mirror of
https://gitcode.com/ageerle/ruoyi-ai.git
synced 2026-09-13 08:25:00 +00:00
Merge pull request #315 from MuSan-Li/update/2026-07-19-fixes
修复RAG相关逻辑优化:统一文档切割配置、向量数据生命周期、 统一检索服务(阈值/重排/缓存)、按知识库路由向量库、重新解析支持
This commit is contained in:
@@ -29,6 +29,12 @@
|
||||
<artifactId>ruoyi-common-chat</artifactId>
|
||||
</dependency>
|
||||
|
||||
<!-- 复用聊天模块的知识库统一检索能力(向量/混合/重排) -->
|
||||
<dependency>
|
||||
<groupId>org.ruoyi</groupId>
|
||||
<artifactId>ruoyi-chat</artifactId>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.ruoyi</groupId>
|
||||
<artifactId>ruoyi-common-web</artifactId>
|
||||
|
||||
@@ -80,9 +80,10 @@ public class KnowledgeRetrievalNode extends AbstractWfNode {
|
||||
String retrievalResult;
|
||||
String mode = config.getRetrievalMode() != null ? config.getRetrievalMode().toLowerCase() : "vector";
|
||||
|
||||
// 目前只支持向量检索,图谱检索需要依赖graph模块
|
||||
if ("graph".equals(mode) || "hybrid".equals(mode)) {
|
||||
log.warn("Graph retrieval mode is not supported in workflow-api module, falling back to vector retrieval");
|
||||
// 图谱检索需要依赖 graph 模块,暂不支持;vector/hybrid 由统一检索服务处理
|
||||
if ("graph".equals(mode)) {
|
||||
log.warn("Graph retrieval mode is not supported");
|
||||
throw new UnsupportedOperationException("GraphRAG retrieval is not supported");
|
||||
}
|
||||
|
||||
retrievalResult = retrieveFromVector(config, finalQuery);
|
||||
@@ -203,18 +204,75 @@ public class KnowledgeRetrievalNode extends AbstractWfNode {
|
||||
}
|
||||
|
||||
/**
|
||||
* 从向量库检索
|
||||
* 从向量库检索(复用聊天模块的统一检索服务:向量 + 可选混合检索 + 可选重排)
|
||||
*/
|
||||
private String retrieveFromVector(KnowledgeRetrievalNodeConfig config, String query) {
|
||||
try {
|
||||
|
||||
// 获取知识库信息以获取embedding模型配置
|
||||
Long knowledgeId = Long.parseLong(config.getKnowledgeId());
|
||||
|
||||
// 合并结果
|
||||
String mergedResult = "根据知识库id + query 查询知识库内容";
|
||||
org.ruoyi.service.knowledge.IKnowledgeInfoService knowledgeInfoService =
|
||||
SpringUtil.getBean(org.ruoyi.service.knowledge.IKnowledgeInfoService.class);
|
||||
org.ruoyi.domain.vo.knowledge.KnowledgeInfoVo kb = knowledgeInfoService.queryById(knowledgeId);
|
||||
if (kb == null) {
|
||||
log.error("Knowledge base not found: {}", knowledgeId);
|
||||
return "错误:知识库不存在, id=" + knowledgeId;
|
||||
}
|
||||
|
||||
return mergedResult;
|
||||
org.ruoyi.common.chat.service.chat.IChatModelService chatModelService =
|
||||
SpringUtil.getBean(org.ruoyi.common.chat.service.chat.IChatModelService.class);
|
||||
org.ruoyi.common.chat.domain.vo.chat.ChatModelVo embModel =
|
||||
chatModelService.selectModelByName(kb.getEmbeddingModel());
|
||||
if (embModel == null) {
|
||||
log.error("Embedding model not found: {}", kb.getEmbeddingModel());
|
||||
return "错误:知识库未配置有效的向量模型";
|
||||
}
|
||||
|
||||
// 组装检索参数:节点配置优先,混合检索/重排继承知识库配置
|
||||
org.ruoyi.domain.bo.vector.QueryVectorBo bo = new org.ruoyi.domain.bo.vector.QueryVectorBo();
|
||||
bo.setQuery(query);
|
||||
bo.setKid(String.valueOf(knowledgeId));
|
||||
bo.setMaxResults(config.getTopK() != null ? config.getTopK() : kb.getRetrieveLimit());
|
||||
bo.setSimilarityThreshold(config.getSimilarityThreshold() != null
|
||||
? config.getSimilarityThreshold() : kb.getSimilarityThreshold());
|
||||
bo.setEmbeddingModelName(kb.getEmbeddingModel());
|
||||
bo.setVectorModelName(kb.getVectorModel());
|
||||
bo.setApiKey(embModel.getApiKey());
|
||||
bo.setBaseUrl(embModel.getApiHost());
|
||||
|
||||
String mode = config.getRetrievalMode() != null ? config.getRetrievalMode().toLowerCase() : "vector";
|
||||
boolean enableHybrid = "hybrid".equals(mode)
|
||||
|| (kb.getEnableHybrid() != null && kb.getEnableHybrid() == 1);
|
||||
bo.setEnableHybrid(enableHybrid);
|
||||
bo.setHybridAlpha(kb.getHybridAlpha());
|
||||
bo.setEnableRerank(kb.getEnableRerank() != null && kb.getEnableRerank() == 1);
|
||||
bo.setRerankModelName(kb.getRerankModel());
|
||||
bo.setRerankTopN(kb.getRerankTopN());
|
||||
bo.setRerankScoreThreshold(kb.getRerankScoreThreshold());
|
||||
|
||||
org.ruoyi.service.retrieval.KnowledgeRetrievalService retrievalService =
|
||||
SpringUtil.getBean(org.ruoyi.service.retrieval.KnowledgeRetrievalService.class);
|
||||
java.util.List<org.ruoyi.domain.vo.knowledge.KnowledgeRetrievalVo> results = retrievalService.retrieve(bo);
|
||||
if (results == null || results.isEmpty()) {
|
||||
log.info("Knowledge retrieval returned no results, kid={}, query={}", knowledgeId, query);
|
||||
return "";
|
||||
}
|
||||
|
||||
// 合并结果
|
||||
boolean returnSource = config.getReturnSource() == null || config.getReturnSource();
|
||||
StringBuilder sb = new StringBuilder();
|
||||
for (int i = 0; i < results.size(); i++) {
|
||||
org.ruoyi.domain.vo.knowledge.KnowledgeRetrievalVo vo = results.get(i);
|
||||
sb.append(i + 1).append(". ").append(vo.getContent());
|
||||
if (returnSource && StringUtils.isNotBlank(vo.getSourceName())) {
|
||||
sb.append("(来源: ").append(vo.getSourceName());
|
||||
if (vo.getScore() != null) {
|
||||
sb.append(String.format(", 相关度: %.3f", vo.getScore()));
|
||||
}
|
||||
sb.append(")");
|
||||
}
|
||||
sb.append("\n");
|
||||
}
|
||||
return sb.toString().trim();
|
||||
} catch (NumberFormatException e) {
|
||||
log.error("Invalid knowledge base ID format: {}", config.getKnowledgeId(), e);
|
||||
return "错误:知识库ID格式无效";
|
||||
|
||||
@@ -9,6 +9,7 @@ import cn.dev33.satoken.annotation.SaCheckPermission;
|
||||
import org.ruoyi.domain.bo.knowledge.KnowledgeAttachBo;
|
||||
import org.ruoyi.domain.bo.knowledge.KnowledgeInfoUploadBo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeAttachVo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeReparseVo;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeAttachService;
|
||||
import org.springframework.web.bind.annotation.*;
|
||||
import org.springframework.validation.annotation.Validated;
|
||||
@@ -106,7 +107,10 @@ public class KnowledgeAttachController extends BaseController {
|
||||
|
||||
/**
|
||||
* 上传知识库附件
|
||||
* 注意:multipart 上传不能加 @RepeatSubmit(其参数序列化不支持 MultipartFile)
|
||||
*/
|
||||
@SaCheckPermission("system:attach:add")
|
||||
@Log(title = "知识库附件", businessType = BusinessType.INSERT)
|
||||
@PostMapping(value = "/upload")
|
||||
public R<String> upload(KnowledgeInfoUploadBo bo){
|
||||
knowledgeAttachService.upload(bo);
|
||||
@@ -118,9 +122,20 @@ public class KnowledgeAttachController extends BaseController {
|
||||
*
|
||||
* @param id 附件ID
|
||||
*/
|
||||
@SaCheckPermission("system:attach:edit")
|
||||
@Log(title = "知识库附件", businessType = BusinessType.UPDATE)
|
||||
@PostMapping("/parse/{id}")
|
||||
@RepeatSubmit()
|
||||
public R<Void> parse(@PathVariable Long id) {
|
||||
knowledgeAttachService.parse(id);
|
||||
return R.ok();
|
||||
}
|
||||
|
||||
@SaCheckPermission("system:attach:edit")
|
||||
@Log(title = "知识库附件批量重新解析", businessType = BusinessType.UPDATE)
|
||||
@PostMapping("/reparse/knowledge/{knowledgeId}")
|
||||
@RepeatSubmit()
|
||||
public R<KnowledgeReparseVo> reparseKnowledge(@PathVariable Long knowledgeId) {
|
||||
return R.ok(knowledgeAttachService.reparseKnowledge(knowledgeId));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -107,7 +107,9 @@ public class KnowledgeFragmentController extends BaseController {
|
||||
/**
|
||||
* 检索测试
|
||||
*/
|
||||
@SaCheckPermission("system:fragment:list")
|
||||
@PostMapping("/retrieval")
|
||||
@RepeatSubmit()
|
||||
public R<List<KnowledgeRetrievalVo>> retrieval(@RequestBody KnowledgeFragmentBo bo) {
|
||||
return R.ok(knowledgeFragmentService.retrieval(bo));
|
||||
}
|
||||
|
||||
@@ -37,6 +37,9 @@ public class KnowledgeAttach extends BaseEntity {
|
||||
*/
|
||||
private String docId;
|
||||
|
||||
/** SHA-256 content digest used for upload idempotency. */
|
||||
private String fileHash;
|
||||
|
||||
/**
|
||||
* 附件名称
|
||||
*/
|
||||
|
||||
@@ -27,6 +27,11 @@ public class KnowledgeFragment extends BaseEntity {
|
||||
@TableId(value = "id")
|
||||
private Long id;
|
||||
|
||||
/**
|
||||
* 向量库片段ID(与向量库中的 fid 元数据对应,用于向量定位与混合检索融合)
|
||||
*/
|
||||
private String fid;
|
||||
|
||||
/**
|
||||
* 文档ID-用于关联文本块信息
|
||||
*/
|
||||
|
||||
