diff --git a/models/cloudbrain.go b/models/cloudbrain.go
index 34869c1ee..db98bb662 100755
--- a/models/cloudbrain.go
+++ b/models/cloudbrain.go
@@ -205,7 +205,7 @@ type Cloudbrain struct {
BenchmarkTypeRankLink string `xorm:"-"`
StartTime timeutil.TimeStamp
EndTime timeutil.TimeStamp
- Cleared bool `xorm:"DEFAULT false"`
+ Cleared bool `xorm:"DEFAULT false"`
Spec *Specification `xorm:"-"`
}
@@ -1823,7 +1823,7 @@ func QueryModelTrainJobVersionList(jobId string) ([]*Cloudbrain, int, error) {
return cloudbrains, int(len(cloudbrains)), nil
}
-func QueryModelTrainJobList(repoId int64) ([]*CloudbrainInfo, int, error) {
+func QueryModelTrainJobList(repoId int64) ([]*Cloudbrain, int, error) {
sess := x.NewSession()
defer sess.Close()
var cond = builder.NewCond()
@@ -1840,14 +1840,14 @@ func QueryModelTrainJobList(repoId int64) ([]*CloudbrainInfo, int, error) {
// builder.In("type", 0, 1),
// )
- cloudbrains := make([]*CloudbrainInfo, 0)
+ cloudbrains := make([]*Cloudbrain, 0)
if err := sess.Select("job_id,display_job_name").Table(&Cloudbrain{}).Where(cond).OrderBy("created_unix DESC").
Find(&cloudbrains); err != nil {
return nil, 0, fmt.Errorf("Find: %v", err)
}
keys := make(map[string]string)
- uniqueElements := make([]*CloudbrainInfo, 0)
+ uniqueElements := make([]*Cloudbrain, 0)
for _, entry := range cloudbrains {
if _, value := keys[entry.JobID]; !value {
keys[entry.JobID] = entry.DisplayJobName
@@ -1988,7 +1988,7 @@ func GetCloudbrainByID(id string) (*Cloudbrain, error) {
return getRepoCloudBrain(cb)
}
-func IsCloudbrainExistByJobName(jobName string)(bool,error){
+func IsCloudbrainExistByJobName(jobName string) (bool, error) {
return x.Unscoped().Exist(&Cloudbrain{
JobName: jobName,
})
@@ -2126,6 +2126,15 @@ func GetCloudbrainByName(jobName string) (*Cloudbrain, error) {
cb := &Cloudbrain{JobName: jobName}
return getRepoCloudBrain(cb)
}
+func GetWaitOrRunFileNotebookByRepo(repoId int64, cloudbrainType int) (*Cloudbrain, error) {
+ cloudBrain := new(Cloudbrain)
+ has, err := x.In("status", JobWaiting, JobRunning, ModelArtsCreateQueue, ModelArtsCreating, ModelArtsStarting,
+ ModelArtsReadyToStart, ModelArtsResizing, ModelArtsStartQueuing, ModelArtsRunning, ModelArtsDeleting, ModelArtsRestarting).Where("repo_id=? and type=? and boot_file!=''", repoId, cloudbrainType).Get(cloudBrain)
+ if has {
+ return cloudBrain, err
+ }
+ return nil, err
+}
func CanDelJob(isSigned bool, user *User, job *CloudbrainInfo) bool {
if !isSigned || (job.Status != string(JobStopped) && job.Status != string(JobFailed) && job.Status != string(ModelArtsStartFailed) && job.Status != string(ModelArtsCreateFailed)) {
@@ -2172,25 +2181,25 @@ func GetCloudBrainOneStoppedNotDebugJobDaysAgo(days int, limit int) ([]*Cloudbra
Limit(limit).
