
@Override
|
||||
public void configure(ChatModelVo config) {
|
||||
this.chatModelVo = config;
|
||||
}
|
||||
|
||||
@Override
|
||||
public RerankResult rerank(RerankRequest rerankRequest) {
|
||||
long startTime = System.currentTimeMillis();
|
||||
|
||||
try {
|
||||
// 构建请求
|
||||
ZhipuRerankRequest request = buildRequest(rerankRequest);
|
||||
ZhipuRerankResponse response = executeRequest(request);
|
||||
|
||||
return response.toRerankResult(
|
||||
rerankRequest.getDocuments().size(),
|
||||
System.currentTimeMillis() - startTime
|
||||
);
|
||||
|
||||
} catch (Exception e) {
|
||||
log.error("智谱重排序失败: {}", e.getMessage(), e);
|
||||
throw new RuntimeException("重排序服务调用失败: " + e.getMessage(), e);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 构建请求对象
|
||||
*/
|
||||
private ZhipuRerankRequest buildRequest(RerankRequest rerankRequest) {
|
||||
return ZhipuRerankRequest.create(
|
||||
chatModelVo.getModelName(),
|
||||
rerankRequest.getQuery(),
|
||||
rerankRequest.getDocuments(),
|
||||
rerankRequest.getTopN(),
|
||||
rerankRequest.getReturnDocuments()
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* 执行HTTP请求并解析响应
|
||||
*/
|
||||
private ZhipuRerankResponse executeRequest(ZhipuRerankRequest request) throws IOException {
|
||||
String jsonBody = request.toJson();
|
||||
RequestBody body = RequestBody.create(jsonBody, MediaType.get("application/json"));
|
||||
|
||||
// 生成智谱认证Token
|
||||
String token = generateToken(chatModelVo.getApiKey());
|
||||
|
||||
// 智谱重排序固定端点路径
|
||||
String url = chatModelVo.getApiHost() + "/api/paas/v4/rerank";
|
||||
Request httpRequest = new Request.Builder()
|
||||
.url(url)
|
||||
.addHeader("Authorization", token)
|
||||
.post(body)
|
||||
.build();
|
||||
|
||||
try (Response response = okHttpClient.newCall(httpRequest).execute()) {
|
||||
if (!response.isSuccessful()) {
|
||||
String err = response.body() != null ? response.body().string() : "无错误信息";
|
||||
throw new IllegalArgumentException("智谱API调用失败: " + response.code() + " - " + err);
|
||||
}
|
||||
|
||||
ResponseBody responseBody = response.body();
|
||||
if (responseBody == null) {
|
||||
throw new IllegalArgumentException("响应体为空");
|
||||
}
|
||||
|
||||
return parseResponse(responseBody.string());
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 解析响应
|
||||
*/
|
||||
private ZhipuRerankResponse parseResponse(String responseBody) throws IOException {
|
||||
return objectMapper.readValue(responseBody, ZhipuRerankResponse.class);
|
||||
}
|
||||
|
||||
/**
|
||||
* 生成智谱JWT Token
|
||||
*/
|
||||
private String generateToken(String apiKey) {
|
||||
try {
|
||||
String[] apiKeyParts = apiKey.split("\\.");
|
||||
String keyId = apiKeyParts[0];
|
||||
String secret = apiKeyParts[1];
|
||||
|
||||
long expireMillis = 1000L * 60 * 30; // 30分钟
|
||||
java.util.Map<String, Object> payload = new java.util.HashMap<>();
|
||||
payload.put("api_key", keyId);
|
||||
payload.put("exp", System.currentTimeMillis() + expireMillis);
|
||||
payload.put("timestamp", System.currentTimeMillis());
|
||||
|
||||
// 使用反射创建 MacAlgorithm（兼容不同版本的 jjwt）
|
||||
MacAlgorithm macAlgorithm;
|
||||
try {
|
||||
Class<?> c = Class.forName("io.jsonwebtoken.impl.security.DefaultMacAlgorithm");
|
||||
Constructor<?> ctor = c.getDeclaredConstructor(String.class, String.class, int.class);