@@ -30,6 +30,11 @@ public class KnowledgeFragmentVo implements Serializable {
|
||||
@ExcelProperty(value = "主键")
|
||||
private Long id;
|
||||
|
||||
/**
|
||||
* 向量库片段ID
|
||||
*/
|
||||
private String fid;
|
||||
|
||||
/**
|
||||
* 文档ID-用于关联文本块信息
|
||||
*/
|
||||
|
||||
@@ -0,0 +1,4 @@
|
||||
package org.ruoyi.domain.vo.knowledge;
|
||||
|
||||
public record KnowledgeReparseVo(int submitted, int skipped, int total) {
|
||||
}
|
||||
@@ -77,13 +77,22 @@ public class EmbeddingModelFactory {
|
||||
|
||||
/**
|
||||
* 刷新模型缓存
|
||||
* 根据给定的嵌入模型ID从缓存中移除对应的模型
|
||||
* 根据给定的嵌入模型ID解析模型名称后,从缓存中移除对应的模型
|
||||
*
|
||||
* @param embeddingModelId 嵌入模型的唯一标识ID
|
||||
*/
|
||||
public void refreshModel(Long embeddingModelId) {
|
||||
// 从模型缓存中移除指定ID的模型
|
||||
modelCache.remove(embeddingModelId);
|
||||
ChatModelVo modelConfig = chatModelService.queryById(embeddingModelId);
|
||||
if (modelConfig != null) {
|
||||
modelCache.remove(modelConfig.getModelName());
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 按模型名称刷新缓存
|
||||
*/
|
||||
public void refreshModelByName(String embeddingModelName) {
|
||||
modelCache.remove(embeddingModelName);
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -55,12 +55,22 @@ public class RerankModelFactory {
|
||||
|
||||
/**
|
||||
* 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
|
||||
* 根据给定的模型ID解析模型名称后,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);
|
||||
ChatModelVo modelConfig = chatModelService.queryById(modelId);
|
||||
if (modelConfig != null) {
|
||||
modelCache.remove(modelConfig.getModelName());
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 按模型名称刷新缓存
|
||||
*/
|
||||
public void refreshModelByName(String modelName) {
|
||||
modelCache.remove(modelName);
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -17,7 +17,7 @@ public class ResourceLoaderFactory {
|
||||
private final ExcelTextSplitter excelTextSplitter;
|
||||
|
||||
public ResourceLoader getLoaderByFileType(String fileType) {
|
||||
fileType = StringUtils.removeStart(fileType, ".");
|
||||
fileType = StringUtils.lowerCase(StringUtils.removeStart(StringUtils.trim(fileType), "."));
|
||||
if (FileTypeConstants.isTextFile(fileType)) {
|
||||
return new TextFileLoader(characterTextSplitter);
|
||||
} else if (FileTypeConstants.isWord(fileType)) {
|
||||
|
||||
@@ -10,6 +10,7 @@ import org.ruoyi.service.vector.impl.MilvusVectorStoreStrategy;
|
||||
import org.ruoyi.service.vector.impl.QdrantVectorStoreStrategy;
|
||||
import org.ruoyi.service.vector.impl.WeaviateVectorStoreStrategy;
|
||||
import org.springframework.stereotype.Component;
|
||||
import org.ruoyi.common.core.exception.ServiceException;
|
||||
|
||||
import java.util.HashMap;
|
||||
import java.util.Map;
|
||||
@@ -45,14 +46,20 @@ public class VectorStoreStrategyFactory {
|
||||
* 获取当前配置的向量库策略
|
||||
*/
|
||||
public VectorStoreService getStrategy() {
|
||||
String vectorStoreType = vectorStoreProperties.getType();
|
||||
return getStrategy(null);
|
||||
}
|
||||
|
||||
public VectorStoreService getStrategy(String requestedType) {
|
||||
String vectorStoreType = requestedType;
|
||||
if (vectorStoreType == null || vectorStoreType.trim().isEmpty()) {
|
||||
vectorStoreType = vectorStoreProperties.getType();
|
||||
}
|
||||
if (vectorStoreType == null || vectorStoreType.trim().isEmpty()) {
|
||||
vectorStoreType = "weaviate"; // 默认使用weaviate
|
||||
}
|
||||
VectorStoreService strategy = strategies.get(vectorStoreType.toLowerCase());
|
||||
if (strategy == null) {
|
||||
log.warn("未找到向量库策略: {}, 使用默认策略: weaviate", vectorStoreType);
|
||||
strategy = strategies.get("weaviate");
|
||||
throw new ServiceException("不支持的向量库类型: " + vectorStoreType);
|
||||
}
|
||||
log.debug("使用向量库策略: {}", vectorStoreType);
|
||||
return strategy;
|
||||
|
||||
@@ -6,6 +6,8 @@ import org.apache.ibatis.annotations.Select;
|
||||
import org.ruoyi.domain.entity.knowledge.KnowledgeAttach;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeAttachVo;
|
||||
import org.ruoyi.common.mybatis.core.mapper.BaseMapperPlus;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
|
||||
/**
|
||||
* 知识库附件Mapper接口
|
||||
@@ -21,4 +23,10 @@ public interface KnowledgeAttachMapper extends BaseMapperPlus<KnowledgeAttach, K
|
||||
*/
|
||||
@Select("SELECT COUNT(*) FROM knowledge_attach WHERE knowledge_id = #{knowledgeId}")
|
||||
int countByKnowledgeId(@Param("knowledgeId") Long knowledgeId);
|
||||
|
||||
@Select("<script>SELECT knowledge_id AS knowledgeId, COUNT(*) AS documentCount " +
|
||||
"FROM knowledge_attach WHERE knowledge_id IN " +
|
||||
"<foreach collection='knowledgeIds' item='id' open='(' separator=',' close=')'>#{id}</foreach> " +
|
||||
"GROUP BY knowledge_id</script>")
|
||||
List<Map<String, Object>> countByKnowledgeIds(@Param("knowledgeIds") List<Long> knowledgeIds);
|
||||
}
|
||||
|
||||
@@ -34,7 +34,7 @@ public interface KnowledgeFragmentMapper extends BaseMapperPlus<KnowledgeFragmen
|
||||
"</script>")
|
||||
List<DocFragmentCountVo> selectFragmentCountByDocIds(@Param("docIds") List<String> docIds);
|
||||
@Select("<script>" +
|
||||
"SELECT id, doc_id AS docId, content, idx, knowledge_id AS knowledgeId " +
|
||||
"SELECT id, fid, doc_id AS docId, content, idx, knowledge_id AS knowledgeId " +
|
||||
"FROM knowledge_fragment " +
|
||||
"WHERE knowledge_id = #{knowledgeId} " +
|
||||
"AND MATCH (content) AGAINST (#{query} IN NATURAL LANGUAGE MODE) " +
|
||||
|
||||
@@ -77,6 +77,7 @@ import org.springframework.web.servlet.mvc.method.annotation.SseEmitter;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
import java.util.LinkedHashMap;
|
||||
import java.util.concurrent.CompletableFuture;
|
||||
import java.util.concurrent.ConcurrentHashMap;
|
||||
|
||||
@@ -161,7 +162,8 @@ public class ChatServiceFacade implements IChatService {
|
||||
throw new IllegalArgumentException("模型不存在: " + chatRequest.getModel());
|
||||
}
|
||||
|
||||
// 2. 构建上下文消息列表
|
||||
// 2. 构建上下文消息列表(系统提示词 + 历史消息 + 当前用户消息)
|
||||
// 注意:RAG 检索增强统一在 handleAgentChat 中执行一次,此处不再重复检索
|
||||
List<ChatMessage> contextMessages = buildContextMessages(chatRequest, agentVo);
|
||||
|
||||
chatRequest.setEmitter(emitter);
|
||||
@@ -282,12 +284,20 @@ public class ChatServiceFacade implements IChatService {
|
||||
.responseStrategy(SupervisorResponseStrategy.SUMMARY);
|
||||
SupervisorAgent supervisor = supervisorBuilder.build();
|
||||
|
||||
// 知识库增强:智能体绑定了知识库时,对 supervisor 输入做一次 RAG 增强
|
||||
// 知识库增强:智能体绑定了知识库时,对 supervisor 输入做一次 RAG 增强(全程唯一一次检索)
|
||||
String augmentedInput = augmentAgentInput(chatRequest, agentVo);
|
||||
// 智能体自定义系统提示词:supervisor builder 不支持 systemMessage,前置到输入
|
||||
String prompt = (agentVo != null && StringUtils.isNotBlank(agentVo.getSystemPrompt()))
|
||||
? agentVo.getSystemPrompt() + "\n\n" + augmentedInput
|
||||
: augmentedInput;
|
||||
// 组装最终 prompt:系统提示词 → 多轮历史 → RAG 增强后的当前提问
|
||||
StringBuilder promptBuilder = new StringBuilder();
|
||||
if (agentVo != null && StringUtils.isNotBlank(agentVo.getSystemPrompt())) {
|
||||
promptBuilder.append(agentVo.getSystemPrompt()).append("\n\n");
|
||||
}
|
||||
String historyText = formatHistoryMessages(chatRequest.getContextMessages(), chatRequest.getContent());
|
||||
if (StringUtils.isNotBlank(historyText)) {
|
||||
promptBuilder.append("以下是本次会话的历史对话,请结合上下文理解用户最新提问:\n")
|
||||
.append(historyText).append("\n\n");
|
||||
}
|
||||
promptBuilder.append(augmentedInput);
|
||||
String prompt = promptBuilder.toString();
|
||||
|
||||
String tokenValue = chatRequest.getTokenValue();
|
||||
|
||||
@@ -316,8 +326,9 @@ public class ChatServiceFacade implements IChatService {
|
||||
* 兜底 MCP 工具装配(无智能体时使用,保留原有 3 个硬编码客户端逻辑)
|
||||
*/
|
||||
private ToolProvider buildDefaultMcpToolProvider(Long userId) {
|
||||
String npxCommand = resolveNpxCommand();
|
||||
McpTransport playwrightTransport = new StdioMcpTransport.Builder()
|
||||
.command(List.of("C:\\Program Files\\nodejs\\npx.cmd", "-y", "@playwright/mcp@latest"))
|
||||
.command(List.of(npxCommand, "-y", "@playwright/mcp@latest"))
|
||||
.logEvents(true)
|
||||
.build();
|
||||
McpClient playwrightMcpClient = new DefaultMcpClient.Builder()
