build: update dockerfile

Dockerfile

@@ -1,16 +1,22 @@
 # Build stage
-FROM registry.cn-beijing.aliyuncs.com/bitwsd/golang AS builder
+FROM crpi-8s2ierii2xan4klg.cn-beijing.personal.cr.aliyuncs.com/texpixel/golang:1.20-apline AS builder
+
 
 WORKDIR /app
 
 # Copy source code
 COPY . .
 
+ENV GOPROXY=https://goproxy.cn,direct
+ENV GOSUMDB=off
+
+
 # Build binary
-RUN CGO_ENABLED=0 GOOS=linux go build -mod=vendor -o main ./main.go 
+RUN go mod download && \ 
+    CGO_ENABLED=0 GOOS=linux go build -ldflags="-s -w" -o doc_ai ./main.go 
 
 # Runtime stage
-FROM registry.cn-beijing.aliyuncs.com/bitwsd/alpine
+FROM crpi-8s2ierii2xan4klg.cn-beijing.personal.cr.aliyuncs.com/texpixel/alpine:latest
 
 # Set timezone
 RUN apk add --no-cache tzdata && \
@@ -21,7 +27,7 @@ RUN apk add --no-cache tzdata && \
 WORKDIR /app
 
 # Copy binary from builder
-COPY --from=builder /app/main .
+COPY --from=builder /app/doc_ai .
 
 # Copy config files
 COPY config/config_*.yaml ./config/
@@ -34,7 +40,7 @@ RUN mkdir -p /data/formula && \
 EXPOSE 8024
 
 # Set entrypoint
-ENTRYPOINT ["./main"]
+ENTRYPOINT ["./doc_ai"]
 
 # Default command (can be overridden)
 CMD ["-env", "prod"]

api/v1/oss/handler.go

@@ -5,6 +5,7 @@ import (
 	"net/http"
 	"os"
 	"path/filepath"
+	"strings"
 	"time"
 
 	"gitea.com/bitwsd/document_ai/config"
@@ -59,7 +60,7 @@ func GetSignatureURL(ctx *gin.Context) {
 		ctx.JSON(http.StatusOK, common.SuccessResponse(ctx, gin.H{"sign_url": "", "repeat": true, "path": task.FileURL}))
 		return
 	}
-	extend := filepath.Ext(req.FileName)
+	extend := strings.ToLower(filepath.Ext(req.FileName))
 	if extend == "" {
 		ctx.JSON(http.StatusOK, common.ErrorResponse(ctx, common.CodeParamError, "invalid file name"))
 		return

api/v1/task/handler.go

@@ -3,7 +3,7 @@ package task
 import (
 	"net/http"
 
-	"gitea.com/bitwsd/core/common/log"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 	"gitea.com/bitwsd/document_ai/internal/model/task"
 	"gitea.com/bitwsd/document_ai/internal/service"
 	"gitea.com/bitwsd/document_ai/pkg/common"

api/v1/user/handler.go

@@ -3,7 +3,7 @@ package user
 import (
 	"net/http"
 
-	"gitea.com/bitwsd/core/common/log"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 	"gitea.com/bitwsd/document_ai/config"
 	model "gitea.com/bitwsd/document_ai/internal/model/user"
 	"gitea.com/bitwsd/document_ai/internal/service"

config/config.go

@@ -1,7 +1,7 @@
 package config
 
 import (
-	"gitea.com/bitwsd/core/common/log"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 	"github.com/spf13/viper"
 )
 

config/config_prod.yaml

@@ -40,6 +40,6 @@ aliyun:
   oss:
     endpoint: oss-cn-beijing.aliyuncs.com
     inner_endpoint: oss-cn-beijing-internal.aliyuncs.com
-    access_key_id: LTAI5tKogxeiBb4gJGWEePWN
+    access_key_id: LTAI5t8qXhow6NCdYDtu1saF
-    access_key_secret: l4oCxtt5iLSQ1DAs40guTzKUfrxXwq
+    access_key_secret: qZ2SwYsNCEBckCVSOszH31yYwXU44A
-    bucket_name: bitwsd-doc-ai
+    bucket_name: texpixel-doc

