863cba4e4e
后端： 1. RAG embedding 接入修正，并兼容 Ark 多模态 embedding 链路 - 更新 backend/infra/rag/embed/eino_embedder.go：文本 embedding 继续走 Eino OpenAI 兼容链路；`doubao-embedding-vision-*` 模型切到 Ark 原生 `/embeddings/multimodal` - 增加 embedding baseURL 归一化：兼容把 `.../embeddings` 或 `.../embeddings/multimodal` 误填进配置的情况，统一回退到 `/api/v3` - 为第三方 embedding 调用增加 panic recover，避免向量检索/写入异常直接打崩主进程 2. RAG runtime / pipeline / store 稳定性加固，统一降级为 error 语义 - 更新 backend/infra/rag/runtime.go：runtime 对外入口增加 panic recover 与观测打点 - 更新 backend/infra/rag/core/pipeline.go：ingest / retrieve 编排边界增加 panic recover - 更新 backend/infra/rag/retrieve/vector_retriever.go：向量检索边界补充 panic recover - 更新 backend/infra/rag/store/milvus_store.go、backend/infra/rag/store/inmemory_store.go：补齐未初始化保护，避免 nil 依赖直接异常退出 3. RAG embedding 配置口径与普通 LLM 链路对齐 - 更新 backend/infra/rag/factory.go：RAG embedding API Key 不再走 `apiKeyEnv` 间接映射，统一直接读取 `ARK_API_KEY` - 更新 backend/infra/rag/config/config.go：删除 `rag.embed.apiKeyEnv` 配置字段，收敛配置分叉 - 更新 backend/config.example.yaml：示例配置切到当前联调口径，保持 `rag.enabled=true`、`memory.rag.enabled=true`，并对齐 Milvus / embed 配置 4. Memory + RAG 联调链路可运行态修正 - 当前已验证 memory 抽取写库、RAG ingest 写入 Milvus、后续语义召回链路可继续联调 - 检索失败场景已从“直接 panic”收敛为“记录日志并降级”，不再阻断主聊天链路 前端：无 仓库：无 undo： 1. 增删改查的 mysql 记忆去重没实现 2. 提取用户话为记忆的过滤机制不足，有点无脑 3. RAG 召回也有问题
99 lines
2.0 KiB
Go
99 lines
2.0 KiB
Go
package retrieve
|
||
|
||
import (
|
||
"context"
|
||
"fmt"
|
||
"strings"
|
||
|
||
"github.com/LoveLosita/smartflow/backend/infra/rag/core"
|
||
)
|
||
|
||
// VectorRetriever 是通用检索器（embed + vector search）。
|
||
type VectorRetriever struct {
|
||
embedder core.Embedder
|
||
store core.VectorStore
|
||
}
|
||
|
||
func NewVectorRetriever(embedder core.Embedder, store core.VectorStore) *VectorRetriever {
|
||
return &VectorRetriever{
|
||
embedder: embedder,
|
||
store: store,
|
||
}
|
||
}
|
||
|
||
func (r *VectorRetriever) Retrieve(ctx context.Context, req core.RetrieveRequest) (result []core.ScoredChunk, err error) {
|
||
defer func() {
|
||
recovered := recover()
|
||
if recovered == nil {
|
||
return
|
||
}
|
||
err = fmt.Errorf("vector retriever panic recovered: %v", recovered)
|
||
}()
|
||
|
||
if r == nil || r.embedder == nil || r.store == nil {
|
||
return nil, core.ErrNilDependency
|
||
}
|
||
query := strings.TrimSpace(req.Query)
|
||
if query == "" {
|
||
return nil, core.ErrInvalidQuery
|
||
}
|
||
topK := req.TopK
|
||
if topK <= 0 {
|
||
topK = 8
|
||
}
|
||
action := strings.TrimSpace(req.Action)
|
||
if action == "" {
|
||
action = "search"
|
||
}
|
||
|
||
vectors, err := r.embedder.Embed(ctx, []string{query}, action)
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
if len(vectors) != 1 {
|
||
return nil, fmt.Errorf("embedding query length mismatch: %d", len(vectors))
|
||
}
|
||
|
||
rows, err := r.store.Search(ctx, core.VectorSearchRequest{
|
||
QueryVector: vectors[0],
|
||
TopK: topK,
|
||
Filter: req.Filter,
|
||
})
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
result = make([]core.ScoredChunk, 0, len(rows))
|
||
for _, row := range rows {
|
||
if row.Score < req.Threshold {
|
||
continue
|
||
}
|
||
result = append(result, core.ScoredChunk{
|
||
ChunkID: row.Row.ID,
|
||
DocumentID: asString(row.Row.Metadata["document_id"]),
|
||
Text: row.Row.Text,
|
||
Score: row.Score,
|
||
Metadata: cloneMap(row.Row.Metadata),
|
||
})
|
||
}
|
||
return result, nil
|
||
}
|
||
|
||
func cloneMap(src map[string]any) map[string]any {
|
||
if len(src) == 0 {
|
||
return map[string]any{}
|
||
}
|
||
dst := make(map[string]any, len(src))
|
||
for k, v := range src {
|
||
dst[k] = v
|
||
}
|
||
return dst
|
||
}
|
||
|
||
func asString(v any) string {
|
||
if v == nil {
|
||
return ""
|
||
}
|
||
return fmt.Sprintf("%v", v)
|
||
}
|