|
||||
@@ -327,7 +338,7 @@ public class ChatServiceFacade implements IChatService {
|
||||
|
||||
String userDir = System.getProperty("user.dir");
|
||||
McpTransport filesystemTransport = new StdioMcpTransport.Builder()
|
||||
.command(List.of("C:\\Program Files\\nodejs\\npx.cmd", "-y",
|
||||
.command(List.of(npxCommand, "-y",
|
||||
"@modelcontextprotocol/server-filesystem", userDir))
|
||||
.logEvents(true)
|
||||
.build();
|
||||
@@ -341,6 +352,14 @@ public class ChatServiceFacade implements IChatService {
|
||||
.build();
|
||||
}
|
||||
|
||||
private String resolveNpxCommand() {
|
||||
String configured = System.getProperty("mcp.npx.command");
|
||||
if (StringUtils.isNotBlank(configured)) return configured;
|
||||
String fromEnv = System.getenv("MCP_NPX_COMMAND");
|
||||
if (StringUtils.isNotBlank(fromEnv)) return fromEnv;
|
||||
return System.getProperty("os.name", "").toLowerCase().contains("win") ? "npx.cmd" : "npx";
|
||||
}
|
||||
|
||||
/**
|
||||
* 装配磁盘 ShellSkills:智能体勾选了技能名时按名过滤,否则加载全部。
|
||||
* 无 skills 时返回 null(调用方据此跳过 SkillsAgent 的 toolProvider 注入)
|
||||
@@ -476,27 +495,7 @@ public class ChatServiceFacade implements IChatService {
|
||||
messages.add(SystemMessage.from(agentVo.getSystemPrompt()));
|
||||
}
|
||||
|
||||
// 1. 初始化当前用户消息
|
||||
UserMessage userMessage = UserMessage.userMessage(chatRequest.getContent());
|
||||
|
||||
// 2. 知识库检索增强 (RAG):智能体的 knowledgeIds 优先,回退到请求的 knowledgeId
|
||||
List<Long> knowledgeIds = collectKnowledgeIds(chatRequest, agentVo);
|
||||
if (knowledgeIds != null && !knowledgeIds.isEmpty()) {
|
||||
RetrievalAugmentor augmentor = buildMultiKnowledgeAugmentor(knowledgeIds);
|
||||
if (augmentor != null) {
|
||||
log.info("执行多知识库 RAG 流程: kids={}", knowledgeIds);
|
||||
Metadata metadata = Metadata.from(userMessage, chatRequest.getSessionId(), new ArrayList<>());
|
||||
AugmentationRequest augmentationRequest = new AugmentationRequest(userMessage, metadata);
|
||||
AugmentationResult result = augmentor.augment(augmentationRequest);
|
||||
ChatMessage augmented = result.chatMessage();
|
||||
if (augmented instanceof UserMessage) {
|
||||
userMessage = (UserMessage) augmented;
|
||||
log.debug("RAG 增强完成,UserMessage 已注入背景知识");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// 3. 从数据库查询历史对话消息(放在前面)
|
||||
// 1. 从数据库查询历史对话消息(放在前面)
|
||||
if (chatRequest.getSessionId() != null) {
|
||||
MessageWindowChatMemory memory = createChatMemory(chatRequest.getSessionId());
|
||||
if (memory != null) {
|
||||
@@ -508,12 +507,37 @@ public class ChatServiceFacade implements IChatService {
|
||||
}
|
||||
}
|
||||
|
||||
// 4. 添加经过增强的用户消息(放在最后)
|
||||
messages.add(userMessage);
|
||||
// 2. 添加当前用户消息(放在最后;RAG 增强在 handleAgentChat 中统一执行,避免重复检索)
|
||||
messages.add(UserMessage.userMessage(chatRequest.getContent()));
|
||||
|
||||
return messages;
|
||||
}
|
||||
|
||||
/**
|
||||
* 将上下文消息格式化为多轮对话文本(供只接受 String 输入的 Supervisor 使用)。
|
||||
* 跳过 SystemMessage(系统提示词单独前置)与最后一条当前用户消息(单独做 RAG 增强后拼接)。
|
||||
*/
|
||||
private String formatHistoryMessages(List<ChatMessage> contextMessages, String currentContent) {
|
||||
if (contextMessages == null || contextMessages.isEmpty()) {
|
||||
return "";
|
||||
}
|
||||
StringBuilder sb = new StringBuilder();
|
||||
int limit = contextMessages.size();
|
||||
// 最后一条是当前用户消息,不纳入历史(避免与增强后的输入重复)
|
||||
if (limit > 0 && contextMessages.get(limit - 1) instanceof UserMessage) {
|
||||
limit--;
|
||||
}
|
||||
for (int i = 0; i < limit; i++) {
|
||||
ChatMessage msg = contextMessages.get(i);
|
||||
if (msg instanceof UserMessage userMsg) {
|
||||
sb.append("用户: ").append(userMsg.singleText()).append("\n");
|
||||
} else if (msg instanceof AiMessage aiMsg) {
|
||||
sb.append("助手: ").append(aiMsg.text()).append("\n");
|
||||
}
|
||||
}
|
||||
return sb.toString().trim();
|
||||
}
|
||||
|
||||
/**
|
||||
* 汇总本次对话要检索的知识库ID列表:智能体绑定的 knowledgeIds 优先,回退到请求的 knowledgeId
|
||||
*/
|
||||
@@ -580,18 +604,35 @@ public class ChatServiceFacade implements IChatService {
|
||||
|
||||
@Override
|
||||
public List<Content> retrieve(Query query) {
|
||||
List<Content> all = new ArrayList<>();
|
||||
for (ContentRetriever r : delegates) {
|
||||
try {
|
||||
List<Content> part = r.retrieve(query);
|
||||
if (part != null) {
|
||||
all.addAll(part);
|
||||
}
|
||||
} catch (Exception e) {
|
||||
log.warn("复合检索子检索器异常: {}", e.getMessage());
|
||||
List<CompletableFuture<List<Content>>> futures = delegates.stream()
|
||||
.map(r -> CompletableFuture.supplyAsync(() -> {
|
||||
try {
|
||||
List<Content> part = r.retrieve(query);
|
||||
return part == null ? List.<Content>of() : part;
|
||||
} catch (Exception e) {
|
||||
log.warn("复合检索子检索器异常: {}", e.getMessage());
|
||||
return List.<Content>of();
|
||||
}
|
||||
})).toList();
|
||||
Map<String, Content> unique = new LinkedHashMap<>();
|
||||
for (CompletableFuture<List<Content>> future : futures) {
|
||||
for (Content content : future.join()) {
|
||||
String key = content.textSegment().metadata().getString("kid") + "|"
|
||||
+ content.textSegment().metadata().getString("docId") + "|"
|
||||
+ content.textSegment().metadata().getString("fid");
|
||||
if (key.endsWith("null|null|null")) key = content.textSegment().text();
|
||||
unique.putIfAbsent(key, content);
|
||||
}
|
||||
}
|
||||
return all;
|
||||
List<Content> bounded = new ArrayList<>();
|
||||
int chars = 0;
|
||||
for (Content content : unique.values()) {
|
||||
int next = content.textSegment().text().length();
|
||||
if (bounded.size() >= 20 || chars + next > 24000) break;
|
||||
bounded.add(content);
|
||||
chars += next;
|
||||
}
|
||||
return bounded;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -19,6 +19,7 @@ import java.util.Set;
|
||||
* @Description: 阿里百炼基础嵌入模型(兼容openai)
|
||||
*/
|
||||
@Component("alibailian")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class AliBaiLianBaseEmbedProvider extends OpenAiEmbeddingProvider {
|
||||
|
||||
private ChatModelVo chatModelVo;
|
||||
|
||||
@@ -24,6 +24,7 @@ import java.util.concurrent.TimeUnit;
|
||||
* 实现了MultiModalEmbedModelService接口,提供文本、图像和视频的嵌入向量生成服务
|
||||
*/
|
||||
@Component("bailianMultiModel")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
@Slf4j
|
||||
public class AliBaiLianMultiEmbeddingProvider implements MultiModalEmbedModelService {
|
||||
private final OkHttpClient okHttpClient;
|
||||
|
||||
@@ -12,6 +12,7 @@ import org.springframework.stereotype.Component;
|
||||
* @date 2026/3/21
|
||||
*/
|
||||
@Component("minimax")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class MinimaxEmbeddingProvider extends OpenAiEmbeddingProvider {
|
||||
|
||||
}
|
||||
|
||||
@@ -19,6 +19,7 @@ import java.util.Set;
|
||||
* @Description: Ollama嵌入模型
|
||||
*/
|
||||
@Component("ollama")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class OllamaEmbeddingProvider implements BaseEmbedModelService {
|
||||
private ChatModelVo chatModelVo;
|
||||
|
||||
|
||||
@@ -19,6 +19,7 @@ import java.util.Set;
|
||||
* @Description: OpenAi嵌入模型
|
||||
*/
|
||||
@Component("openai")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class OpenAiEmbeddingProvider implements BaseEmbedModelService {
|
||||
protected ChatModelVo chatModelVo;
|
||||
|
||||
|
||||
@@ -9,6 +9,7 @@ import org.springframework.stereotype.Component;
|
||||
* @Description: 硅基流动(兼容 OpenAi)
|
||||
*/
|
||||
@Component("siliconflow")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class SiliconFlowEmbeddingProvider extends OpenAiEmbeddingProvider {
|
||||
|
||||
}
|
||||
|
||||
@@ -21,6 +21,7 @@ import java.util.Set;
|
||||
* @Description: 智谱AI嵌入模型
|
||||
*/
|
||||
@Component("zhipu")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class ZhipuAiEmbeddingProvider implements BaseEmbedModelService {
|
||||
protected ChatModelVo chatModelVo;
|
||||
|
||||
|
||||
@@ -0,0 +1,20 @@
|
||||
package org.ruoyi.service.knowledge;
|
||||
|
||||
import org.ruoyi.common.core.exception.ServiceException;
|
||||
|
||||
/** Immutable snapshot of the split settings used for one parse operation. */
|
||||