go.mod

@@ -3,7 +3,6 @@ module gitea.com/bitwsd/document_ai
 go 1.20
 
 require (
-	gitea.com/bitwsd/core v0.0.0-20241128075635-8d72a929b914
 	github.com/alibabacloud-go/darabonba-openapi v0.2.1
 	github.com/alibabacloud-go/dysmsapi-20170525/v2 v2.0.18
 	github.com/alibabacloud-go/tea v1.1.19
@@ -13,7 +12,9 @@ require (
 	github.com/gin-gonic/gin v1.10.0
 	github.com/google/uuid v1.6.0
 	github.com/redis/go-redis/v9 v9.7.0
+	github.com/rs/zerolog v1.33.0
 	github.com/spf13/viper v1.19.0
+	gopkg.in/natefinch/lumberjack.v2 v2.2.1
 	gorm.io/driver/mysql v1.5.7
 	gorm.io/gorm v1.25.12
 )
@@ -54,7 +55,6 @@ require (
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.2 // indirect
-	github.com/rs/zerolog v1.33.0 // indirect
 	github.com/sagikazarmark/locafero v0.4.0 // indirect
 	github.com/sagikazarmark/slog-shim v0.1.0 // indirect
 	github.com/sourcegraph/conc v0.3.0 // indirect
@@ -76,6 +76,5 @@ require (
 	golang.org/x/time v0.5.0 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
-	gopkg.in/natefinch/lumberjack.v2 v2.2.1 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -1,5 +1,3 @@
-gitea.com/bitwsd/core v0.0.0-20241128075635-8d72a929b914 h1:3aRCeiuq/PWMr2yjEN9Y5NusfmpdMKiO4i/5tM5qc34=
-gitea.com/bitwsd/core v0.0.0-20241128075635-8d72a929b914/go.mod h1:hbEUo3t/AFGCnQbxwdG4oiw2IHdlRgK02cqd0yicP1Y=
 github.com/alibabacloud-go/alibabacloud-gateway-spi v0.0.4 h1:iC9YFYKDGEy3n/FtqJnOkZsene9olVspKmkX5A2YBEo=
 github.com/alibabacloud-go/alibabacloud-gateway-spi v0.0.4/go.mod h1:sCavSAvdzOjul4cEqeVtvlSaSScfNsTQ+46HwlTL1hc=
 github.com/alibabacloud-go/darabonba-openapi v0.1.18/go.mod h1:PB4HffMhJVmAgNKNq3wYbTUlFvPgxJpTzd1F5pTuUsc=
@@ -33,9 +31,7 @@ github.com/aliyun/aliyun-oss-go-sdk v3.0.2+incompatible/go.mod h1:T/Aws4fEfogEE9
 github.com/aliyun/credentials-go v1.1.2 h1:qU1vwGIBb3UJ8BwunHDRFtAhS6jnQLnde/yk0+Ih2GY=
 github.com/aliyun/credentials-go v1.1.2/go.mod h1:ozcZaMR5kLM7pwtCMEpVmQ242suV6qTJya2bDq4X1Tw=
 github.com/bsm/ginkgo/v2 v2.12.0 h1:Ny8MWAHyOepLGlLKYmXG4IEkioBysk6GpaRTLC8zwWs=
-github.com/bsm/ginkgo/v2 v2.12.0/go.mod h1:SwYbGRRDovPVboqFv0tPTcG1sN61LM1Z4ARdbAV9g4c=
 github.com/bsm/gomega v1.27.10 h1:yeMWxP2pV2fG3FgAODIY8EiRE3dy0aeFYt4l7wh6yKA=
-github.com/bsm/gomega v1.27.10/go.mod h1:JyEr/xRbxbtgWNi8tIEVPUYZ5Dzef52k01W3YH0H+O0=
 github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc0=
 github.com/bytedance/sonic v1.11.6/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4=
 github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM=
@@ -53,13 +49,11 @@ github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSV
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
-github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgrijalva/jwt-go v3.2.0+incompatible h1:7qlOGliEKZXTDg6OTjfoBKDXWrumCAMpl/TFQ4/5kLM=
 github.com/dgrijalva/jwt-go v3.2.0+incompatible/go.mod h1:E3ru+11k8xSBh+hMPgOLZmtrrCbhqsmaPHjLKYnJCaQ=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/rVNCu3HqELle0jiPLLBs70cWOduZpkS1E78=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
 github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHkI4W8=
-github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
 github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
 github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
@@ -69,7 +63,6 @@ github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm
 github.com/gin-gonic/gin v1.10.0 h1:nTuyha1TYqgedzytsKYqna+DfLos46nTv2ygFy86HFU=
 github.com/gin-gonic/gin v1.10.0/go.mod h1:4PMNQiOhvDRa013RKVbsiNwoyezlm2rm0uX/T7kzp5Y=
 github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
-github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
 github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
 github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY=
@@ -82,7 +75,6 @@ github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 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/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@@ -103,11 +95,9 @@ github.com/klauspost/cpuid/v2 v2.2.7 h1:ZWSB3igEs+d0qvnxR/ZBzXVmxkgt8DdzP6m9pfuV
 github.com/klauspost/cpuid/v2 v2.2.7/go.mod h1:Lcz8mBdAVJIBVzewtcLocK12l3Y+JytZYpaMropDUws=
 github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
-github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
-github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/leodido/go-urn v1.4.0 h1:WT9HwE9SGECu3lg4d/dIA+jxlljEa1/ffXKmRjqdmIQ=
 github.com/leodido/go-urn v1.4.0/go.mod h1:bvxc+MVxLKB4z00jd1z+Dvzr47oO32F/QSNjSBOlFxI=
 github.com/magiconair/properties v1.8.7 h1:IeQXZAiQcpL9mgcAe1Nu6cX9LLw6ExEHKjN0VQdvPDY=
@@ -134,11 +124,9 @@ github.com/pelletier/go-toml/v2 v2.2.2/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
-github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/redis/go-redis/v9 v9.7.0 h1:HhLSs+B6O021gwzl+locl0zEDnyNkxMtf/Z3NNBMa9E=
 github.com/redis/go-redis/v9 v9.7.0/go.mod h1:f6zhXITC7JUJIlPEiBOTXxJgPLdZcA93GewI7inzyWw=
 github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
-github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
 github.com/rs/xid v1.5.0/go.mod h1:trrq9SKmegXys3aeAKXMUTdJsYXVwGY3RLcfgqegfbg=
 github.com/rs/zerolog v1.33.0 h1:1cU2KZkvPxNyfgEmhHAz/1A9Bz+llsdYzklWFzgp0r8=
 github.com/rs/zerolog v1.33.0/go.mod h1:/7mN4D5sKwJLZQ2b/znpjC3/GQWY/xaDXUM0kKWRHss=