|
||||
ctor.setAccessible(true);
|
||||
macAlgorithm = (MacAlgorithm) ctor.newInstance("HS256", "HmacSHA256", 128);
|
||||
} catch (Exception e) {
|
||||
macAlgorithm = Jwts.SIG.HS256;
|
||||
}
|
||||
|
||||
String token = Jwts.builder()
|
||||
.header()
|
||||
.add("alg", "HS256")
|
||||
.add("sign_type", "SIGN")
|
||||
.and()
|
||||
.content(objectMapper.writeValueAsString(payload))
|
||||
.signWith(new SecretKeySpec(secret.getBytes(StandardCharsets.UTF_8), "HmacSHA256"), macAlgorithm)
|
||||
.compact();
|
||||
|
||||
return "Bearer " + token;
|
||||
} catch (Exception e) {
|
||||
throw new RuntimeException("生成智谱Token失败: " + e.getMessage(), e);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,24 @@
|
||||
package org.ruoyi.service.retrieval;
|
||||
|
||||
import org.ruoyi.domain.bo.vector.QueryVectorBo;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 知识库检索服务接口
|
||||
* 整合粗召回（向量检索）和重排序流程
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
public interface KnowledgeRetrievalService {
|
||||
|
||||
/**
|
||||
* 执行知识库检索，返回文本内容
|
||||
* 流程：向量粗召回 -> 重排序（可选） -> 返回结果
|
||||
*
|
||||
* @param queryVectorBo 查询参数
|
||||
* @return 文本内容列表
|
||||
*/
|
||||
List<String> retrieveTexts(QueryVectorBo queryVectorBo);
|
||||
}
|
||||
@@ -0,0 +1,135 @@
|
||||
package org.ruoyi.service.retrieval.impl;
|
||||
|
||||
import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.domain.bo.rerank.RerankRequest;
|
||||
import org.ruoyi.domain.bo.rerank.RerankResult;
|
||||
import org.ruoyi.domain.bo.vector.QueryVectorBo;
|
||||
import org.ruoyi.factory.RerankModelFactory;
|
||||
import org.ruoyi.service.rerank.RerankModelService;
|
||||
import org.ruoyi.service.retrieval.KnowledgeRetrievalService;
|
||||
import org.ruoyi.service.vector.VectorStoreService;
|
||||
import org.springframework.stereotype.Service;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 知识库检索服务实现
|
||||
* 整合粗召回（向量检索）和重排序流程
|
||||
*
|
||||
* @author yang
|
||||
* @date 2026-04-19
|
||||
*/
|
||||
@Slf4j
|
||||
@Service
|
||||
@RequiredArgsConstructor
|
||||
public class KnowledgeRetrievalServiceImpl implements KnowledgeRetrievalService {
|
||||
|
||||
private final VectorStoreService vectorStoreService;
|
||||
private final RerankModelFactory rerankModelFactory;
|
||||
|
||||
/**
|
||||
* 粗召回默认扩大倍数
|
||||
* 如果启用重排序，粗召回会获取更多结果供重排序筛选
|
||||
*/
|
||||
private static final int RERANK_EXPANSION_FACTOR = 3;
|
||||
|
||||
@Override
|
||||
public List<String> retrieveTexts(QueryVectorBo queryVectorBo) {
|
||||
log.info("开始知识库检索, kid={}, query={}", queryVectorBo.getKid(), queryVectorBo.getQuery());
|
||||
|
||||
// 1. 粗召回阶段 - 向量检索
|
||||
List<String> coarseResults = coarseRetrieval(queryVectorBo);
|
||||
log.debug("粗召回返回 {} 条结果", coarseResults.size());
|
||||
|
||||
if (coarseResults.isEmpty()) {
|
||||
return coarseResults;
|
||||
}
|
||||
|
||||
// 2. 重排序阶段（可选）
|
||||
if (Boolean.TRUE.equals(queryVectorBo.getEnableRerank()) &&
|
||||
queryVectorBo.getRerankModelName() != null) {
|
||||
return rerank(queryVectorBo, coarseResults);
|
||||
}
|
||||
|
||||
return coarseResults;
|
||||
}
|
||||
|
||||
/**
|
||||
* 粗召回阶段 - 向量检索
|
||||
*/
|
||||
private List<String> coarseRetrieval(QueryVectorBo queryVectorBo) {
|
||||
// 如果启用重排序，扩大粗召回数量
|
||||
int originalMaxResults = queryVectorBo.getMaxResults();
|
||||