Find(&cloudbrains)
}
+
/**
本方法考虑了再次调试的情况，多次调试取最后一次的任务的结束时间
- */
+*/
func GetCloudBrainOneStoppedDebugJobDaysAgo(days int, limit int) ([]*Cloudbrain, error) {
cloudbrains := make([]*Cloudbrain, 0, 10)
endTimeBefore := time.Now().Unix() - int64(days)*24*3600
missEndTimeBefore := endTimeBefore - 24*3600
- sql:=`SELECT id,job_name,job_id from (SELECT DISTINCT ON (job_name)
+ sql := `SELECT id,job_name,job_id from (SELECT DISTINCT ON (job_name)
id, job_name, job_id,status,end_time,updated_unix,cleared
FROM cloudbrain
where type=0 and job_type='DEBUG'
ORDER BY job_name, updated_unix DESC) a
where status in ('STOPPED','SUCCEEDED','FAILED') and (((end_time is null or end_time=0) and updated_unix 1 {
+ break
+ }
+
+ }
+
+ }
+ if xsrf != "" {
+ c.Cookies = cookies
+ c.Xsrf = xsrf
+ }
+
+ }
+ }
+ c.Cookies = cookies
+
+}
+
+func (c *NotebookContent) IsNoteBookContentsExist() bool {
+ client := getRestyClient()
+ uploadUrl := getJupyterBaseUrl(c.Url) + "api/contents/" + c.Path + "?type=" + c.PathType
+ res, err := client.R().
+ SetCookies(c.Cookies).
+ SetHeader("X-XSRFToken", c.Xsrf).
+ Get(uploadUrl)
+ if err != nil {
+ log.Warn("browser url error:"+uploadUrl, err)
+ return false
+ }
+ return res.StatusCode() == http.StatusOK
+}
+
+func (c *NotebookContent) UploadNoteBookFile(task *models.Cloudbrain) error {
+
+ err := c.MakeNoteBookDir()
+ if err != nil {
+ return err
+ }
+
+ codePath := setting.JobPath + task.JobName + cloudbrain.CodeMountPath
+ fileContents, err := ioutil.ReadFile(codePath + "/" + c.Path)
+ if err != nil {
+ log.Error("read jupyter file failed:%v", task.DisplayJobName, err)
+ }
+
+ base64Content := base64.StdEncoding.EncodeToString(fileContents)
+ client := getRestyClient()
+ uploadUrl := getJupyterBaseUrl(c.Url) + "api/contents/" + c.Path
+ res, err := client.R().
+ SetCookies(c.Cookies).
+ SetHeader("X-XSRFToken", c.Xsrf).
+ SetBody(map[string]interface{}{
+ "type": "file",
+ "format": "base64",
+ "name": path.Base(c.Path),
+ "path": c.Path,
+ "content": base64Content}).
+ Put(uploadUrl)
+ if err != nil {
+ log.Error("upload jupyter file failed:%v", task.DisplayJobName, err)
+ return err
+ } else if res.StatusCode() != http.StatusCreated {
+ log.Error("upload jupyter file failed:%v, status is %s", task.DisplayJobName, res.Status(), err)
+ return fmt.Errorf("status:", res.StatusCode())
+ }
+ return nil
+}
+
+/**
+ if c.Path is a/b/c.txt
+ makedir a/b
+ if c.Path is a/b/c
+ makedir a/b
+*/
+func (c *NotebookContent) MakeNoteBookDir() error {
+ filePaths := strings.Split(c.Path, "/")
+
+ for i := 0; i < len(filePaths)-1; i++ {
+ cTemp := &NotebookContent{
+ Url: c.Url,
+ Cookies: c.Cookies,
+ Path: path.Join(filePaths[0 : i+1]...),
+ PathType: "directory",
+ Xsrf: c.Xsrf,
+ }
+ if !cTemp.IsNoteBookContentsExist() {
+
+ createTempDirUrl := getJupyterBaseUrl(cTemp.Url) + "api/contents/" + cTemp.Path
+ client := getRestyClient()
+ var jobResult NotebookApiResponse
+ res, err := client.R().
+ SetCookies(c.Cookies).
+ SetHeader("X-XSRFToken", c.Xsrf).
+ SetBody(map[string]interface{}{
+ "type": cTemp.PathType,
+ "path": cTemp.Path,
+ }).SetResult(&jobResult).
