Version: 0.9.65.dev.260503

后端:
1. 阶段 1.5/1.6
收口 llm-service / rag-service,统一模型出口与检索基础设施入口,清退 backend/infra/llm 与 backend/infra/rag 旧实现;
2. 同步更新相关调用链与微服务迁移计划文档
This commit is contained in:
Losita
2026-05-03 23:21:03 +08:00
parent a6c1e5d077
commit 9902ca3563
65 changed files with 550 additions and 376 deletions

View File

@@ -0,0 +1,85 @@
package chunk
import (
"context"
"fmt"
"strings"
"github.com/LoveLosita/smartflow/backend/services/rag/core"
)
// TextChunker 是默认文本切块器。
type TextChunker struct{}
func NewTextChunker() *TextChunker {
return &TextChunker{}
}
// Chunk 对文本执行固定窗口切块。
//
// 步骤化说明:
// 1. 先做空白归一,避免无效块进入向量库;
// 2. 再按 chunk_size/overlap 滑窗切割;
// 3. 每块继承原文 metadata并补充 chunk 序号。
func (c *TextChunker) Chunk(_ context.Context, doc core.SourceDocument, opt core.ChunkOption) ([]core.Chunk, error) {
if strings.TrimSpace(doc.ID) == "" {
return nil, fmt.Errorf("empty document id")
}
text := strings.TrimSpace(doc.Text)
if text == "" {
return nil, nil
}
if opt.ChunkSize <= 0 {
opt.ChunkSize = 400
}
if opt.ChunkOverlap < 0 {
opt.ChunkOverlap = 0
}
if opt.ChunkOverlap >= opt.ChunkSize {
opt.ChunkOverlap = opt.ChunkSize / 5
}
runes := []rune(text)
step := opt.ChunkSize - opt.ChunkOverlap
if step <= 0 {
step = opt.ChunkSize
}
result := make([]core.Chunk, 0, len(runes)/step+1)
order := 0
for start := 0; start < len(runes); start += step {
end := start + opt.ChunkSize
if end > len(runes) {
end = len(runes)
}
chunkText := strings.TrimSpace(string(runes[start:end]))
if chunkText == "" {
continue
}
metadata := cloneMap(doc.Metadata)
metadata["chunk_order"] = order
result = append(result, core.Chunk{
ID: fmt.Sprintf("%s#%d", doc.ID, order),
DocumentID: doc.ID,
Text: chunkText,
Order: order,
Metadata: metadata,
})
order++
if end == len(runes) {
break
}
}
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
}