int expandedResults = originalMaxResults;
|
||||
if (Boolean.TRUE.equals(queryVectorBo.getEnableRerank()) &&
|
||||
queryVectorBo.getRerankModelName() != null) {
|
||||
expandedResults = originalMaxResults * RERANK_EXPANSION_FACTOR;
|
||||
log.debug("启用重排序，粗召回数量从 {} 扩大到 {}", originalMaxResults, expandedResults);
|
||||
}
|
||||
|
||||
// 临时修改查询数量
|
||||
queryVectorBo.setMaxResults(expandedResults);
|
||||
try {
|
||||
return vectorStoreService.getQueryVector(queryVectorBo);
|
||||
} finally {
|
||||
// 恢复原始值
|
||||
queryVectorBo.setMaxResults(originalMaxResults);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 重排序阶段
|
||||
*/
|
||||
private List<String> rerank(QueryVectorBo queryVectorBo, List<String> coarseResults) {
|
||||
long startTime = System.currentTimeMillis();
|
||||
|
||||
try {
|
||||
// 1. 通过工厂获取重排序模型
|
||||
RerankModelService rerankModel = rerankModelFactory.createModel(queryVectorBo.getRerankModelName());
|
||||
|
||||
// 2. 构建重排序请求
|
||||
int topN = queryVectorBo.getRerankTopN() != null ?
|
||||
queryVectorBo.getRerankTopN() : queryVectorBo.getMaxResults();
|
||||
|
||||
RerankRequest rerankRequest = RerankRequest.builder()
|
||||
.query(queryVectorBo.getQuery())
|
||||
.documents(coarseResults)
|
||||
.topN(topN)
|
||||
.returnDocuments(true)
|
||||
.build();
|
||||
|
||||
log.info("执行重排序, model={}, documents={}, topN={}",
|
||||
queryVectorBo.getRerankModelName(), coarseResults.size(), topN);
|
||||
|
||||
// 3. 执行重排序
|
||||
RerankResult rerankResult = rerankModel.rerank(rerankRequest);
|
||||
|
||||
// 4. 转换重排序结果
|
||||
List<String> finalResults = new ArrayList<>();
|
||||
for (RerankResult.RerankDocument doc : rerankResult.getDocuments()) {
|
||||
// 应用分数阈值过滤
|
||||
if (queryVectorBo.getRerankScoreThreshold() != null &&
|
||||
doc.getRelevanceScore() < queryVectorBo.getRerankScoreThreshold()) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (doc.getDocument() != null) {
|
||||
finalResults.add(doc.getDocument());
|
||||
}
|
||||
}
|
||||
|
||||
long duration = System.currentTimeMillis() - startTime;
|
||||
log.info("重排序完成, 返回 {} 条结果, 耗时 {}ms", finalResults.size(), duration);
|
||||
|
||||
return finalResults;
|
||||
|
||||
} catch (Exception e) {
|
||||
log.error("重排序失败: {}", e.getMessage(), e);
|
||||
// 重排序失败时返回原始粗召回结果（截取到期望数量）
|
||||
int limit = Math.min(queryVectorBo.getMaxResults(), coarseResults.size());
|
||||
return new ArrayList<>(coarseResults.subList(0, limit));
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,42 @@
|
||||
package org.ruoyi.enums;
|
||||
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
|
||||
/**
|
||||
* Unit tests for ChatModeType enum
|
||||
*/
|
||||
class ChatModeTypeTest {
|
||||
|
||||
@Test
|
||||
void minimaxEnumExists() {
|
||||
ChatModeType minimax = ChatModeType.MINIMAX;
|
||||
assertNotNull(minimax);
|
||||
}
|
||||
|
||||
@Test
|
||||
void minimaxCode_isMinimax() {
|
||||
assertEquals("minimax", ChatModeType.MINIMAX.getCode());
|
||||
}
|
||||
|
||||
@Test
|
||||
void minimaxDescription_isMiniMax() {
|
||||
assertEquals("MiniMax", ChatModeType.MINIMAX.getDescription());
|
||||
}
|
||||
|
||||
@Test
|
||||
void allProviders_haveUniqueCode() {
|
||||
ChatModeType[] values = ChatModeType.values();
|
||||
long uniqueCodes = java.util.Arrays.stream(values)
|
||||
.map(ChatModeType::getCode)
|