+ Put(createTempDirUrl)
+ if err != nil {
+ return err
+ }
+ if res.StatusCode() != http.StatusCreated {
+ return fmt.Errorf("status code:" + res.Status())
+ }
+
+ }
+
+ }
+ return nil
+}
+
+func getJupyterBaseUrl(url string) string {
+ jupyterUrlLength := len(url)
+ baseUrl := url
+ if strings.HasSuffix(url, "lab") {
+ baseUrl = url[0 : jupyterUrlLength-len(path.Base(url))]
+ }
+
+ return baseUrl
+}
+
+func getRestyClient() *resty.Client {
+ if restyClient == nil {
+ restyClient = resty.New()
+ restyClient.SetTLSClientConfig(&tls.Config{InsecureSkipVerify: true})
+ }
+ return restyClient
+}
diff --git a/modules/structs/cloudbrain.go b/modules/structs/cloudbrain.go
index 9ea5601c9..e4403ed04 100644
--- a/modules/structs/cloudbrain.go
+++ b/modules/structs/cloudbrain.go
@@ -47,6 +47,7 @@ type CreateFileNotebookJobOption struct {
BranchName string `json:"branch_name" binding:"Required"`
OwnerName string `json:"owner_name" binding:"Required"`
ProjectName string `json:"project_name" binding:"Required"`
+ JobId string `json:"job_id"`
}
type Cloudbrain struct {
diff --git a/options/locale/locale_en-US.ini b/options/locale/locale_en-US.ini
index 702c17bce..f05ea5799 100755
--- a/options/locale/locale_en-US.ini
+++ b/options/locale/locale_en-US.ini
@@ -577,6 +577,7 @@ static.CloudBrainTaskNum=CloudBrain Task Count
static.CloudBrainRunTime=CloudBrain Run Time
static.CommitDatasetNum=Commit Dataset Count
static.CommitModelCount=Commit Model Count
+static.ModelConvertCount=Model Convert Count
static.UserIndex=Normalized user index
static.UserIndexPrimitive=User Index
static.countdate=Count Date
@@ -1061,7 +1062,7 @@ model_rename=Duplicate model name, please modify model name.
notebook_file_not_exist=Notebook file does not exist.
notebook_select_wrong=Please select a Notebook(.ipynb) file first.
notebook_file_no_right=You have no right to access the Notebook(.ipynb) file.
-debug_again_fail=Fail to restart debug task, please try again later.
+notebook_repo_conflict=The files in different branches of the same repository can not run together.
date=Date
repo_add=Project Increment
diff --git a/options/locale/locale_zh-CN.ini b/options/locale/locale_zh-CN.ini
index 5ae74ef98..f08665431 100755
--- a/options/locale/locale_zh-CN.ini
+++ b/options/locale/locale_zh-CN.ini
@@ -581,6 +581,7 @@ static.CloudBrainTaskNum=云脑任务数
static.CloudBrainRunTime=云脑运行时间（小时）
static.CommitDatasetNum=上传（提交）数据集文件数
static.CommitModelCount=提交模型数
+static.ModelConvertCount=模型转换数
static.UserIndex=归一化用户指数
static.UserIndexPrimitive=用户指数
static.countdate=系统统计时间
@@ -1060,7 +1061,7 @@ model_rename=模型名称重复，请修改模型名称
notebook_file_not_exist=Notebook文件不存在。
notebook_select_wrong=请先选择Notebook（.ipynb）文件。
notebook_file_no_right=您没有这个Notebook文件的读权限。