public record DocumentSplitConfig(String separator, int blockSize, int overlap, String fileType) {
|
||||
|
||||
public static final int DEFAULT_BLOCK_SIZE = 1000;
|
||||
public static final int DEFAULT_OVERLAP = 50;
|
||||
|
||||
public DocumentSplitConfig {
|
||||
if (blockSize <= 0) {
|
||||
throw new ServiceException("文本块大小必须大于0");
|
||||
}
|
||||
if (overlap < 0 || overlap >= blockSize) {
|
||||
throw new ServiceException("重叠字符数必须大于等于0且小于文本块大小");
|
||||
}
|
||||
fileType = fileType == null ? "" : fileType.strip().replaceFirst("^\\.", "").toLowerCase();
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ import org.ruoyi.common.mybatis.core.page.PageQuery;
|
||||
import org.ruoyi.domain.bo.knowledge.KnowledgeAttachBo;
|
||||
import org.ruoyi.domain.bo.knowledge.KnowledgeInfoUploadBo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeAttachVo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeReparseVo;
|
||||
|
||||
import java.util.Collection;
|
||||
import java.util.List;
|
||||
@@ -79,4 +80,6 @@ public interface IKnowledgeAttachService {
|
||||
* @param id 附件ID
|
||||
*/
|
||||
void parse(Long id);
|
||||
|
||||
KnowledgeReparseVo reparseKnowledge(Long knowledgeId);
|
||||
}
|
||||
|
||||
@@ -10,5 +10,5 @@ public interface ResourceLoader {
|
||||
|
||||
String getContent(InputStream inputStream);
|
||||
|
||||
List<String> getChunkList(String content, String kid);
|
||||
List<String> getChunkList(String content, DocumentSplitConfig config);
|
||||
}
|
||||
|
||||
@@ -11,8 +11,8 @@ public interface TextSplitter {
|
||||
* 文本切分
|
||||
*
|
||||
* @param content 文本内容
|
||||
* @param kid 知识库id
|
||||
* @param config 本次解析的分片配置快照
|
||||
* @return 切分后的文本列表
|
||||
*/
|
||||
List<String> split(String content, String kid);
|
||||
List<String> split(String content, DocumentSplitConfig config);
|
||||
}
|
||||
|
||||
@@ -2,6 +2,7 @@ package org.ruoyi.service.knowledge.impl;
|
||||
|
||||
import cn.hutool.core.collection.CollUtil;
|
||||
import cn.hutool.core.util.RandomUtil;
|
||||
import cn.hutool.crypto.digest.DigestUtil;
|
||||
import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
|
||||
import com.baomidou.mybatisplus.core.toolkit.Wrappers;
|
||||
import com.baomidou.mybatisplus.extension.plugins.pagination.Page;
|
||||
@@ -11,6 +12,7 @@ import org.ruoyi.common.chat.domain.vo.chat.ChatModelVo;
|
||||
import org.ruoyi.common.chat.service.chat.IChatModelService;
|
||||
import org.ruoyi.enums.KnowledgeAttachStatus;
|
||||
import org.ruoyi.common.core.domain.dto.OssDTO;
|
||||
import org.ruoyi.common.core.exception.ServiceException;
|
||||
import org.ruoyi.common.core.service.OssService;
|
||||
import org.ruoyi.common.core.utils.MapstructUtils;
|
||||
import org.ruoyi.common.core.utils.SpringUtils;
|
||||
@@ -25,13 +27,16 @@ import org.ruoyi.domain.entity.knowledge.KnowledgeFragment;
|
||||
import org.ruoyi.domain.vo.knowledge.DocFragmentCountVo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeAttachVo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeInfoVo;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeReparseVo;
|
||||
import org.ruoyi.factory.ResourceLoaderFactory;
|
||||
import org.ruoyi.mapper.knowledge.KnowledgeAttachMapper;
|
||||
import org.ruoyi.mapper.knowledge.KnowledgeFragmentMapper;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeAttachService;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeInfoService;
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.vector.VectorStoreService;
|
||||
import org.ruoyi.service.retrieval.KnowledgeRetrievalService;
|
||||
import org.springframework.scheduling.annotation.Async;
|
||||
import org.springframework.stereotype.Service;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
@@ -60,6 +65,7 @@ public class KnowledgeAttachServiceImpl implements IKnowledgeAttachService {
|
||||
private final ResourceLoaderFactory resourceLoaderFactory;
|
||||
private final VectorStoreService vectorStoreService;
|
||||
private final OssService ossService;
|
||||
private final KnowledgeRetrievalService knowledgeRetrievalService;
|
||||
|
||||
@Override
|
||||
public KnowledgeAttachVo queryById(Long id) {
|
||||
@@ -126,18 +132,44 @@ public class KnowledgeAttachServiceImpl implements IKnowledgeAttachService {
|
||||
|
||||
@Override
|
||||
public Boolean deleteWithValidByIds(Collection<Long> ids, Boolean isValid) {
|
||||
// 删除附件前,同步清理其片段记录与向量库中的向量
|
||||
List<KnowledgeAttach> attaches = baseMapper.selectByIds(ids);
|
||||
for (KnowledgeAttach attach : attaches) {
|
||||
String docId = attach.getDocId();
|
||||
String kid = String.valueOf(attach.getKnowledgeId());
|
||||
vectorStoreService.removeByDocId(docId, kid);
|
||||
knowledgeFragmentMapper.delete(
|
||||
Wrappers.<KnowledgeFragment>lambdaQuery().eq(KnowledgeFragment::getDocId, docId));
|
||||
if (attach.getOssId() != null) {
|
||||
ossService.deleteFile(attach.getOssId());
|
||||
}
|
||||
knowledgeRetrievalService.invalidateKnowledge(kid);
|
||||
}
|
||||
return baseMapper.deleteByIds(ids) > 0;
|
||||
}
|
||||
|
||||
@Override
|
||||
public void upload(KnowledgeInfoUploadBo bo) {
|
||||
MultipartFile file = bo.getFile();
|
||||
final String fileHash;
|
||||
try (InputStream input = file.getInputStream()) {
|
||||
fileHash = DigestUtil.sha256Hex(input);
|
||||
} catch (Exception e) {
|
||||
throw new ServiceException("计算文件摘要失败", e);
|
||||
}
|
||||
boolean duplicate = baseMapper.exists(Wrappers.<KnowledgeAttach>lambdaQuery()
|
||||
.eq(KnowledgeAttach::getKnowledgeId, bo.getKnowledgeId())
|
||||
.eq(KnowledgeAttach::getFileHash, fileHash));
|
||||
if (duplicate) {
|
||||
throw new ServiceException("该文件已上传,请勿重复提交");
|
||||
}
|
||||
OssDTO ossDTO = ossService.uploadFile(file);
|
||||
|
||||
KnowledgeAttach knowledgeAttach = new KnowledgeAttach();
|
||||
knowledgeAttach.setKnowledgeId(bo.getKnowledgeId());
|
||||
knowledgeAttach.setOssId(ossDTO.getOssId());
|
||||
knowledgeAttach.setDocId(RandomUtil.randomString(10));
|
||||
knowledgeAttach.setFileHash(fileHash);
|
||||
knowledgeAttach.setName(ossDTO.getOriginalName());
|
||||
knowledgeAttach.setType(ossDTO.getFileSuffix());
|
||||
knowledgeAttach.setStatus(KnowledgeAttachStatus.WAITING.getCode()); // 待解析
|
||||
@@ -154,10 +186,17 @@ public class KnowledgeAttachServiceImpl implements IKnowledgeAttachService {
|
||||
@Override
|
||||
public void parse(Long id) {
|
||||
KnowledgeAttach attach = baseMapper.selectById(id);
|
||||
if (attach == null || (!KnowledgeAttachStatus.WAITING.getCode().equals(attach.getStatus()) && !KnowledgeAttachStatus.FAILED.getCode().equals(attach.getStatus()))) {
|
||||
if (attach == null || KnowledgeAttachStatus.PARSING.getCode().equals(attach.getStatus())) {
|
||||
return;
|
||||
}
|
||||
|
||||
int claimed = baseMapper.update(null, Wrappers.<KnowledgeAttach>lambdaUpdate()
|
||||
.set(KnowledgeAttach::getStatus, KnowledgeAttachStatus.PARSING.getCode())
|
||||
.set(KnowledgeAttach::getRemark, null)
|
||||
.eq(KnowledgeAttach::getId, id)
|
||||
.ne(KnowledgeAttach::getStatus, KnowledgeAttachStatus.PARSING.getCode()));
|
||||
if (claimed == 0) return;
|
||||
|
||||
try {
|
||||
attach.setStatus(KnowledgeAttachStatus.PARSING.getCode()); // 解析中
|
||||
baseMapper.updateById(attach);
|
||||
@@ -166,6 +205,18 @@ public class KnowledgeAttachServiceImpl implements IKnowledgeAttachService {
|
||||
|
||||
Long knowledgeId = attach.getKnowledgeId();
|
||||
String docId = attach.getDocId();
|
||||
KnowledgeInfoVo knowledgeInfoVo = knowledgeInfoService.queryById(knowledgeId);
|
||||
if (knowledgeInfoVo == null) {
|
||||
throw new ServiceException("知识库不存在: " + knowledgeId);
|
||||
}
|
||||
int blockSize = knowledgeInfoVo.getTextBlockSize() == null
|
||||
? DocumentSplitConfig.DEFAULT_BLOCK_SIZE : knowledgeInfoVo.getTextBlockSize().intValue();
|
||||
int overlap = knowledgeInfoVo.getOverlapChar() == null
|
||||
? DocumentSplitConfig.DEFAULT_OVERLAP : knowledgeInfoVo.getOverlapChar().intValue();
|
||||
DocumentSplitConfig splitConfig = new DocumentSplitConfig(
|
||||
knowledgeInfoVo.getSeparator(), blockSize, overlap, attach.getType());
|
||||
List<KnowledgeFragment> oldFragments = knowledgeFragmentMapper.selectList(