||||
.distinct()
|
||||
.count();
|
||||
assertEquals(values.length, uniqueCodes, "All providers must have unique codes");
|
||||
}
|
||||
|
||||
@Test
|
||||
void valueOf_minimax() {
|
||||
assertEquals(ChatModeType.MINIMAX, ChatModeType.valueOf("MINIMAX"));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,70 @@
|
||||
package org.ruoyi.integration;
|
||||
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.junit.jupiter.api.condition.EnabledIfEnvironmentVariable;
|
||||
import org.ruoyi.common.chat.domain.dto.request.ChatRequest;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.service.chat.impl.provider.MinimaxServiceImpl;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
|
||||
/**
|
||||
* Integration tests for MiniMax provider.
|
||||
* These tests require a valid MINIMAX_API_KEY environment variable.
|
||||
*/
|
||||
@EnabledIfEnvironmentVariable(named = "MINIMAX_API_KEY", matches = ".+")
|
||||
class MinimaxIntegrationTest {
|
||||
|
||||
private MinimaxServiceImpl minimaxService;
|
||||
private String apiKey;
|
||||
|
||||
@BeforeEach
|
||||
void setUp() {
|
||||
minimaxService = new MinimaxServiceImpl();
|
||||
apiKey = System.getenv("MINIMAX_API_KEY");
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildStreamingChatModel_withRealApiKey_M27() {
|
||||
ChatModelVo modelVo = new ChatModelVo();
|
||||
modelVo.setApiHost("https://api.minimax.io/v1");
|
||||
modelVo.setApiKey(apiKey);
|
||||
modelVo.setModelName("MiniMax-M2.7");
|
||||
|
||||
ChatRequest request = new ChatRequest();
|
||||
request.setEnableThinking(false);
|
||||
|
||||
StreamingChatModel model = minimaxService.buildStreamingChatModel(modelVo, request);
|
||||
assertNotNull(model, "Should create streaming model with real API key");
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildStreamingChatModel_withRealApiKey_M25() {
|
||||
ChatModelVo modelVo = new ChatModelVo();
|
||||
modelVo.setApiHost("https://api.minimax.io/v1");
|
||||
modelVo.setApiKey(apiKey);
|
||||
modelVo.setModelName("MiniMax-M2.5");
|
||||
|
||||
ChatRequest request = new ChatRequest();
|
||||
request.setEnableThinking(false);
|
||||
|
||||
StreamingChatModel model = minimaxService.buildStreamingChatModel(modelVo, request);
|
||||
assertNotNull(model, "Should create streaming model with M2.5");
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildStreamingChatModel_withRealApiKey_M25Highspeed() {
|
||||
ChatModelVo modelVo = new ChatModelVo();
|
||||
modelVo.setApiHost("https://api.minimax.io/v1");
|
||||
modelVo.setApiKey(apiKey);
|
||||
modelVo.setModelName("MiniMax-M2.5-highspeed");
|
||||
|
||||
ChatRequest request = new ChatRequest();
|
||||
request.setEnableThinking(false);
|
||||
|
||||
StreamingChatModel model = minimaxService.buildStreamingChatModel(modelVo, request);
|
||||
assertNotNull(model, "Should create streaming model with M2.5-highspeed");
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,76 @@
|
||||
package org.ruoyi.service.chat.impl.provider;
|
||||
|
||||
import dev.langchain4j.model.chat.StreamingChatModel;
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.ruoyi.common.chat.domain.dto.request.ChatRequest;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.enums.ChatModeType;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
|
||||
/**
|
||||
