``` refactor(knowledge-base): 重构RAG向量检索功能的文件关联和异步处理

云

10 天以前 f818fa5eca223270f0656e0455c338ec1f2fac88

 src/main/java/com/ruoyi/ai/service/impl/KnowledgeRagServiceImpl.java

@@ -46,13 +46,15 @@
    private static final int CHUNK_OVERLAP = 100;

    @Override
    @Async
    @Async("threadPoolTaskExecutor")
    public void processVectorAsync(Long vectorId) {
        log.info("开始异步向量化处理: vectorId={}, thread={}", vectorId, Thread.currentThread().getName());
        processVector(vectorId);
    }

    @Override
    public void processVector(Long vectorId) {
        log.info("开始处理向量化: vectorId={}", vectorId);
        KnowledgeBaseVector vector = knowledgeBaseVectorService.getById(vectorId);
        if (vector == null) {
            log.error("向量记录不存在: {}", vectorId);
@@ -61,30 +63,38 @@

        try {
            // 更新状态为处理中
            log.info("更新状态为处理中: vectorId={}", vectorId);
            knowledgeBaseVectorService.updateVectorStatus(vectorId,
                    KnowledgeBaseVector.STATUS_PROCESSING, null, null);

            // 获取文件内容
            log.info("获取文件信息: storageBlobId={}", vector.getStorageBlobId());
            StorageBlob blob = storageBlobService.getById(vector.getStorageBlobId());
            if (blob == null) {
                throw new RuntimeException("文件不存在: " + vector.getStorageBlobId());
            }

            File file = getFile(blob);
            log.info("文件路径: {}, 是否存在: {}", file.getAbsolutePath(), file.exists());

            // 直接读取文件内容，不使用 MultipartFile 包装
            log.info("提取文件内容: fileName={}", vector.getFileName());
            String content = extractFileContent(file, vector.getFileName(), blob.getContentType());
            log.info("文件内容长度: {}", content != null ? content.length() : 0);

            if (content == null || content.trim().isEmpty()) {
                throw new RuntimeException("文件内容为空");
            }

            // 文本切片
            log.info("开始文本切片");
            List<TextSegment> chunks = splitText(content, vector);
            log.info("切片完成，共 {} 个块", chunks.size());

            // 批量生成嵌入向量并存储
            int chunkCount = 0;
            for (TextSegment chunk : chunks) {
                log.debug("处理第 {} 个块", chunkCount + 1);
                Embedding embedding = embeddingModel.embed(chunk).content();
                embeddingStore.add(embedding, chunk);
                chunkCount++;