-debug_again_fail=再次调试失败，请稍后再试。
+notebook_repo_conflict=同一个仓库的不同分支文件不能同时运行。
date=日期
repo_add=新增项目
@@ -1672,7 +1673,7 @@ issues.action_assignee_no_select=未指派
issues.opened_by=由 %[3]s 于 %[1]s创建
pulls.merged_by=由 %[3]s 于 %[1]s 合并
pulls.merged_by_fake=由 %[2]s 于 %[1]s 合并
-issues.closed_by=按 %[3]s 关闭%[1]s
+issues.closed_by=由 %[3]s 创建，被关闭于 %[1]s
issues.opened_by_fake=由 %[2]s 于 %[1]s创建
issues.closed_by_fake=通过 %[2]s 关闭 %[1]s
issues.previous=上一页
diff --git a/routers/api/v1/api.go b/routers/api/v1/api.go
index 4936c2362..b5ba895be 100755
--- a/routers/api/v1/api.go
+++ b/routers/api/v1/api.go
@@ -745,7 +745,7 @@ func RegisterRoutes(m *macaron.Macaron) {
m.Group("/file_notebook", func() {
m.Get("", repo.GetFileNoteBookInfo)
m.Post("/create", reqToken(), reqWeChat(), bind(api.CreateFileNotebookJobOption{}), repo.CreateFileNoteBook)
-
+ m.Post("/status", reqToken(), bind(api.CreateFileNotebookJobOption{}), repo.FileNoteBookStatus)
})
m.Group("/repos", func() {
@@ -1024,6 +1024,8 @@ func RegisterRoutes(m *macaron.Macaron) {
m.Get("/query_model_byName", repo.QueryModelByName)
m.Get("/query_model_for_predict", repo.QueryModelListForPredict)
m.Get("/query_modelfile_for_predict", repo.QueryModelFileForPredict)
+ m.Get("/query_train_job", repo.QueryTrainJobList)
+ m.Get("/query_train_job_version", repo.QueryTrainJobVersionList)
m.Get("/query_train_model", repo.QueryTrainModelList)
m.Post("/create_model_convert", repo.CreateModelConvert)
m.Post("/convert_stop", repo.StopModelConvert)
diff --git a/routers/api/v1/repo/cloudbrain.go b/routers/api/v1/repo/cloudbrain.go
index 805443788..250a08423 100755
--- a/routers/api/v1/repo/cloudbrain.go
+++ b/routers/api/v1/repo/cloudbrain.go
@@ -110,6 +110,9 @@ func GeneralCloudBrainJobStop(ctx *context.APIContext) {
func CreateFileNoteBook(ctx *context.APIContext, option api.CreateFileNotebookJobOption) {
cloudbrainTask.FileNotebookCreate(ctx.Context, option)
}
+func FileNoteBookStatus(ctx *context.APIContext, option api.CreateFileNotebookJobOption) {
+ cloudbrainTask.FileNotebookStatus(ctx.Context, option)
+}
func GetFileNoteBookInfo(ctx *context.APIContext) {
//image description spec description waiting count
diff --git a/routers/api/v1/repo/modelmanage.go b/routers/api/v1/repo/modelmanage.go
index 3b0aed0d5..696231fea 100644
--- a/routers/api/v1/repo/modelmanage.go
+++ b/routers/api/v1/repo/modelmanage.go
@@ -4,8 +4,10 @@ import (
"net/http"
"code.gitea.io/gitea/modules/context"
+ "code.gitea.io/gitea/modules/convert"
"code.gitea.io/gitea/modules/log"
"code.gitea.io/gitea/modules/storage"
+ api "code.gitea.io/gitea/modules/structs"
routerRepo "code.gitea.io/gitea/routers/repo"
)
@@ -54,6 +56,21 @@ func QueryModelListForPredict(ctx *context.APIContext) {