* Unit tests for MinimaxServiceImpl
|
||||
*/
|
||||
class MinimaxServiceImplTest {
|
||||
|
||||
private MinimaxServiceImpl minimaxService;
|
||||
|
||||
@BeforeEach
|
||||
void setUp() {
|
||||
minimaxService = new MinimaxServiceImpl();
|
||||
}
|
||||
|
||||
@Test
|
||||
void getProviderName_returnsMinimaxCode() {
|
||||
assertEquals("minimax", minimaxService.getProviderName());
|
||||
assertEquals(ChatModeType.MINIMAX.getCode(), minimaxService.getProviderName());
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildStreamingChatModel_returnsNonNull() {
|
||||
ChatModelVo modelVo = new ChatModelVo();
|
||||
modelVo.setApiHost("https://api.minimax.io/v1");
|
||||
modelVo.setApiKey("test-api-key");
|
||||
modelVo.setModelName("MiniMax-M2.7");
|
||||
|
||||
ChatRequest request = new ChatRequest();
|
||||
request.setEnableThinking(false);
|
||||
|
||||
StreamingChatModel model = minimaxService.buildStreamingChatModel(modelVo, request);
|
||||
assertNotNull(model);
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildStreamingChatModel_withThinkingEnabled() {
|
||||
ChatModelVo modelVo = new ChatModelVo();
|
||||
modelVo.setApiHost("https://api.minimax.io/v1");
|
||||
modelVo.setApiKey("test-api-key");
|
||||
modelVo.setModelName("MiniMax-M2.5");
|
||||
|
||||
ChatRequest request = new ChatRequest();
|
||||
request.setEnableThinking(true);
|
||||
|
||||
StreamingChatModel model = minimaxService.buildStreamingChatModel(modelVo, request);
|
||||
assertNotNull(model);
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildStreamingChatModel_withHighspeedModel() {
|
||||
ChatModelVo modelVo = new ChatModelVo();
|
||||
modelVo.setApiHost("https://api.minimax.io/v1");
|
||||
modelVo.setApiKey("test-api-key");
|
||||
modelVo.setModelName("MiniMax-M2.5-highspeed");
|
||||
|
||||
ChatRequest request = new ChatRequest();
|
||||
request.setEnableThinking(false);
|
||||
|
||||
StreamingChatModel model = minimaxService.buildStreamingChatModel(modelVo, request);
|
||||
assertNotNull(model);
|
||||
}
|
||||
|
||||
@Test
|
||||
void implementsAbstractChatService() {
|
||||
assertInstanceOf(org.ruoyi.service.chat.AbstractChatService.class, minimaxService);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,55 @@
|
||||
package org.ruoyi.service.embed.impl;
|
||||
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.enums.ModalityType;
|
||||
import org.ruoyi.service.embed.BaseEmbedModelService;
|
||||
|
||||
import java.util.Set;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
|
||||
/**
|
||||
* Unit tests for MinimaxEmbeddingProvider
|
||||
*/
|
||||
class MinimaxEmbeddingProviderTest {
|
||||
|
||||
private MinimaxEmbeddingProvider provider;
|
||||
|
||||
@BeforeEach
|
||||
void setUp() {
|
||||
provider = new MinimaxEmbeddingProvider();
|
||||
}
|
||||
|
||||
@Test
|
||||
void implementsBaseEmbedModelService() {
|
||||
assertInstanceOf(BaseEmbedModelService.class, provider);
|
||||
}
|
||||
|
||||
@Test
|
||||
void extendsOpenAiEmbeddingProvider() {
|
||||
assertInstanceOf(OpenAiEmbeddingProvider.class, provider);
|
||||
}
|
||||
|
||||
@Test
|
||||
void getSupportedModalities_returnsText() {
|
||||
Set<ModalityType> modalities = provider.getSupportedModalities();
|
||||
assertNotNull(modalities);
|
||||
assertTrue(modalities.contains(ModalityType.TEXT));
|
||||