internal/model/formula/response.go

@@ -11,3 +11,8 @@ type GetFormulaTaskResponse struct {
 	Count  int    `json:"count"`
 	Latex  string `json:"latex"`
 }
+
+// FormulaRecognitionResponse 公式识别服务返回的响应
+type FormulaRecognitionResponse struct {
+	Result string `json:"result"`
+}

internal/service/recognition_service.go

@@ -11,11 +11,11 @@ import (
 	"strings"
 	"time"
 
-	"gitea.com/bitwsd/core/common/log"
 	"gitea.com/bitwsd/document_ai/config"
 	"gitea.com/bitwsd/document_ai/internal/model/formula"
 	"gitea.com/bitwsd/document_ai/internal/storage/cache"
 	"gitea.com/bitwsd/document_ai/internal/storage/dao"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 
 	"gitea.com/bitwsd/document_ai/pkg/common"
 	"gitea.com/bitwsd/document_ai/pkg/constant"
@@ -200,7 +200,7 @@ func (s *RecognitionService) processVLFormula(ctx context.Context, taskID int64)
 	log.Info(ctx, "func", "processVLFormulaQueue", "msg", "获取任务成功", "task_id", taskID)
 
 	// 处理具体任务
-	if err := s.processVLFormulaTask(ctx, taskID, task.FileURL); err != nil {
+	if err := s.processVLFormulaTask(ctx, taskID, task.FileURL, utils.ModelVLQwen3VL32BInstruct); err != nil {
 		log.Error(ctx, "func", "processVLFormulaQueue", "msg", "处理任务失败", "error", err)
 		return
 	}
@@ -263,11 +263,11 @@ func (s *RecognitionService) processFormulaTask(ctx context.Context, taskID int6
 		return err
 	}
 
