feat: 集成 AI-Core gRPC 文档解析服务

- 新增 AICoreClient 客户端 - 添加 document_parser_client.go - 知识库服务集成 AI-Core 解析 - 配置中添加 ai_core_service_addr Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 12:50:27 +08:00
parent 0d4fd6b425
commit dc1c825d2e
8 changed files with 227 additions and 17 deletions
--- a/server/cmd/api/main.go
+++ b/server/cmd/api/main.go
@@ -87,7 +87,7 @@ func main() {
 	if err != nil {
 		log.Printf("Warning: Failed to initialize upload service: %v (files will not be available)", err)
 	}
-	knowledgeService := service.NewKnowledgeService(knowledgeRepo, modelRepo, uploadService, cfg.PythonServiceURL)
+	knowledgeService := service.NewKnowledgeService(knowledgeRepo, modelRepo, uploadService, cfg.PythonServiceURL, cfg.AICoreServiceAddr)

 	// 6. 初始化 Handler
 	dbHandler := handler.NewDatabaseHandler(dbService)
--- a/server/config/config.yaml
+++ b/server/config/config.yaml
@@ -1,9 +1,17 @@
 # 本地开发配置
 port: "8082"
 jwt_secret: "dev-secret-key"
-# Docker 内访问用 db:3306，本地访问用 localhost:6036
-database_url: "root:root@tcp(localhost:6036)/x_agents?charset=utf8mb4&parseTime=True&loc=Local"
+
+# 数据库配置
+database_host: "localhost"
+database_port: "6036"
+database_user: "root"
+database_password: "root"
+database_name: "x_agents"
+
+# AI 服务配置
 python_service_url: "http://localhost:8081"
+ai_core_service_addr: "localhost:50051"

 # 文件上传配置 (local 或 minio)
 upload_mode: "local"
--- a/server/go.mod
+++ b/server/go.mod
@@ -70,7 +70,9 @@ require (
 	golang.org/x/net v0.48.0 // indirect
 	golang.org/x/sys v0.39.0 // indirect
 	golang.org/x/text v0.32.0 // indirect
-	google.golang.org/protobuf v1.31.0 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20251202230838-ff82c1b0f217 // indirect
+	google.golang.org/grpc v1.79.2 // indirect
+	google.golang.org/protobuf v1.36.10 // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )
--- a/server/go.sum
+++ b/server/go.sum
@@ -44,6 +44,7 @@ github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
 github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
 github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/uuid v1.5.0 h1:1p67kYwdtXjb0gL0BPiP1Av9wiZPo5A8z2cWkTZ+eyU=
 github.com/google/uuid v1.5.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@@ -185,9 +186,16 @@ golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/text v0.32.0 h1:ZD01bjUt1FQ9WJ0ClOL5vxgxOI/sVCNgX1YtKwcY0mU=
 golang.org/x/text v0.32.0/go.mod h1:o/rUWzghvpD5TXrTIBuJU77MTaN0ljMWE47kxGJQ7jY=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/genproto v0.0.0-20231106174013-bbf56f31fb17 h1:wpZ8pe2x1Q3f2KyT5f8oP/fa9rHAKgFPr/HZdNuS+PQ=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20251202230838-ff82c1b0f217 h1:gRkg/vSppuSQoDjxyiGfN4Upv/h/DQmIR10ZU8dh4Ww=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20251202230838-ff82c1b0f217/go.mod h1:7i2o+ce6H/6BluujYR+kqX3GKH+dChPTQU19wjRPiGk=
+google.golang.org/grpc v1.79.2 h1:fRMD94s2tITpyJGtBBn7MkMseNpOZU8ZxgC3MMBaXRU=
+google.golang.org/grpc v1.79.2/go.mod h1:KmT0Kjez+0dde/v2j9vzwoAScgEPx/Bw1CYChhHLrHQ=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.31.0 h1:g0LDEJHgrBl9N9r17Ru3sqWhkIx2NB67okBHPwC7hs8=
 google.golang.org/protobuf v1.31.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+google.golang.org/protobuf v1.36.10 h1:AYd7cD/uASjIL6Q9LiTjz8JLcrh/88q5UObnmY3aOOE=
+google.golang.org/protobuf v1.36.10/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo=
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
--- a/server/internal/config/config.go
+++ b/server/internal/config/config.go
@@ -14,8 +14,14 @@ import (
 type Config struct {
 	Port              string
 	JWTSecret         string
-	DatabaseURL       string
+	DatabaseHost      string
+	DatabasePort      string
+	DatabaseUser      string
+	DatabasePassword  string
+	DatabaseName      string
+	DatabaseURL       string // 拼接后的完整连接字符串
 	PythonServiceURL  string
+	AICoreServiceAddr string // AI-Core gRPC 服务地址，如 "localhost:50051"
 	// 文件上传配置
 	UploadMode      string // "local" 或 "minio"
 	UploadLocalPath string // 本地存储路径，如 "resource/files"
@@ -39,7 +45,13 @@ func Load() *Config {
 	viper.SetDefault("port", "8080")
 	viper.SetDefault("jwt_secret", "your-secret-key-change-in-production")
 	viper.SetDefault("python_service_url", "http://localhost:8081")
-	viper.SetDefault("database_url", "root:root@tcp(localhost:3306)/x_agents?charset=utf8mb4&parseTime=True&loc=Local")
+	viper.SetDefault("ai_core_service_addr", "localhost:50051")
+	// 数据库默认配置
+	viper.SetDefault("database_host", "localhost")
+	viper.SetDefault("database_port", "3306")
+	viper.SetDefault("database_user", "root")
+	viper.SetDefault("database_password", "root")
+	viper.SetDefault("database_name", "x_agents")
 	// 文件上传默认配置
 	viper.SetDefault("upload_mode", "local")
 	viper.SetDefault("upload_local_path", "resource/files")
@@ -54,11 +66,26 @@ func Load() *Config {
 		log.Printf("Using default config: %v", err)
 	}