|
||||
Wrappers.<KnowledgeFragment>lambdaQuery().eq(KnowledgeFragment::getDocId, docId));
|
||||
|
||||
// 获取文件信息并下载
|
||||
List<OssDTO> ossDTOs = ossService.selectByIds(String.valueOf(attach.getOssId()));
|
||||
@@ -178,28 +229,27 @@ public class KnowledgeAttachServiceImpl implements IKnowledgeAttachService {
|
||||
try (InputStream inputStream = new URL(ossDTO.getUrl()).openStream()) {
|
||||
content = resourceLoader.getContent(inputStream);
|
||||
}
|
||||
List<String> chunkList = resourceLoader.getChunkList(content, String.valueOf(knowledgeId));
|
||||
List<String> chunkList = resourceLoader.getChunkList(content, splitConfig);
|
||||
|
||||
List<String> fids = new ArrayList<>();
|
||||
List<KnowledgeFragment> knowledgeFragmentList = new ArrayList<>();
|
||||
if (CollUtil.isNotEmpty(chunkList)) {
|
||||
for (int i = 0; i < chunkList.size(); i++) {
|
||||
String fid = RandomUtil.randomString(10);
|
||||
fids.add(fid);
|
||||
KnowledgeFragment knowledgeFragment = new KnowledgeFragment();
|
||||
knowledgeFragment.setKnowledgeId(knowledgeId);
|
||||
knowledgeFragment.setDocId(docId);
|
||||
knowledgeFragment.setIdx(i);
|
||||
knowledgeFragment.setContent(chunkList.get(i));
|
||||
knowledgeFragment.setCreateTime(new Date());
|
||||
knowledgeFragmentList.add(knowledgeFragment);
|
||||
}
|
||||
knowledgeFragmentMapper.delete(Wrappers.<KnowledgeFragment>lambdaQuery().eq(KnowledgeFragment::getDocId, docId));
|
||||
knowledgeFragmentMapper.insertBatch(knowledgeFragmentList);
|
||||
log.info("文档切片并入库完成,共计 {} 个片段。id: {}", chunkList.size(), id);
|
||||
if (CollUtil.isEmpty(chunkList)) {
|
||||
throw new RuntimeException("文档分片结果为空,请检查文档内容或分片器是否支持该文件类型");
|
||||
}
|
||||
|
||||
KnowledgeInfoVo knowledgeInfoVo = knowledgeInfoService.queryById(knowledgeId);
|
||||
// 重新解析前先清理旧的向量数据,避免向量重复累积
|
||||
List<String> fids = new ArrayList<>();
|
||||
List<KnowledgeFragment> knowledgeFragmentList = new ArrayList<>();
|
||||
for (int i = 0; i < chunkList.size(); i++) {
|
||||
String fid = RandomUtil.randomString(10);
|
||||
fids.add(fid);
|
||||
KnowledgeFragment knowledgeFragment = new KnowledgeFragment();
|
||||
knowledgeFragment.setKnowledgeId(knowledgeId);
|
||||
knowledgeFragment.setDocId(docId);
|
||||
knowledgeFragment.setFid(fid);
|
||||
knowledgeFragment.setIdx(i);
|
||||
knowledgeFragment.setContent(chunkList.get(i));
|
||||
knowledgeFragment.setCreateTime(new Date());
|
||||
knowledgeFragmentList.add(knowledgeFragment);
|
||||
}
|
||||
ChatModelVo chatModelVo = chatModelService.selectModelByName(knowledgeInfoVo.getEmbeddingModel());
|
||||
|
||||
StoreEmbeddingBo storeEmbeddingBo = new StoreEmbeddingBo();
|
||||
@@ -211,7 +261,27 @@ public class KnowledgeAttachServiceImpl implements IKnowledgeAttachService {
|
||||
storeEmbeddingBo.setEmbeddingModelName(knowledgeInfoVo.getEmbeddingModel());
|
||||
storeEmbeddingBo.setApiKey(chatModelVo.getApiKey());
|
||||
storeEmbeddingBo.setBaseUrl(chatModelVo.getApiHost());
|
||||
vectorStoreService.storeEmbeddings(storeEmbeddingBo);
|
||||
try {
|
||||
vectorStoreService.storeEmbeddings(storeEmbeddingBo);
|
||||
for (KnowledgeFragment old : oldFragments) {
|
||||
if (StringUtils.isNotBlank(old.getFid())) {
|
||||
vectorStoreService.removeByFid(old.getFid(), String.valueOf(knowledgeId));
|
||||
}
|
||||
}
|
||||
} catch (Exception vectorError) {
|
||||
for (String newFid : fids) {
|
||||
try {
|
||||
vectorStoreService.removeByFid(newFid, String.valueOf(knowledgeId));
|
||||
} catch (Exception cleanupError) {
|
||||
log.error("补偿删除新向量失败, kid={}, fid={}", knowledgeId, newFid, cleanupError);
|
||||
}
|
||||
}
|
||||
throw vectorError;
|
||||
}
|
||||
|
||||
knowledgeFragmentMapper.delete(Wrappers.<KnowledgeFragment>lambdaQuery().eq(KnowledgeFragment::getDocId, docId));
|
||||
knowledgeFragmentMapper.insertBatch(knowledgeFragmentList);
|
||||
knowledgeRetrievalService.invalidateKnowledge(String.valueOf(knowledgeId));
|
||||
|
||||
attach.setStatus(KnowledgeAttachStatus.COMPLETED.getCode()); // 已完成
|
||||
baseMapper.updateById(attach);
|
||||
@@ -223,4 +293,22 @@ public class KnowledgeAttachServiceImpl implements IKnowledgeAttachService {
|
||||
baseMapper.updateById(attach);
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
public KnowledgeReparseVo reparseKnowledge(Long knowledgeId) {
|
||||
List<KnowledgeAttach> attachments = baseMapper.selectList(
|
||||
Wrappers.<KnowledgeAttach>lambdaQuery().eq(KnowledgeAttach::getKnowledgeId, knowledgeId));
|
||||
int submitted = 0;
|
||||
int skipped = 0;
|
||||
IKnowledgeAttachService proxy = SpringUtils.getBean(IKnowledgeAttachService.class);
|
||||
for (KnowledgeAttach attachment : attachments) {
|
||||
if (KnowledgeAttachStatus.PARSING.getCode().equals(attachment.getStatus())) {
|
||||
skipped++;
|
||||
} else {
|
||||
proxy.parse(attachment.getId());
|
||||
submitted++;
|
||||
}
|
||||
}
|
||||
return new KnowledgeReparseVo(submitted, skipped, attachments.size());
|
||||
}
|
||||
}
|
||||
|
||||
@@ -40,6 +40,7 @@ public class KnowledgeFragmentServiceImpl implements IKnowledgeFragmentService {
|
||||
private final IKnowledgeInfoService knowledgeInfoService;
|
||||
private final IChatModelService chatModelService;
|
||||
private final KnowledgeRetrievalService knowledgeRetrievalService;
|
||||
private final org.ruoyi.service.vector.VectorStoreService vectorStoreService;
|
||||
|
||||
/**
|
||||
* 查询知识片段
|
||||
@@ -114,7 +115,11 @@ public class KnowledgeFragmentServiceImpl implements IKnowledgeFragmentService {
|
||||
public Boolean updateByBo(KnowledgeFragmentBo bo) {
|
||||
KnowledgeFragment update = MapstructUtils.convert(bo, KnowledgeFragment.class);
|
||||
validEntityBeforeSave(update);
|
||||
return baseMapper.updateById(update) > 0;
|
||||
boolean updated = baseMapper.updateById(update) > 0;
|
||||
if (updated && update.getKnowledgeId() != null) {
|
||||
knowledgeRetrievalService.invalidateKnowledge(String.valueOf(update.getKnowledgeId()));
|
||||
}
|
||||
return updated;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -136,6 +141,14 @@ public class KnowledgeFragmentServiceImpl implements IKnowledgeFragmentService {
|
||||
if(isValid){
|
||||
//TODO 做一些业务上的校验,判断是否需要校验
|
||||
}
|
||||
// 删除 DB 片段前,同步删除向量库中对应向量
|
||||
List<KnowledgeFragment> fragments = baseMapper.selectByIds(ids);
|
||||
for (KnowledgeFragment fragment : fragments) {
|
||||
if (StringUtils.isNotBlank(fragment.getFid()) && fragment.getKnowledgeId() != null) {
|
||||
vectorStoreService.removeByFid(fragment.getFid(), String.valueOf(fragment.getKnowledgeId()));
|
||||
knowledgeRetrievalService.invalidateKnowledge(String.valueOf(fragment.getKnowledgeId()));
|
||||
}
|
||||
}
|
||||
return baseMapper.deleteByIds(ids) > 0;
|
||||
}
|
||||
|
||||
|
||||
@@ -16,6 +16,10 @@ import org.ruoyi.mapper.knowledge.KnowledgeAttachMapper;
|
||||
import org.ruoyi.mapper.knowledge.KnowledgeInfoMapper;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeInfoService;
|
||||
import org.springframework.stereotype.Service;
|
||||
import org.springframework.transaction.annotation.Transactional;
|
||||
import org.ruoyi.service.retrieval.KnowledgeRetrievalService;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.common.core.service.OssService;
|
||||
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
@@ -36,6 +40,12 @@ public class KnowledgeInfoServiceImpl implements IKnowledgeInfoService {
|
||||
|
||||
private final KnowledgeAttachMapper knowledgeAttachMapper;
|
||||
|
||||
private final org.ruoyi.mapper.knowledge.KnowledgeFragmentMapper knowledgeFragmentMapper;
|
||||
|
||||
private final org.ruoyi.service.vector.VectorStoreService vectorStoreService;
|
||||
private final KnowledgeRetrievalService knowledgeRetrievalService;
|
||||
private final OssService ossService;
|
||||
|
||||
/**
|
||||
* 查询知识库
|
||||
*
|
||||
@@ -97,10 +107,14 @@ public class KnowledgeInfoServiceImpl implements IKnowledgeInfoService {
|
||||
*/
|
||||
private void fillDocumentCount(List<KnowledgeInfoVo> records) {
|
||||
if (records == null || records.isEmpty()) return;
|
||||
for (KnowledgeInfoVo vo : records) {
|
||||