-	downloadURL, err := oss.GetDownloadURL(ctx, fileURL)
+	// downloadURL, err := oss.GetDownloadURL(ctx, fileURL)
-	if err != nil {
+	// if err != nil {
-		log.Error(ctx, "func", "processFormulaTask", "msg", "获取下载URL失败", "error", err)
+	// 	log.Error(ctx, "func", "processFormulaTask", "msg", "获取下载URL失败", "error", err)
-		return err
+	// 	return err
-	}
+	// }
 
 	// 将图片转为base64编码
 	base64Image := base64.StdEncoding.EncodeToString(imageData)
@@ -275,7 +275,6 @@ func (s *RecognitionService) processFormulaTask(ctx context.Context, taskID int6
 	// 创建JSON请求
 	requestData := map[string]string{
 		"image_base64": base64Image,
-		"img_url":      downloadURL,
 	}
 
 	jsonData, err := json.Marshal(requestData)
@@ -288,7 +287,7 @@ func (s *RecognitionService) processFormulaTask(ctx context.Context, taskID int6
 	headers := map[string]string{"Content-Type": "application/json", utils.RequestIDHeaderKey: utils.GetRequestIDFromContext(ctx)}
 
 	// 发送请求时会使用带超时的context
-	resp, err := s.httpClient.RequestWithRetry(ctx, http.MethodPost, s.getURL(ctx), bytes.NewReader(jsonData), headers)
+	resp, err := s.httpClient.RequestWithRetry(ctx, http.MethodPost, "http://cloud.texpixel.com:1080/formula/predict", bytes.NewReader(jsonData), headers)
 	if err != nil {
 		if ctx.Err() == context.DeadlineExceeded {
 			log.Error(ctx, "func", "processFormulaTask", "msg", "请求超时")
@@ -299,13 +298,21 @@ func (s *RecognitionService) processFormulaTask(ctx context.Context, taskID int6
 	}
 	defer resp.Body.Close()
 
-	log.Info(ctx, "func", "processFormulaTask", "msg", "请求成功", "resp", resp.Body)
+	log.Info(ctx, "func", "processFormulaTask", "msg", "请求成功")
 	body := &bytes.Buffer{}
 	if _, err = body.ReadFrom(resp.Body); err != nil {
 		log.Error(ctx, "func", "processFormulaTask", "msg", "读取响应体失败", "error", err)
 		return err
 	}
-	katex := utils.ToKatex(body.String())
+	log.Info(ctx, "func", "processFormulaTask", "msg", "响应内容", "body", body.String())
+
+	// 解析 JSON 响应
+	var formulaResp formula.FormulaRecognitionResponse
+	if err := json.Unmarshal(body.Bytes(), &formulaResp); err != nil {
+		log.Error(ctx, "func", "processFormulaTask", "msg", "解析响应JSON失败", "error", err)
+		return err
+	}
+	katex := utils.ToKatex(formulaResp.Result)
 	content := &dao.FormulaRecognitionContent{Latex: katex}
 	b, _ := json.Marshal(content)
 	// Save recognition result
@@ -322,7 +329,7 @@ func (s *RecognitionService) processFormulaTask(ctx context.Context, taskID int6
 	return nil
 }
 
-func (s *RecognitionService) processVLFormulaTask(ctx context.Context, taskID int64, fileURL string) error {
+func (s *RecognitionService) processVLFormulaTask(ctx context.Context, taskID int64, fileURL string, model string) error {
 	isSuccess := false
 	defer func() {
 		if !isSuccess {
@@ -349,28 +356,11 @@ func (s *RecognitionService) processVLFormulaTask(ctx context.Context, taskID in
 		log.Error(ctx, "func", "processVLFormulaTask", "msg", "读取图片数据失败", "error", err)
 		return err
 	}
-	prompt := `
+	prompt := `Please perform OCR on the image and output only LaTeX code.`
-Please perform OCR on the image and output only LaTeX code.
-Important instructions:
-
- * "The image contains mathematical formulas, no plain text."
-
- * "Preserve all layout, symbols, subscripts, summations, parentheses, etc., exactly as shown."
-
- * "Use \[ ... \] or align environments to represent multiline math expressions."
-
- * "Use adaptive symbols such as \left and \right where applicable."
-
- * "Do not include any extra commentary, template answers, or unrelated equations."
-
- * "Only output valid LaTeX code based on the actual content of the image, and not change the original mathematical expression."
-
- * "The output result must be can render by better-react-mathjax." 
- `
 	base64Image := base64.StdEncoding.EncodeToString(imageData)
 