+	// 拼接数据库连接字符串
+	dbHost := viper.GetString("database_host")
+	dbPort := viper.GetString("database_port")
+	dbUser := viper.GetString("database_user")
+	dbPassword := viper.GetString("database_password")
+	dbName := viper.GetString("database_name")
+	databaseURL := fmt.Sprintf("%s:%s@tcp(%s:%s)/%s?charset=utf8mb4&parseTime=True&loc=Local",
+		dbUser, dbPassword, dbHost, dbPort, dbName)
+
 	return &Config{
-		Port:             viper.GetString("port"),
-		JWTSecret:        viper.GetString("jwt_secret"),
-		DatabaseURL:      viper.GetString("database_url"),
-		PythonServiceURL: viper.GetString("python_service_url"),
+		Port:              viper.GetString("port"),
+		JWTSecret:         viper.GetString("jwt_secret"),
+		DatabaseURL:       databaseURL,
+		DatabaseHost:      dbHost,
+		DatabasePort:      dbPort,
+		DatabaseUser:      dbUser,
+		DatabasePassword:  dbPassword,
+		DatabaseName:      dbName,
+		PythonServiceURL:  viper.GetString("python_service_url"),
+		AICoreServiceAddr:  viper.GetString("ai_core_service_addr"),
 		// 文件上传配置
 		UploadMode:      viper.GetString("upload_mode"),
 		UploadLocalPath: viper.GetString("upload_local_path"),
--- a/server/internal/model/knowledge_info.go
+++ b/server/internal/model/knowledge_info.go
@@ -87,6 +87,7 @@ type KnowledgeDocument struct {
 	FileKey          string    `json:"file_key" gorm:"type:varchar(500)"`
 	FileURL          string    `json:"file_url" gorm:"type:varchar(500)"`  // 文件访问 URL
 	FileSize         int64     `json:"file_size" gorm:"type:bigint;default:0"`
+	Content          string    `json:"content" gorm:"type:longtext"`        // Markdown 内容（AI-Core 解析结果）
 	Status           string    `json:"status" gorm:"type:varchar(20);default:parsing"` // parsing / parsed / failed
 	ChunkCount       int       `json:"chunk_count" gorm:"default:0"`
 	UploadedAt       time.Time `json:"uploaded_at"`
--- a/server/internal/service/document_parser_client.go
+++ b/server/internal/service/document_parser_client.go
@@ -0,0 +1,132 @@
+package service
+
+import (
+	"context"
+	"fmt"
+	"time"
+
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
+)
+
+// AICoreClient AI-Core 文档解析服务客户端
+type AICoreClient struct {
+	conn    *grpc.ClientConn
+	address string
+}
+
+// ParseResult 解析结果
+type ParseResult struct {
+	Success       bool
+	Content       string
+	Message       string
+	ContentLength int32
+	FileType      string
+	ParserEngine  string
+}
+
+// NewAICoreClient 创建 AI-Core 客户端
+func NewAICoreClient(address string) (*AICoreClient, error) {
+	return &AICoreClient{address: address}, nil
+}
+
+// Connect 连接到 gRPC 服务
+func (c *AICoreClient) Connect() error {
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	conn, err := grpc.DialContext(ctx, c.address,
+		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithBlock(),
+	)
+	if err != nil {
+		return fmt.Errorf("failed to connect to AI-Core service: %w", err)
+	}
+	c.conn = conn
+	return nil
+}
+
+// Close 关闭连接
+func (c *AICoreClient) Close() {
+	if c.conn != nil {
+		c.conn.Close()
+	}
+}
+
+// ParseDocument 解析文档
+func (c *AICoreClient) ParseDocument(fileURL, fileName, fileType string) (*ParseResult, error) {
+	if c.conn == nil {
+		if err := c.Connect(); err != nil {
+			return nil, err
+		}
+	}
+
+	// 使用 gRPC raw bytes 调用
+	// 由于没有生成 protobuf 代码，使用 raw bytes 方式调用
+	client := NewDocumentParserClient(c.conn)
+
+	req := &ParseRequest{
+		FileUrl:  fileURL,
+		FileName: fileName,
+		FileType: fileType,
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
+	defer cancel()
+
+	resp, err := client.ParseDocument(ctx, req)
+	if err != nil {
+		return nil, fmt.Errorf("failed to parse document: %w", err)
+	}
+
+	return &ParseResult{
+		Success:       resp.Success,
+		Content:       resp.Content,
+		Message:       resp.Message,
+		ContentLength: resp.ContentLength,
+		FileType:      resp.FileType,
+		ParserEngine:  resp.ParserEngine,
+	}, nil
+}
+
+// 以下是手动定义的 protobuf messages（与 proto 文件一致）
+// 不需要生成 .pb.go 文件，直接手动定义
+
+type ParseRequest struct {
+	FileUrl       string
+	FileName     string
+	FileType     string
+	ParserEngine string
+}
+
+type ParseResponse struct {
+	Success       bool
+	Content       string
+	Message       string
+	ContentLength int32
+	FileType      string
+	ParserEngine  string
+}
+
+// DocumentParserClient gRPC 客户端接口（手动实现）
+type DocumentParserClient interface {
+	ParseDocument(ctx context.Context, in *ParseRequest, opts ...grpc.CallOption) (*ParseResponse, error)
+}
+
+type documentParserClient struct {
+	cc grpc.ClientConnInterface
+}
+
+// NewDocumentParserClient 创建 DocumentParser 客户端
+func NewDocumentParserClient(cc grpc.ClientConnInterface) DocumentParserClient {
+	return &documentParserClient{cc: cc}
+}
+
+func (c *documentParserClient) ParseDocument(ctx context.Context, in *ParseRequest, opts ...grpc.CallOption) (*ParseResponse, error) {
+	out := new(ParseResponse)
+	err := c.cc.Invoke(ctx, "/docparser.DocumentParser/ParseDocument", in, out, opts...)
+	if err != nil {
+		return nil, err
+	}
+	return out, nil
+}
--- a/server/internal/service/knowledge_service.go
+++ b/server/internal/service/knowledge_service.go
@@ -24,18 +24,21 @@ func init() {
 }