int count = knowledgeAttachMapper.countByKnowledgeId(vo.getId());
|
||||
vo.setDocumentCount(count);
|
||||
List<Long> ids = records.stream().map(KnowledgeInfoVo::getId).toList();
|
||||
Map<Long, Integer> counts = new java.util.HashMap<>();
|
||||
for (Map<String, Object> row : knowledgeAttachMapper.countByKnowledgeIds(ids)) {
|
||||
Number kid = (Number) (row.get("knowledgeId") != null ? row.get("knowledgeId") : row.get("knowledgeid"));
|
||||
Number count = (Number) (row.get("documentCount") != null ? row.get("documentCount") : row.get("documentcount"));
|
||||
if (kid != null && count != null) counts.put(kid.longValue(), count.intValue());
|
||||
}
|
||||
records.forEach(vo -> vo.setDocumentCount(counts.getOrDefault(vo.getId(), 0)));
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -130,13 +144,20 @@ public class KnowledgeInfoServiceImpl implements IKnowledgeInfoService {
|
||||
public Boolean updateByBo(KnowledgeInfoBo bo) {
|
||||
KnowledgeInfo update = MapstructUtils.convert(bo, KnowledgeInfo.class);
|
||||
validEntityBeforeSave(update);
|
||||
return baseMapper.updateById(update) > 0;
|
||||
boolean updated = baseMapper.updateById(update) > 0;
|
||||
if (updated) knowledgeRetrievalService.invalidateKnowledge(String.valueOf(bo.getId()));
|
||||
return updated;
|
||||
}
|
||||
|
||||
/**
|
||||
* 保存前的数据校验
|
||||
*/
|
||||
private void validEntityBeforeSave(KnowledgeInfo entity){
|
||||
int blockSize = entity.getTextBlockSize() == null
|
||||
? DocumentSplitConfig.DEFAULT_BLOCK_SIZE : entity.getTextBlockSize().intValue();
|
||||
int overlap = entity.getOverlapChar() == null
|
||||
? DocumentSplitConfig.DEFAULT_OVERLAP : entity.getOverlapChar().intValue();
|
||||
new DocumentSplitConfig(entity.getSeparator(), blockSize, overlap, "");
|
||||
//TODO 做一些数据校验,如唯一约束
|
||||
}
|
||||
|
||||
@@ -148,10 +169,33 @@ public class KnowledgeInfoServiceImpl implements IKnowledgeInfoService {
|
||||
* @return 是否删除成功
|
||||
*/
|
||||
@Override
|
||||
@Transactional(rollbackFor = Exception.class)
|
||||
public Boolean deleteWithValidByIds(Collection<Long> ids, Boolean isValid) {
|
||||
if(isValid){
|
||||
//TODO 做一些业务上的校验,判断是否需要校验
|
||||
}
|
||||
for (Long kid : ids) {
|
||||
KnowledgeInfo info = baseMapper.selectById(kid);
|
||||
// 1. 删除向量库中该知识库的所有向量(按文档逐个清理,三种向量库行为一致)
|
||||
List<org.ruoyi.domain.entity.knowledge.KnowledgeAttach> attaches = knowledgeAttachMapper.selectList(
|
||||
Wrappers.lambdaQuery(org.ruoyi.domain.entity.knowledge.KnowledgeAttach.class)
|
||||
.eq(org.ruoyi.domain.entity.knowledge.KnowledgeAttach::getKnowledgeId, kid));
|
||||
vectorStoreService.removeById(String.valueOf(kid), info == null ? null : info.getVectorModel());
|
||||
List<Long> ossIds = attaches.stream()
|
||||
.map(org.ruoyi.domain.entity.knowledge.KnowledgeAttach::getOssId)
|
||||
.filter(java.util.Objects::nonNull).toList();
|
||||
if (!ossIds.isEmpty()) {
|
||||
for (Long ossId : ossIds) {
|
||||
ossService.deleteFile(ossId);
|
||||
}
|
||||
}
|
||||
// 2. 删除该知识库下的附件与片段记录
|
||||
knowledgeAttachMapper.delete(Wrappers.lambdaQuery(org.ruoyi.domain.entity.knowledge.KnowledgeAttach.class)
|
||||
.eq(org.ruoyi.domain.entity.knowledge.KnowledgeAttach::getKnowledgeId, kid));
|
||||
knowledgeFragmentMapper.delete(Wrappers.lambdaQuery(org.ruoyi.domain.entity.knowledge.KnowledgeFragment.class)
|
||||
.eq(org.ruoyi.domain.entity.knowledge.KnowledgeFragment::getKnowledgeId, kid));
|
||||
knowledgeRetrievalService.invalidateKnowledge(String.valueOf(kid));
|
||||
}
|
||||
return baseMapper.deleteByIds(ids) > 0;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -3,13 +3,16 @@ package org.ruoyi.service.knowledge.impl.loader;
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.ruoyi.common.core.exception.ServiceException;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.io.BufferedReader;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.util.List;
|
||||
|
||||
@Component
|
||||
@@ -21,20 +24,20 @@ public class CodeFileLoader implements ResourceLoader {
|
||||
@Override
|
||||
public String getContent(InputStream inputStream) {
|
||||
StringBuffer stringBuffer = new StringBuffer();
|
||||
try (InputStreamReader reader = new InputStreamReader(inputStream);
|
||||
try (InputStreamReader reader = new InputStreamReader(inputStream, StandardCharsets.UTF_8);
|
||||
BufferedReader bufferedReader = new BufferedReader(reader)) {
|
||||
String line;
|
||||
while ((line = bufferedReader.readLine()) != null) {
|
||||
stringBuffer.append(line).append("\n");
|
||||
}
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
throw new ServiceException("读取代码文件失败", e);
|
||||
}
|
||||
return stringBuffer.toString();
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
return textSplitter.split(content, kid);
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return textSplitter.split(content, config);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package org.ruoyi.service.knowledge.impl.loader;
|
||||
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
|
||||
import java.io.InputStream;
|
||||
import java.util.List;
|
||||
@@ -12,7 +13,7 @@ public class CsvFileLoader implements ResourceLoader {
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@ import dev.langchain4j.data.document.parser.apache.tika.ApacheTikaDocumentParser
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
@@ -38,7 +39,7 @@ public class ExcelFileLoader implements ResourceLoader {
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
return textSplitter.split(content, kid);
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return textSplitter.split(content, config);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package org.ruoyi.service.knowledge.impl.loader;
|
||||
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
|
||||
import java.io.InputStream;
|
||||
import java.util.List;
|
||||
@@ -12,7 +13,7 @@ public class FolderLoader implements ResourceLoader {
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package org.ruoyi.service.knowledge.impl.loader;
|
||||
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
|
||||
import java.io.InputStream;
|
||||
import java.util.List;
|
||||
@@ -12,7 +13,7 @@ public class GithubLoader implements ResourceLoader {
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package org.ruoyi.service.knowledge.impl.loader;
|
||||
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
|
||||
import java.io.InputStream;
|
||||
import java.util.List;
|
||||
@@ -12,7 +13,7 @@ public class JsonFileLoader implements ResourceLoader {
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -3,13 +3,16 @@ package org.ruoyi.service.knowledge.impl.loader;
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.ruoyi.common.core.exception.ServiceException;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.io.BufferedReader;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.util.List;
|
||||
|
||||
@Component
|
||||
@@ -21,20 +24,20 @@ public class MarkDownFileLoader implements ResourceLoader {
|
||||
@Override
|
||||
public String getContent(InputStream inputStream) {
|
||||
StringBuffer stringBuffer = new StringBuffer();
|
||||
try (InputStreamReader reader = new InputStreamReader(inputStream);
|
||||
try (InputStreamReader reader = new InputStreamReader(inputStream, StandardCharsets.UTF_8);
|
||||
BufferedReader bufferedReader = new BufferedReader(reader)) {
|
||||
String line;
|
||||
while ((line = bufferedReader.readLine()) != null) {
|
||||
stringBuffer.append(line).append("\n");
|
||||
}
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
throw new ServiceException("读取 Markdown 文件失败", e);
|
||||
}
|
||||
return stringBuffer.toString();
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
return textSplitter.split(content, kid);
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return textSplitter.split(content, config);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@ import org.apache.pdfbox.io.RandomAccessReadBuffer;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.text.PDFTextStripper;
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
