fae162162a
后端： 1. Memory Day1 链路打通（chat_history -> outbox -> memory_jobs） - 更新 service/events/chat_history_persist.go：聊天消息落库同事务追加 memory.extract.requested 事件（仅 user 消息，失败回滚后由 outbox 重试） - 新建 service/events/memory_extract_requested.go：消费 memory.extract.requested 并幂等入队 memory_jobs，补齐 payload 校验、文本截断与 idempotency key - 更新 cmd/start.go：注册 RegisterMemoryExtractRequestedHandler 2. Memory 模块骨架落地（先跑通状态机，再接入真实抽取） - 新建 memory/model、repo、service、orchestrator、worker、utils 目录与 Day1 mock 抽取执行链 - 新建 model/memory.go：补齐 memory_items / memory_jobs / memory_audit_logs / memory_user_settings 与事件 payload 模型 - 更新 inits/mysql.go：接入 4 张 memory 相关表 AutoMigrate 3. RAG 复用基础设施预埋（依赖可替换） - 新建 infra/rag：core pipeline + chunk/embed/retrieve/rerank/store/corpus/config 分层实现 - 默认接入 MockEmbedder + InMemoryStore，预留 Milvus / Eino 适配实现 - 新增 infra/rag/RAG复用接口实施计划.md 4. 本地依赖与交接文档同步 - 更新 docker-compose.yml：新增 etcd / minio / milvus / attu 服务与数据卷 - 删除 newAgent/HANDOFF_工具研究与运行态重置.md、newAgent/阶段3_上下文瘦身设计.md - 新增 newAgent/HANDOFF_WebSearch两阶段实施计划.md、memory/HANDOFF-RAG复用后续实施计划.md、memory/README.md 前端：无 仓库：无
91 lines
1.9 KiB
Go
91 lines
1.9 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) ([]core.ScoredChunk, error) {
|
||
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)
|
||
}
|