 	requestBody := formula.VLFormulaRequest{
-		Model:            "Qwen/Qwen2.5-VL-32B-Instruct",
+		Model:            model,
 		Stream:           false,
 		MaxTokens:        512,
 		Temperature:      0.1,
@@ -517,24 +507,12 @@ func (s *RecognitionService) processOneTask(ctx context.Context) {
 	ctx = context.WithValue(ctx, utils.RequestIDKey, task.TaskUUID)
 	log.Info(ctx, "func", "processFormulaQueue", "msg", "获取任务成功", "task_id", taskID)
 
-	// 处理具体任务
+	// 处理任务
-	if err := s.processFormulaTask(ctx, taskID, task.FileURL); err != nil {
+	err = s.processFormulaTask(ctx, taskID, task.FileURL)
+	if err != nil {
 		log.Error(ctx, "func", "processFormulaQueue", "msg", "处理任务失败", "error", err)
 		return
 	}
 
 	log.Info(ctx, "func", "processFormulaQueue", "msg", "处理任务成功", "task_id", taskID)
 }
-
-func (s *RecognitionService) getURL(ctx context.Context) string {
-	return "http://cloud.srcstar.com:8045/formula/predict"
-	count, err := cache.IncrURLCount(ctx)
-	if err != nil {
-		log.Error(ctx, "func", "getURL", "msg", "获取URL计数失败", "error", err)
-		return "http://cloud.srcstar.com:8026/formula/predict"
-	}
-	if count%2 == 0 {
-		return "http://cloud.srcstar.com:8026/formula/predict"
-	}
-	return "https://cloud.texpixel.com:1080/formula/predict"
-}

internal/service/task.go

@@ -5,7 +5,7 @@ import (
 	"errors"
 	"strings"
 
-	"gitea.com/bitwsd/core/common/log"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 	"gitea.com/bitwsd/document_ai/internal/model/task"
 	"gitea.com/bitwsd/document_ai/internal/storage/dao"
 	"gorm.io/gorm"

internal/service/user_service.go

@@ -6,7 +6,7 @@ import (
 	"fmt"
 	"math/rand"
 
-	"gitea.com/bitwsd/core/common/log"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 	"gitea.com/bitwsd/document_ai/internal/storage/cache"
 	"gitea.com/bitwsd/document_ai/internal/storage/dao"
 	"gitea.com/bitwsd/document_ai/pkg/sms"

main.go

@@ -10,9 +10,9 @@ import (
 	"syscall"
 	"time"
 
-	"gitea.com/bitwsd/core/common/cors"
+	"gitea.com/bitwsd/document_ai/pkg/cors"
-	"gitea.com/bitwsd/core/common/log"
+	"gitea.com/bitwsd/document_ai/pkg/log"
-	"gitea.com/bitwsd/core/common/middleware"
+	"gitea.com/bitwsd/document_ai/pkg/middleware"
 	"gitea.com/bitwsd/document_ai/api"
 	"gitea.com/bitwsd/document_ai/config"
 	"gitea.com/bitwsd/document_ai/internal/storage/cache"

