feat: Phase 6.6 知识库 RAG 增强 — 文档索引 + 语义检索 + KnowledgeProvider

- rag.Embedder: LLM API 文本向量化 (OpenAI-compatible)
- rag.KnowledgeStore: 文档分块 + 重叠窗口 + 余弦相似度搜索
- rag.Retriever: 高级知识检索 + 格式化摘要
- KnowledgeProvider: 子会话提供者，整合入编排管线
- knowledge_search / knowledge_ingest 工具
- EnrichmentData 管线全线支持 KnowledgeInfo

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend/ai-core/internal/rag/embedder.go

@@ -0,0 +1,118 @@
+package rag
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"time"
+)
+
+// Embedder creates text embeddings using an LLM API.
+type Embedder struct {
+	baseURL    string
+	apiKey     string
+	model      string
+	httpClient *http.Client
+}
+
+// NewEmbedder creates a new embedding service.
+func NewEmbedder(baseURL, apiKey, model string) *Embedder {
+	return &Embedder{
+		baseURL: baseURL,
+		apiKey:  apiKey,
+		model:   model,
+		httpClient: &http.Client{
+			Timeout: 30 * time.Second,
+		},
+	}
+}
+
+type embeddingRequest struct {
+	Input []string `json:"input"`
+	Model string   `json:"model"`
+}
+
+type embeddingResponse struct {
+	Data   []embeddingData `json:"data"`
+	Model  string          `json:"model"`
+	Usage  embeddingUsage  `json:"usage,omitempty"`
+	Error  *embeddingError `json:"error,omitempty"`
+}
+
+type embeddingData struct {
+	Embedding []float64 `json:"embedding"`
+	Index     int       `json:"index"`
+}
+
+type embeddingUsage struct {
+	PromptTokens int `json:"prompt_tokens"`
+	TotalTokens  int `json:"total_tokens"`
+}
+
+type embeddingError struct {
+	Message string `json:"message"`
+	Code    string `json:"code"`
+}
+
+// Embed generates an embedding vector for the given text.
+func (e *Embedder) Embed(ctx context.Context, text string) ([]float64, error) {
+	return e.EmbedBatch(ctx, []string{text})
+}
+
+// EmbedBatch generates embeddings for multiple texts.
+func (e *Embedder) EmbedBatch(ctx context.Context, texts []string) ([]float64, error) {
+	if !e.IsAvailable() {
+		return nil, fmt.Errorf("embedding service not available: no API key configured")
+	}
+
+	reqBody := embeddingRequest{
+		Input: texts,
+		Model: e.model,
+	}
+
+	jsonBody, err := json.Marshal(reqBody)
+	if err != nil {
+		return nil, fmt.Errorf("marshal embedding request: %w", err)
+	}
+
+	req, err := http.NewRequestWithContext(ctx, "POST", e.baseURL+"/embeddings", bytes.NewReader(jsonBody))
+	if err != nil {
+		return nil, fmt.Errorf("create embedding request: %w", err)
+	}
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", "Bearer "+e.apiKey)
+
+	resp, err := e.httpClient.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("embedding request failed: %w", err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return nil, fmt.Errorf("read embedding response: %w", err)
+	}
+
+	var embResp embeddingResponse
+	if err := json.Unmarshal(body, &embResp); err != nil {
+		return nil, fmt.Errorf("parse embedding response: %w", err)
+	}
+
+	if embResp.Error != nil {
+		return nil, fmt.Errorf("embedding API error: %s (code=%s)", embResp.Error.Message, embResp.Error.Code)
+	}
+
+	if len(embResp.Data) == 0 {
+		return nil, fmt.Errorf("no embedding returned")
+	}
+
+	return embResp.Data[0].Embedding, nil
+}
+
+// IsAvailable checks if the embedding service is configured.
+func (e *Embedder) IsAvailable() bool {
+	return e.apiKey != "" && e.baseURL != ""
+}