assertEquals(1, modalities.size());
|
||||
}
|
||||
|
||||
@Test
|
||||
void configure_setsModelConfig() {
|
||||
ChatModelVo config = new ChatModelVo();
|
||||
config.setApiHost("https://api.minimax.io/v1");
|
||||
config.setApiKey("test-api-key");
|
||||
config.setModelName("embo-01");
|
||||
config.setModelDimension(1536);
|
||||
|
||||
provider.configure(config);
|
||||
// configure sets internal state; verify no exception thrown
|
||||
assertNotNull(provider);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,126 @@
|
||||
package org.ruoyi.service.rerank.impl;
|
||||
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.domain.bo.rerank.RerankRequest;
|
||||
import org.ruoyi.domain.bo.rerank.RerankResult;
|
||||
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
|
||||
/**
|
||||
* 阿里百炼重排序模型测试类
|
||||
* 运行前请设置环境变量 DASHSCOPE_API_KEY 或直接修改 apiKey
|
||||
*/
|
||||
class AliBaiLianRerankModelServiceTest {
|
||||
|
||||
private AliBaiLianRerankModelService service;
|
||||
|
||||
// 请替换为你的 API Key
|
||||
private static final String API_KEY = System.getenv("DASHSCOPE_API_KEY");
|
||||
private static final String API_HOST = "https://dashscope.aliyuncs.com";
|
||||
private static final String MODEL_NAME = "qwen3-rerank";
|
||||
|
||||
@BeforeEach
|
||||
void setUp() {
|
||||
service = new AliBaiLianRerankModelService();
|
||||
}
|
||||
|
||||
@Test
|
||||
void testConfigure() {
|
||||
ChatModelVo config = createConfig();
|
||||
service.configure(config);
|
||||
assertNotNull(service);
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRerank() {
|
||||
// 跳过测试如果没有配置 API Key
|
||||
if (API_KEY == null || API_KEY.isEmpty()) {
|
||||
System.out.println("跳过测试: 未设置环境变量 DASHSCOPE_API_KEY");
|
||||
return;
|
||||
}
|
||||
|
||||
ChatModelVo config = createConfig();
|
||||
service.configure(config);
|
||||
|
||||
List<String> documents = Arrays.asList(
|
||||
"文本排序模型广泛用于搜索引擎和推荐系统中，它们根据文本相关性对候选文本进行排序",
|
||||
"量子计算是计算科学的一个前沿领域",
|
||||
"预训练语言模型的发展给文本排序模型带来了新的进展"
|
||||
);
|
||||
|
||||
RerankRequest request = RerankRequest.builder()
|
||||
.query("什么是文本排序模型")
|
||||
.documents(documents)
|
||||
.topN(2)
|
||||
.returnDocuments(true)
|
||||
.build();
|
||||
|
||||
RerankResult result = service.rerank(request);
|
||||
|
||||
System.out.println("=== 重排序结果 ===");
|
||||
System.out.println("总文档数: " + result.getTotalDocuments());
|
||||
System.out.println("耗时: " + result.getDurationMs() + "ms");
|
||||
|
||||
result.getDocuments().forEach(doc -> {
|
||||
System.out.println("索引: " + doc.getIndex() +
|
||||
", 相关性分数: " + doc.getRelevanceScore() +
|
||||
", 文档: " + doc.getDocument());
|
||||
});
|
||||
|
||||
assertNotNull(result);
|
||||
assertNotNull(result.getDocuments());
|
||||
assertFalse(result.getDocuments().isEmpty());
|
||||
assertEquals(2, result.getDocuments().size());
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRerankWithFullDocuments() {
|
||||
if (API_KEY == null || API_KEY.isEmpty()) {
|
||||
System.out.println("跳过测试: 未设置环境变量 DASHSCOPE_API_KEY");
|
||||
return;
|
||||
}
|
||||
|
||||
ChatModelVo config = createConfig();
|
||||
service.configure(config);
|
||||
|
||||
List<String> documents = Arrays.asList(
|
||||
"Java是一种广泛使用的编程语言",
|
||||
"Python是人工智能领域最流行的语言",
|
||||
"Go语言由Google开发，适合并发编程"
|
||||
);
|
||||
|
||||
RerankRequest request = RerankRequest.builder()
|