pkg/cors/cors.go

@@ -0,0 +1,61 @@
+package cors
+
+import (
+	"strconv"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+)
+
+type Config struct {
+	AllowOrigins     []string
+	AllowMethods     []string
+	AllowHeaders     []string
+	ExposeHeaders    []string
+	AllowCredentials bool
+	MaxAge           int
+}
+
+func DefaultConfig() Config {
+	return Config{
+		AllowOrigins:     []string{"*"},
+		AllowMethods:     []string{"GET", "POST", "PUT", "DELETE", "OPTIONS"},
+		AllowHeaders:     []string{"Origin", "Content-Type", "Accept"},
+		ExposeHeaders:    []string{"Content-Length"},
+		AllowCredentials: true,
+		MaxAge:           86400, // 24 hours
+	}
+}
+
+func Cors(config Config) gin.HandlerFunc {
+	return func(c *gin.Context) {
+		origin := c.Request.Header.Get("Origin")
+
+		// 检查是否允许该来源
+		allowOrigin := "*"
+		for _, o := range config.AllowOrigins {
+			if o == origin {
+				allowOrigin = origin
+				break
+			}
+		}
+
+		c.Header("Access-Control-Allow-Origin", allowOrigin)
+		c.Header("Access-Control-Allow-Methods", strings.Join(config.AllowMethods, ","))
+		c.Header("Access-Control-Allow-Headers", strings.Join(config.AllowHeaders, ","))
+		c.Header("Access-Control-Expose-Headers", strings.Join(config.ExposeHeaders, ","))
+		c.Header("Access-Control-Max-Age", strconv.Itoa(config.MaxAge))
+
+		if config.AllowCredentials {
+			c.Header("Access-Control-Allow-Credentials", "true")
+		}
+
+		if c.Request.Method == "OPTIONS" {
+			c.AbortWithStatus(204)
+			return
+		}
+
+		c.Next()
+	}
+}
+

pkg/httpclient/client.go

@@ -10,7 +10,7 @@ import (
 	"net/http"
 	"time"
 
-	"gitea.com/bitwsd/core/common/log"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 )
 
 // RetryConfig 重试配置

pkg/log/log_config.go

@@ -0,0 +1,30 @@
+package log
+
+var (
+	maxSize    = 100 // MB
+	outputPath = "/app/logs/app.log"
+)
+
+type LogConfig struct {
+	AppName    string `yaml:"appName"`    // 应用名称
+	Level      string `yaml:"level"`      // debug, info, warn, error
+	Format     string `yaml:"format"`     // json, console
+	OutputPath string `yaml:"outputPath"` // 日志文件路径
+	MaxSize    int    `yaml:"maxSize"`    // 单个日志文件最大尺寸，单位MB
+	MaxAge     int    `yaml:"maxAge"`     // 日志保留天数
+	MaxBackups int    `yaml:"maxBackups"` // 保留的旧日志文件最大数量
+	Compress   bool   `yaml:"compress"`   // 是否压缩旧日志
+}
+
+func DefaultLogConfig() *LogConfig {
+	return &LogConfig{
+		Level:      "info",
+		Format:     "json",
+		OutputPath: outputPath,
+		MaxSize:    maxSize,
+		MaxAge:     7,
+		MaxBackups: 3,
+		Compress:   true,
+	}
+}
+