@@ -32,7 +33,7 @@ public class PdfFileLoader implements ResourceLoader {
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
return characterTextSplitter.split(content, kid);
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return characterTextSplitter.split(content, config);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -3,7 +3,9 @@ package org.ruoyi.service.knowledge.impl.loader;
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.ruoyi.common.core.exception.ServiceException;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.io.BufferedReader;
|
||||
@@ -22,18 +24,16 @@ public class TextFileLoader implements ResourceLoader {
|
||||
|
||||
@Override
|
||||
public String getContent(InputStream inputStream) {
|
||||
String stringBuffer = "";
|
||||
try (InputStreamReader reader = new InputStreamReader(inputStream, StandardCharsets.UTF_8);
|
||||
BufferedReader bufferedReader = new BufferedReader(reader)) {
|
||||
stringBuffer = bufferedReader.lines().collect(Collectors.joining());
|
||||
return bufferedReader.lines().collect(Collectors.joining("\n"));
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
throw new ServiceException("读取文本文件失败", e);
|
||||
}
|
||||
return stringBuffer;
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
return textSplitter.split(content, kid);
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return textSplitter.split(content, config);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -5,6 +5,7 @@ import lombok.extern.slf4j.Slf4j;
|
||||
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
|
||||
import org.apache.poi.xwpf.usermodel.XWPFDocument;
|
||||
import org.ruoyi.service.knowledge.ResourceLoader;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
@@ -32,8 +33,8 @@ public class WordLoader implements ResourceLoader {
|
||||
}
|
||||
|
||||
@Override
|
||||
public List<String> getChunkList(String content, String kid) {
|
||||
return textSplitter.split(content, kid);
|
||||
public List<String> getChunkList(String content, DocumentSplitConfig config) {
|
||||
return textSplitter.split(content, config);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -1,82 +1,17 @@
|
||||
package org.ruoyi.service.knowledge.impl.split;
|
||||
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.common.core.utils.StringUtils;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeInfoVo;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeInfoService;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.springframework.context.annotation.Primary;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
|
||||
@Component
|
||||
@Slf4j
|
||||
@Primary
|
||||
@AllArgsConstructor
|
||||
public class CharacterTextSplitter implements TextSplitter {
|
||||
|
||||
private final IKnowledgeInfoService knowledgeInfoService;
|
||||
|
||||
@Override
|
||||
public List<String> split(String content, String kid) {
|
||||
// 默认配置值
|
||||
String knowledgeSeparator = "#";
|
||||
int textBlockSize = 1000;
|
||||
int overlapChar = 50;
|
||||
|
||||
// 根据知识库ID查询配置,覆盖默认值
|
||||
if (StringUtils.isNotBlank(kid)) {
|
||||
try {
|
||||
KnowledgeInfoVo info = knowledgeInfoService.queryById(Long.parseLong(kid));
|
||||
if (info != null) {
|
||||
if (StringUtils.isNotBlank(info.getSeparator())) {
|
||||
knowledgeSeparator = info.getSeparator();
|
||||
}
|
||||
if (info.getTextBlockSize() != null && info.getTextBlockSize() > 0) {
|
||||
textBlockSize = info.getTextBlockSize().intValue();
|
||||
}
|
||||
if (info.getOverlapChar() != null && info.getOverlapChar() > 0) {
|
||||
overlapChar = info.getOverlapChar().intValue();
|
||||
}
|
||||
}
|
||||
} catch (Exception e) {
|
||||
log.warn("查询知识库配置失败,使用默认配置, kid={}", kid, e);
|
||||
}
|
||||
}
|
||||
|
||||
List<String> chunkList = new ArrayList<>();
|
||||
if (content.contains(knowledgeSeparator) && StringUtils.isNotBlank(knowledgeSeparator)) {
|
||||
// 按自定义分隔符切分
|
||||
String[] chunks = content.split(knowledgeSeparator);
|
||||
chunkList.addAll(Arrays.asList(chunks));
|
||||
} else {
|
||||
int indexMin = 0;
|
||||
int len = content.length();
|
||||
int i = 0;
|
||||
int right = 0;
|
||||
while (true) {
|
||||
if (len > right) {
|
||||
int begin = i * textBlockSize - overlapChar;
|
||||
if (begin < indexMin) {
|
||||
begin = indexMin;
|
||||
}
|
||||
int end = textBlockSize * (i + 1) + overlapChar;
|
||||
if (end > len) {
|
||||
end = len;
|
||||
}
|
||||
String chunk = content.substring(begin, end);
|
||||
chunkList.add(chunk);
|
||||
i++;
|
||||
right = right + textBlockSize;
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
return chunkList;
|
||||
public List<String> split(String content, DocumentSplitConfig config) {
|
||||
return SplitterSupport.split(content, config, SplitterSupport::paragraphs);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,18 +1,15 @@
|
||||
package org.ruoyi.service.knowledge.impl.split;
|
||||
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
@Component
|
||||
@AllArgsConstructor
|
||||
@Slf4j
|
||||
public class CodeTextSplitter implements TextSplitter {
|
||||
@Override
|
||||
public List<String> split(String content, String kid) {
|
||||
return null;
|
||||
public List<String> split(String content, DocumentSplitConfig config) {
|
||||
return SplitterSupport.split(content, config, SplitterSupport::paragraphs);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,79 +1,15 @@
|
||||
package org.ruoyi.service.knowledge.impl.split;
|
||||
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.common.core.utils.StringUtils;
|
||||
import org.ruoyi.domain.vo.knowledge.KnowledgeInfoVo;
|
||||
import org.ruoyi.service.knowledge.IKnowledgeInfoService;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
|
||||
@Component
|
||||
@AllArgsConstructor
|
||||
@Slf4j
|
||||
public class ExcelTextSplitter implements TextSplitter {
|
||||
|
||||
private final IKnowledgeInfoService knowledgeInfoService;
|
||||
|
||||
@Override
|
||||
public List<String> split(String content, String kid) {
|
||||
// 默认配置
|
||||
String knowledgeSeparator = "#";
|
||||
int textBlockSize = 1000;
|
||||
int overlapChar = 50;
|
||||
|
||||
// 根据知识库ID查询配置,覆盖默认值
|
||||
if (StringUtils.isNotBlank(kid)) {
|
||||
try {
|
||||
KnowledgeInfoVo info = knowledgeInfoService.queryById(Long.parseLong(kid));
|
||||
if (info != null) {
|
||||
if (StringUtils.isNotBlank(info.getSeparator())) {
|
||||
knowledgeSeparator = info.getSeparator();
|
||||
}
|
||||
if (info.getTextBlockSize() != null && info.getTextBlockSize() > 0) {
|
||||
textBlockSize = info.getTextBlockSize().intValue();
|
||||
}
|
||||
if (info.getOverlapChar() != null && info.getOverlapChar() > 0) {
|
||||
overlapChar = info.getOverlapChar().intValue();
|
||||
}
|
||||
}
|
||||
} catch (Exception e) {
|
||||
log.warn("查询知识库配置失败,使用默认配置, kid={}", kid, e);
|
||||
}
|
||||
}
|
||||
List<String> chunkList = new ArrayList<>();
|
||||
if (content.contains(knowledgeSeparator) && StringUtils.isNotBlank(knowledgeSeparator)) {
|
||||
// 按自定义分隔符切分
|
||||
String[] chunks = content.split(knowledgeSeparator);
|
||||
chunkList.addAll(Arrays.asList(chunks));
|
||||
} else {
|
||||
int indexMin = 0;
|
||||
int len = content.length();
|
||||
int i = 0;
|
||||
int right = 0;
|
||||
while (true) {
|
||||
if (len > right) {
|
||||
int begin = i * textBlockSize - overlapChar;
|
||||
if (begin < indexMin) {
|
||||
begin = indexMin;
|
||||
}
|
||||
int end = textBlockSize * (i + 1) + overlapChar;
|
||||
if (end > len) {
|
||||
end = len;
|
||||
}
|
||||
String chunk = content.substring(begin, end);
|
||||
chunkList.add(chunk);
|
||||
i++;
|
||||
right = right + textBlockSize;
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
return chunkList;
|
||||
public List<String> split(String content, DocumentSplitConfig config) {
|
||||
return SplitterSupport.split(content, config, SplitterSupport::lines);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,18 +1,56 @@
|
||||
package org.ruoyi.service.knowledge.impl.split;
|
||||
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
@Component
|
||||
@AllArgsConstructor
|
||||
@Slf4j
|
||||