routerRepo.QueryModelListForPredict(ctx.Context)
}
+func QueryTrainJobList(ctx *context.APIContext) {
+ result, err := routerRepo.QueryTrainJobListApi(ctx.Context)
+ if err != nil {
+ log.Info("query error." + err.Error())
+ ctx.JSON(http.StatusOK, nil)
+ } else {
+ re := make([]*api.Cloudbrain, 0)
+ for _, task := range result {
+ conRe := convert.ToCloudBrain(task)
+ re = append(re, conRe)
+ }
+ ctx.JSON(http.StatusOK, re)
+ }
+}
+
func QueryTrainModelList(ctx *context.APIContext) {
result, err := routerRepo.QueryTrainModelFileById(ctx.Context)
if err != nil {
@@ -63,6 +80,21 @@ func QueryTrainModelList(ctx *context.APIContext) {
ctx.JSON(http.StatusOK, re)
}
+func QueryTrainJobVersionList(ctx *context.APIContext) {
+ result, err := routerRepo.QueryTrainJobVersionListApi(ctx.Context)
+ if err != nil {
+ log.Info("query error." + err.Error())
+ ctx.JSON(http.StatusOK, nil)
+ } else {
+ re := make([]*api.Cloudbrain, 0)
+ for _, task := range result {
+ conRe := convert.ToCloudBrain(task)
+ re = append(re, conRe)
+ }
+ ctx.JSON(http.StatusOK, re)
+ }
+}
+
func convertFileFormat(result []storage.FileInfo) []FileInfo {
re := make([]FileInfo, 0)
if result != nil {
diff --git a/routers/repo/ai_model_manage.go b/routers/repo/ai_model_manage.go
index 592194371..a074119fc 100644
--- a/routers/repo/ai_model_manage.go
+++ b/routers/repo/ai_model_manage.go
@@ -2,7 +2,6 @@ package repo
import (
"archive/zip"
- "code.gitea.io/gitea/services/repository"
"encoding/json"
"errors"
"fmt"
@@ -12,6 +11,8 @@ import (
"regexp"
"strings"
+ "code.gitea.io/gitea/services/repository"
+
"code.gitea.io/gitea/models"
"code.gitea.io/gitea/modules/context"
"code.gitea.io/gitea/modules/log"
@@ -710,36 +711,42 @@ func downloadFromCloudBrainTwo(path string, task *models.AiModelManage, ctx *con
}
func QueryTrainJobVersionList(ctx *context.Context) {
+
+ VersionListTasks, err := QueryTrainJobVersionListApi(ctx)
+ if err != nil {
+ ctx.JSON(200, nil)
+ } else {
+ ctx.JSON(200, VersionListTasks)
+ }
+}
+
+func QueryTrainJobVersionListApi(ctx *context.Context) ([]*models.Cloudbrain, error) {
log.Info("query train job version list. start.")
JobID := ctx.Query("jobId")
if JobID == "" {
JobID = ctx.Query("JobId")
}
-
VersionListTasks, count, err := models.QueryModelTrainJobVersionList(JobID)
-
log.Info("query return count=" + fmt.Sprint(count))
+ return VersionListTasks, err
+}
+
+func QueryTrainJobList(ctx *context.Context) {
+ VersionListTasks, err := QueryTrainJobListApi(ctx)
if err != nil {
- ctx.ServerError("QueryTrainJobList:", err)
+ ctx.JSON(200, nil)
} else {
ctx.JSON(200, VersionListTasks)
}
}
-func QueryTrainJobList(ctx *context.Context) {
- log.Info("query train job list. start.")