pkg/log/logger.go

@@ -0,0 +1,152 @@
+package log
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"runtime"
+	"time"
+
+	"github.com/rs/zerolog"
+	"gopkg.in/natefinch/lumberjack.v2"
+)
+
+type LogType string
+
+const (
+	TypeAccess   LogType = "access"
+	TypeBusiness LogType = "business"
+	TypeError    LogType = "error"
+)
+
+var (
+	logger zerolog.Logger
+)
+
+// Setup 初始化日志配置
+func Setup(conf LogConfig) error {
+	// 确保日志目录存在
+	if err := os.MkdirAll(filepath.Dir(conf.OutputPath), 0755); err != nil {
+		return fmt.Errorf("create log directory failed: %v", err)
+	}
+
+	// 配置日志轮转
+	writer := &lumberjack.Logger{
+		Filename:   conf.OutputPath,
+		MaxSize:    conf.MaxSize, // MB
+		MaxAge:     conf.MaxAge,  // days
+		MaxBackups: conf.MaxBackups,
+		Compress:   conf.Compress,
+	}
+
+	// 设置日志级别
+	level, err := zerolog.ParseLevel(conf.Level)
+	if err != nil {
+		level = zerolog.InfoLevel
+	}
+	zerolog.SetGlobalLevel(level)
+
+	// 初始化logger 并添加 app_name
+	logger = zerolog.New(writer).With().
+		Timestamp().
+		Str("app_name", conf.AppName). // 添加 app_name
+		Logger()
+
+	return nil
+}
+
+// log 统一的日志记录函数
+func log(ctx context.Context, level zerolog.Level, logType LogType, kv ...interface{}) {
+	if len(kv)%2 != 0 {
+		kv = append(kv, "MISSING")
+	}
+
+	event := logger.WithLevel(level)
+
+	// 添加日志类型
+	event.Str("type", string(logType))
+
+	// 添加请求ID
+	if reqID, exists := ctx.Value("request_id").(string); exists {
+		event.Str("request_id", reqID)
+	}
+
+	// 添加调用位置
+	if pc, file, line, ok := runtime.Caller(2); ok {
+		event.Str("caller", fmt.Sprintf("%s:%d %s", filepath.Base(file), line, runtime.FuncForPC(pc).Name()))
+	}
+
+	// 处理key-value对
+	for i := 0; i < len(kv); i += 2 {
+		key, ok := kv[i].(string)
+		if !ok {
+			continue
+		}
+		value := kv[i+1]
+
+		switch v := value.(type) {
+		case error:
+			event.AnErr(key, v)
+		case int:
+			event.Int(key, v)
+		case int64:
+			event.Int64(key, v)
+		case float64:
+			event.Float64(key, v)
+		case bool:
+			event.Bool(key, v)
+		case time.Duration:
+			event.Dur(key, v)
+		case time.Time:
+			event.Time(key, v)
+		case []byte:
+			event.Bytes(key, v)
+		case string:
+			event.Str(key, v)
+		default:
+			event.Interface(key, v)
+		}
+	}
+
+	event.Send()
+}
+
+// Debug 记录调试日志
+func Debug(ctx context.Context, kv ...interface{}) {
+	log(ctx, zerolog.DebugLevel, TypeBusiness, kv...)
+}
+
+// Info 记录信息日志
+func Info(ctx context.Context, kv ...interface{}) {
+	log(ctx, zerolog.InfoLevel, TypeBusiness, kv...)
+}
+
+// Warn 记录警告日志
+func Warn(ctx context.Context, kv ...interface{}) {
+	log(ctx, zerolog.WarnLevel, TypeError, kv...)
+}
+
+// Error 记录错误日志
+func Error(ctx context.Context, kv ...interface{}) {
+	log(ctx, zerolog.ErrorLevel, TypeError, kv...)
+}
+
+func Fatal(ctx context.Context, kv ...interface{}) {
+	// 获取错误堆栈
+	buf := make([]byte, 4096)
+	n := runtime.Stack(buf, false)
+
+	// 添加堆栈信息到kv
+	newKv := make([]interface{}, 0, len(kv)+2)
+	newKv = append(newKv, kv...)
+	newKv = append(newKv, "stack", string(buf[:n]))
+
+	log(ctx, zerolog.FatalLevel, TypeError, newKv...)
+}
+
+// Access 记录访问日志
+func Access(ctx context.Context, kv ...interface{}) {
+	log(ctx, zerolog.InfoLevel, TypeAccess, kv...)
+}
+