public class MarkdownTextSplitter implements TextSplitter {
|
||||
@Override
|
||||
public List<String> split(String content, String kid) {
|
||||
return null;
|
||||
public List<String> split(String content, DocumentSplitConfig config) {
|
||||
return SplitterSupport.split(content, config, this::sections);
|
||||
}
|
||||
|
||||
/** Split headings without treating heading-looking lines inside fenced code as headings. */
|
||||
private List<String> sections(String markdown) {
|
||||
String[] lines = markdown.split("\\n", -1);
|
||||
List<String> sections = new ArrayList<>();
|
||||
StringBuilder current = new StringBuilder();
|
||||
boolean fenced = false;
|
||||
String fenceMarker = null;
|
||||
for (int i = 0; i < lines.length; i++) {
|
||||
String line = lines[i];
|
||||
String trimmed = line.stripLeading();
|
||||
if (trimmed.startsWith("```") || trimmed.startsWith("~~~")) {
|
||||
String marker = trimmed.substring(0, 3);
|
||||
if (!fenced) {
|
||||
fenced = true;
|
||||
fenceMarker = marker;
|
||||
} else if (marker.equals(fenceMarker)) {
|
||||
fenced = false;
|
||||
fenceMarker = null;
|
||||
}
|
||||
}
|
||||
boolean atx = !fenced && line.matches("^#{1,6}(\\s+.*)?$");
|
||||
boolean setextTitle = !fenced && i + 1 < lines.length
|
||||
&& lines[i + 1].matches("^\\s*(=+|-+)\\s*$") && !line.isBlank();
|
||||
if ((atx || setextTitle) && current.length() > 0) flush(sections, current);
|
||||
current.append(line);
|
||||
if (i < lines.length - 1) current.append('\n');
|
||||
if (setextTitle) {
|
||||
current.append(lines[++i]);
|
||||
if (i < lines.length - 1) current.append('\n');
|
||||
}
|
||||
}
|
||||
flush(sections, current);
|
||||
return sections;
|
||||
}
|
||||
|
||||
private static void flush(List<String> sections, StringBuilder current) {
|
||||
if (!current.toString().isBlank()) sections.add(current.toString());
|
||||
current.setLength(0);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,67 @@
|
||||
package org.ruoyi.service.knowledge.impl.split;
|
||||
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.util.function.Function;
|
||||
import java.util.regex.Pattern;
|
||||
|
||||
/** Shared, deterministic split pipeline used by every supported document format. */
|
||||
public final class SplitterSupport {
|
||||
private SplitterSupport() {}
|
||||
|
||||
public static List<String> split(String content, DocumentSplitConfig config,
|
||||
Function<String, List<String>> naturalSections) {
|
||||
if (content == null || content.isBlank()) return List.of();
|
||||
String normalized = content.replace("\r\n", "\n").replace('\r', '\n');
|
||||
List<String> primary = literalSections(normalized, config.separator());
|
||||
List<String> result = new ArrayList<>();
|
||||
for (String part : primary) {
|
||||
List<String> sections = naturalSections.apply(part);
|
||||
String joined = sections.stream().filter(s -> s != null && !s.isBlank())
|
||||
.map(String::strip).reduce((a, b) -> a + "\n\n" + b).orElse("");
|
||||
result.addAll(slidingWindow(joined, config.blockSize(), config.overlap()));
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
static List<String> literalSections(String content, String separator) {
|
||||
if (separator == null || separator.isEmpty() || !content.contains(separator)) return List.of(content);
|
||||
List<String> parts = new ArrayList<>();
|
||||
for (String part : content.split(Pattern.quote(separator), -1)) {
|
||||
if (!part.isBlank()) parts.add(part);
|
||||
}
|
||||
return parts;
|
||||
}
|
||||
|
||||
/** blockSize is a strict maximum; overlap is the repeated suffix/prefix length. */
|
||||
public static List<String> slidingWindow(String content, int blockSize, int overlap) {
|
||||
if (content == null || content.isBlank()) return List.of();
|
||||
String value = content.strip();
|
||||
List<String> chunks = new ArrayList<>();
|
||||
int step = blockSize - overlap;
|
||||
for (int start = 0; start < value.length(); start += step) {
|
||||
int end = Math.min(value.length(), start + blockSize);
|
||||
String chunk = value.substring(start, end).strip();
|
||||
if (!chunk.isEmpty()) chunks.add(chunk);
|
||||
if (end == value.length()) break;
|
||||
}
|
||||
return chunks;
|
||||
}
|
||||
|
||||
/** Compatibility helper retained for callers/tests; now enforces strict maximum size. */
|
||||
public static List<String> mergeAndSplit(String[] sections, int blockSize, int overlap) {
|
||||
return split(String.join("\n\n", sections),
|
||||
new DocumentSplitConfig(null, blockSize, overlap, ""),
|
||||
text -> List.of(text));
|
||||
}
|
||||
|
||||
static List<String> paragraphs(String content) {
|
||||
return List.of(content.split("\\n\\s*\\n+"));
|
||||
}
|
||||
|
||||
static List<String> lines(String content) {
|
||||
return List.of(content.split("\\n+"));
|
||||
}
|
||||
}
|
||||
@@ -3,6 +3,7 @@ package org.ruoyi.service.knowledge.impl.split;
|
||||
import lombok.AllArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
import org.ruoyi.service.knowledge.TextSplitter;
|
||||
import org.ruoyi.service.knowledge.DocumentSplitConfig;
|
||||
import org.springframework.stereotype.Component;
|
||||
|
||||
import java.util.List;
|
||||
@@ -12,7 +13,7 @@ import java.util.List;
|
||||
@Slf4j
|
||||
public class TokenTextSplitter implements TextSplitter {
|
||||
@Override
|
||||
public List<String> split(String content, String kid) {
|
||||
return null;
|
||||
public List<String> split(String content, DocumentSplitConfig config) {
|
||||
return SplitterSupport.split(content, config, SplitterSupport::paragraphs);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package org.ruoyi.service.knowledge.retriever;
|
||||
|
||||
import dev.langchain4j.data.segment.TextSegment;
|
||||
import dev.langchain4j.data.document.Metadata;
|
||||
import dev.langchain4j.rag.content.Content;
|
||||
import dev.langchain4j.rag.content.retriever.ContentRetriever;
|
||||
import dev.langchain4j.rag.query.Query;
|
||||
@@ -55,11 +56,17 @@ public class CustomVectorRetriever implements ContentRetriever {
|
||||
queryVectorBo.setRerankScoreThreshold(knowledgeInfoVo.getRerankScoreThreshold());
|
||||
|
||||
// 通过统一服务执行检索
|
||||
List<String> nearestList = knowledgeRetrievalService.retrieveTexts(queryVectorBo);
|
||||
var nearestList = knowledgeRetrievalService.retrieve(queryVectorBo);
|
||||
|
||||
// 将结果包装为标准的 Content 返回
|
||||
return nearestList.stream()
|
||||
.map(text -> Content.from(TextSegment.from(text)))
|
||||
.map(vo -> {
|
||||
Metadata metadata = new Metadata();
|
||||
metadata.put("kid", String.valueOf(knowledgeInfoVo.getId()));
|
||||
metadata.put("docId", Objects.toString(vo.getDocId(), ""));
|
||||
metadata.put("fid", Objects.toString(vo.getId(), ""));
|
||||
return Content.from(TextSegment.from(vo.getContent(), metadata));
|
||||
})
|
||||
.collect(Collectors.toList());
|
||||
}
|
||||
}
|
||||
|
||||
@@ -23,6 +23,7 @@ import java.util.concurrent.TimeUnit;
|
||||
*/
|
||||
@Slf4j
|
||||
@Component("qianwenRerank")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class AliBaiLianRerankModelService implements RerankModelService {
|
||||
|
||||
private final OkHttpClient okHttpClient;
|
||||
|
||||
@@ -25,6 +25,7 @@ import java.util.concurrent.TimeUnit;
|
||||
*/
|
||||
@Slf4j
|
||||
@Component("siliconflowRerank")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class SiliconFlowRerankModelService implements RerankModelService {
|
||||
|
||||
private static final String DEFAULT_BASE_URL = "https://api.siliconflow.cn/v1/rerank";
|
||||
|
||||
@@ -28,6 +28,7 @@ import java.util.concurrent.TimeUnit;
|
||||
*/
|
||||
@Slf4j
|
||||
@Component("zhipuRerank")
|
||||
@org.springframework.context.annotation.Scope("prototype")
|
||||
public class ZhiPuRerankModelService implements RerankModelService {
|
||||
|
||||
private final OkHttpClient okHttpClient;
|
||||
|
||||
@@ -31,4 +31,6 @@ public interface KnowledgeRetrievalService {
|
||||
* @return 检索结果列表
|
||||
*/
|
||||
List<KnowledgeRetrievalVo> retrieve(QueryVectorBo queryVectorBo);
|
||||
|
||||
void invalidateKnowledge(String kid);
|
||||
}
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user