 type KnowledgeService struct {
-	repo            *repository.KnowledgeRepository
-	modelRepo       *repository.ModelRepository
-	uploadService   *UploadService
+	repo             *repository.KnowledgeRepository
+	modelRepo        *repository.ModelRepository
+	uploadService    *UploadService
 	pythonServiceURL string
+	aiCoreClient     *AICoreClient
 }

-func NewKnowledgeService(repo *repository.KnowledgeRepository, modelRepo *repository.ModelRepository, uploadService *UploadService, pythonServiceURL string) *KnowledgeService {
+func NewKnowledgeService(repo *repository.KnowledgeRepository, modelRepo *repository.ModelRepository, uploadService *UploadService, pythonServiceURL, aiCoreServiceAddr string) *KnowledgeService {
+	aiCoreClient, _ := NewAICoreClient(aiCoreServiceAddr)
 	return &KnowledgeService{
-		repo:            repo,
-		modelRepo:       modelRepo,
-		uploadService:   uploadService,
+		repo:             repo,
+		modelRepo:        modelRepo,
+		uploadService:    uploadService,
 		pythonServiceURL: pythonServiceURL,
+		aiCoreClient:     aiCoreClient,
 	}
 }

@@ -227,6 +230,9 @@ func (s *KnowledgeService) UploadDocument(kbID string, file *multipart.FileHeade
 	// 异步调用 Python 服务解析文档
 	go s.parseDocument(kbID, doc.ID, result.URL, kb.ParsingConfig)

+	// 异步调用 AI-Core gRPC 服务解析文档（获取 Markdown）
+	go s.parseDocumentWithAICore(doc.ID, result.URL, doc.Name)
+
 	return doc, result.URL, nil
 }

@@ -284,6 +290,32 @@ func (s *KnowledgeService) parseDocument(kbID, docID, fileURL string, config mod
 	}
 }

+// parseDocumentWithAICore 调用 AI-Core gRPC 服务解析文档
+func (s *KnowledgeService) parseDocumentWithAICore(docID, fileURL, fileName string) {
+	if s.aiCoreClient == nil {
+		knowledgeDebugLog.Printf("[AICore] AI-Core 客户端未初始化")
+		return
+	}
+
+	knowledgeDebugLog.Printf("[AICore] 开始解析文档: docID=%s, fileURL=%s, fileName=%s", docID, fileURL, fileName)
+
+	result, err := s.aiCoreClient.ParseDocument(fileURL, fileName, "")
+	if err != nil {
+		knowledgeDebugLog.Printf("[AICore] 解析失败: docID=%s, err=%v", docID, err)
+		return
+	}
+
+	if result.Success && result.Content != "" {
+		knowledgeDebugLog.Printf("[AICore] 解析成功: docID=%s, contentLength=%d", docID, len(result.Content))
+		// 更新文档的 Content 字段
+		s.repo.UpdateDocument(docID, map[string]interface{}{
+			"content": result.Content,
+		})
+	} else {
+		knowledgeDebugLog.Printf("[AICore] 解析返回失败: docID=%s, message=%s", docID, result.Message)
+	}
+}
+
 // DeleteDocument 删除文档
 func (s *KnowledgeService) DeleteDocument(kbID, docID string) error {
 	// 验证文档存在