||||
.query("哪种语言适合AI开发")
|
||||
.documents(documents)
|
||||
.build();
|
||||
|
||||
RerankResult result = service.rerank(request);
|
||||
|
||||
System.out.println("=== 重排序结果2 ===");
|
||||
result.getDocuments().forEach(doc -> {
|
||||
System.out.println("索引: " + doc.getIndex() +
|
||||
", 分数: " + doc.getRelevanceScore() +
|
||||
", 文档: " + doc.getDocument());
|
||||
});
|
||||
|
||||
assertNotNull(result);
|
||||
assertEquals(3, result.getDocuments().size());
|
||||
|
||||
// Python相关文档应该排在前面
|
||||
assertEquals(1, result.getDocuments().get(0).getIndex());
|
||||
assertTrue(result.getDocuments().get(0).getRelevanceScore() > 0.5);
|
||||
}
|
||||
|
||||
private ChatModelVo createConfig() {
|
||||
ChatModelVo config = new ChatModelVo();
|
||||
config.setApiHost(API_HOST);
|
||||
config.setApiKey(API_KEY != null ? API_KEY : "test-api-key");
|
||||
config.setModelName(MODEL_NAME);
|
||||
return config;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,73 @@
|
||||
package org.ruoyi.service.rerank.impl;
|
||||
|
||||
import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.domain.bo.rerank.RerankRequest;
|
||||
import org.ruoyi.domain.bo.rerank.RerankResult;
|
||||
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* 阿里百炼重排序模型测试 - Main方法直接运行
|
||||
* 运行前请设置 API_KEY
|
||||
*/
|
||||
public class AliBaiLianRerankTestMain {
|
||||
|
||||
// 请替换为你的 API Key
|
||||
private static final String API_KEY = "sk-your-api-key-here";
|
||||
private static final String API_HOST = "https://dashscope.aliyuncs.com";
|
||||
private static final String MODEL_NAME = "qwen3-rerank";
|
||||
|
||||
public static void main(String[] args) {
|
||||
AliBaiLianRerankModelService service = new AliBaiLianRerankModelService();
|
||||
|
||||
// 配置
|
||||
ChatModelVo config = new ChatModelVo();
|
||||
config.setApiHost(API_HOST);
|
||||
config.setApiKey(API_KEY);
|
||||
config.setModelName(MODEL_NAME);
|
||||
service.configure(config);
|
||||
|
||||
// 测试数据
|
||||
List<String> documents = Arrays.asList(
|
||||
"文本排序模型广泛用于搜索引擎和推荐系统中，它们根据文本相关性对候选文本进行排序",
|
||||
"量子计算是计算科学的一个前沿领域",
|
||||
"预训练语言模型的发展给文本排序模型带来了新的进展"
|
||||
);
|
||||
|
||||
RerankRequest request = RerankRequest.builder()
|
||||
.query("什么是文本排序模型")
|
||||
.documents(documents)
|
||||
.topN(2)
|
||||
.returnDocuments(true)
|
||||
.build();
|
||||
|
||||
System.out.println("=== 开始测试阿里百炼重排序 ===");
|
||||
System.out.println("API Host: " + API_HOST);
|
||||
System.out.println("Model: " + MODEL_NAME);
|
||||
System.out.println("Query: 什么是文本排序模型");
|
||||
System.out.println();
|
||||
|
||||
try {
|
||||
RerankResult result = service.rerank(request);
|
||||
|
||||
System.out.println("=== 重排序结果 ===");
|
||||
System.out.println("总文档数: " + result.getTotalDocuments());
|
||||
System.out.println("耗时: " + result.getDurationMs() + "ms");
|
||||
System.out.println();
|
||||
|
||||
result.getDocuments().forEach(doc -> {
|
||||
System.out.println("索引: " + doc.getIndex());
|
||||
System.out.println("相关性分数: " + doc.getRelevanceScore());
|
||||
System.out.println("文档: " + doc.getDocument());
|
||||
System.out.println("---");
|
||||
});
|
||||
|
||||
System.out.println("=== 测试成功 ===");
|
||||
|
||||
} catch (Exception e) {
|
||||
System.err.println("=== 测试失败 ===");
|
||||
e.printStackTrace();
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user