pkg/middleware/access.go

@@ -0,0 +1,75 @@
+package middleware
+
+import (
+	"bytes"
+	"io"
+	"strings"
+	"time"
+
+	"gitea.com/bitwsd/document_ai/pkg/log"
+	"github.com/gin-gonic/gin"
+)
+
+const (
+	maxBodySize = 1024 * 500 // 500KB 限制
+)
+
+// 自定义 ResponseWriter 来捕获响应
+type bodyWriter struct {
+	gin.ResponseWriter
+	body *bytes.Buffer
+}
+
+func (w *bodyWriter) Write(b []byte) (int, error) {
+	w.body.Write(b)
+	return w.ResponseWriter.Write(b)
+}
+
+func AccessLog() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		start := time.Now()
+		path := c.Request.URL.Path
+		raw := c.Request.URL.RawQuery
+
+		// 处理请求体
+		var reqBody string
+		if c.Request.Body != nil && (c.Request.Method == "POST" || c.Request.Method == "PUT") {
+			// 读取并限制请求体大小
+			bodyBytes, _ := io.ReadAll(io.LimitReader(c.Request.Body, maxBodySize))
+			c.Request.Body = io.NopCloser(bytes.NewBuffer(bodyBytes)) // 重新设置 body
+			reqBody = string(bodyBytes)
+		}
+
+		// 设置自定义 ResponseWriter
+		var responseBody string
+		if !strings.Contains(c.GetHeader("Accept"), "text/event-stream") {
+			bw := &bodyWriter{body: &bytes.Buffer{}, ResponseWriter: c.Writer}
+			c.Writer = bw
+		}
+
+		c.Next()
+
+		// 获取响应体（非 SSE）
+		if writer, ok := c.Writer.(*bodyWriter); ok {
+			responseBody = writer.body.String()
+			if len(responseBody) > maxBodySize {
+				responseBody = responseBody[:maxBodySize] + "... (truncated)"
+			}
+		}
+
+		// 记录访问日志
+		log.Access(c.Request.Context(),
+			"request_id", c.GetString("request_id"),
+			"method", c.Request.Method,
+			"path", path,
+			"query", raw,
+			"ip", c.ClientIP(),
+			"user_agent", c.Request.UserAgent(),
+			"status", c.Writer.Status(),
+			"duration", time.Since(start),
+			"request_body", reqBody,
+			"response_body", responseBody,
+		)
+	}
+}
+

pkg/middleware/requestid.go

@@ -0,0 +1,19 @@
+package middleware
+
+import (
+	"github.com/gin-gonic/gin"
+	"github.com/google/uuid"
+)
+
+func RequestID() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		requestID := c.Request.Header.Get("X-Request-ID")
+		if requestID == "" {
+			requestID = uuid.New().String()
+		}
+		c.Request.Header.Set("X-Request-ID", requestID)
+		c.Set("request_id", requestID)
+		c.Next()
+	}
+}
+

pkg/oss/policy.go

@@ -12,8 +12,8 @@ import (
 	"strings"
 	"time"
 
-	"gitea.com/bitwsd/core/common/log"
 	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 	"github.com/aliyun/aliyun-oss-go-sdk/oss"
 )
 
@@ -125,9 +125,7 @@ func DownloadFile(ctx context.Context, ossPath string) (io.ReadCloser, error) {
 	}
 
 	// Create OSS client
-	client, err := oss.New(endpoint,
+	client, err := oss.New(endpoint, config.GlobalConfig.Aliyun.OSS.AccessKeyID, config.GlobalConfig.Aliyun.OSS.AccessKeySecret)
-		config.GlobalConfig.Aliyun.OSS.AccessKeyID,
-		config.GlobalConfig.Aliyun.OSS.AccessKeySecret)
 	if err != nil {
 		log.Error(ctx, "func", "DownloadFile", "msg", "create oss client failed", "error", err)
 		return nil, err

pkg/utils/katex.go

@@ -23,6 +23,8 @@ func rmDollarSurr(text string) string {
 func ToKatex(formula string) string {
 	res := formula
 
+	res = strings.ReplaceAll(res, "\n", "")
+
 	// Remove mbox surrounding
 	res = changeAll(res, `\mbox `, " ", "{", "}", "", "")
 	res = changeAll(res, `\mbox`, " ", "{", "}", "", "")

pkg/utils/model.go

@@ -0,0 +1,6 @@
+package utils
+
+const (
+	ModelVLDeepSeekOCR        = "deepseek-ai/DeepSeek-OCR"
+	ModelVLQwen3VL32BInstruct = "Qwen/Qwen3-VL-32B-Instruct"
+)

pkg/utils/routine.go

@@ -3,7 +3,7 @@ package utils
 import (
 	"context"
 
-	"gitea.com/bitwsd/core/common/log"
+	"gitea.com/bitwsd/document_ai/pkg/log"
 )
 
 func SafeGo(fn func()) {

pkg/utils/token.go

@@ -1,5 +1,5 @@
 package utils
 
 const (
-	SiliconFlowToken = "Bearer sk-akbroznlbxikkbiouzasspbbzwgxubnjjtqlujxmxsnvpmhn"
+	SiliconFlowToken = "Bearer sk-wiggxqscvjdveqvwcdywwpipcinglkzkewkcfjnrgjqbdbmc"
 )