+func QueryTrainJobListApi(ctx *context.Context) ([]*models.Cloudbrain, error) {
repoId := ctx.QueryInt64("repoId")
-
VersionListTasks, count, err := models.QueryModelTrainJobList(repoId)
log.Info("query return count=" + fmt.Sprint(count))
- if err != nil {
- ctx.ServerError("QueryTrainJobList:", err)
- } else {
- ctx.JSON(200, VersionListTasks)
- }
-
+ return VersionListTasks, err
}
func QueryTrainModelFileById(ctx *context.Context) ([]storage.FileInfo, error) {
diff --git a/routers/repo/cloudbrain.go b/routers/repo/cloudbrain.go
index 24d1a9e91..b01c0ade8 100755
--- a/routers/repo/cloudbrain.go
+++ b/routers/repo/cloudbrain.go
@@ -923,10 +923,13 @@ func cloudBrainShow(ctx *context.Context, tpName base.TplName, jobType models.Jo
func CloudBrainDebug(ctx *context.Context) {
task := ctx.Cloudbrain
debugUrl := setting.DebugServerHost + "jpylab_" + task.JobID + "_" + task.SubTaskName
- if task.BootFile != "" {
- ctx.Redirect(getFileUrl(debugUrl, task.BootFile))
+ if ctx.QueryTrim("file") != "" {
+ ctx.Redirect(getFileUrl(debugUrl, ctx.QueryTrim("file")))
} else {
+ if task.BootFile != "" {
+ go cloudbrainTask.UploadNotebookFiles(task)
+ }
ctx.Redirect(debugUrl)
}
@@ -1650,6 +1653,21 @@ func CloudBrainDownloadModel(ctx *context.Context) {
ctx.Resp.Header().Set("Cache-Control", "max-age=0")
http.Redirect(ctx.Resp, ctx.Req.Request, url, http.StatusMovedPermanently)
}
+
+func CloudBrainDownloadMultiModel(ctx *context.Context) {
+ parentDir := ctx.Query("parentDir")
+ jobName := ctx.Query("jobName")
+ filePath := "jobs/" + jobName + "/model/" + parentDir
+ allFile, err := storage.GetAllObjectByBucketAndPrefixMinio(setting.Attachment.Minio.Bucket, filePath)
+ if err == nil {
+ returnFileName := jobName + ".zip"
+ MinioDownloadManyFile(filePath, ctx, returnFileName, allFile)
+ } else {
+ log.Info("error,msg=" + err.Error())
+ ctx.ServerError("no file to download.", err)
+ }
+}
+
func CloudBrainDownloadInferenceResult(ctx *context.Context) {
parentDir := ctx.Query("parentDir")
fileName := ctx.Query("fileName")
diff --git a/routers/repo/modelarts.go b/routers/repo/modelarts.go
index 48f6f703b..1ddef4ffc 100755
--- a/routers/repo/modelarts.go
+++ b/routers/repo/modelarts.go
@@ -455,9 +455,13 @@ func NotebookDebug2(ctx *context.Context) {
ctx.RenderWithErr(err.Error(), tplModelArtsNotebookIndex, nil)
return
}
- if task.BootFile != "" {
- ctx.Redirect(getFileUrl(result.Url, task.BootFile) + "?token=" + result.Token)
+
+ if ctx.QueryTrim("file") != "" {
+ ctx.Redirect(getFileUrl(result.Url, ctx.QueryTrim("file")) + "?token=" + result.Token)
} else {
+ if task.BootFile != "" {
+ go cloudbrainTask.UploadNotebookFiles(task)
+ }
ctx.Redirect(result.Url + "?token=" + result.Token)
}
@@ -479,7 +483,7 @@ func getFileUrl(url string, filename string) string {
}
}
- return url + middle + path.Base(filename)
+ return url + middle + filename
}
func NotebookRestart(ctx *context.Context) {
@@ -646,7 +650,7 @@ func NotebookStop(ctx *context.Context) {
if task.Status != string(models.ModelArtsRunning) {
log.Error("the job(%s) is not running", task.JobName, ctx.Data["MsgID"])
resultCode = "-1"
- errorMsg = "the job is not running"
+ errorMsg = ctx.Tr("cloudbrain.Already_stopped")
break
}
@@ -2669,6 +2673,44 @@ func InferenceJobShow(ctx *context.Context) {
ctx.HTML(http.StatusOK, tplModelArtsInferenceJobShow)
}
+func MultiModelDownload(ctx *context.Context) {
+ var (
+ err error
+ )
+ jobID := ctx.Params(":jobid")
+ versionName := ctx.Query("version_name")
+ parentDir := ctx.Query("parent_dir")
+
+ task, err := models.GetCloudbrainByJobIDAndVersionName(jobID, versionName)
+ if err != nil {
+ log.Error("GetCloudbrainByJobIDAndVersionName(%s) failed:%v", task.JobName, err.Error())
+ return
+ }
+
+ if task.ComputeResource == models.NPUResource {
+ path := strings.TrimPrefix(path.Join(setting.TrainJobModelPath, task.JobName, setting.OutPutPath, versionName, parentDir), "/")
+ allFile, err := storage.GetAllObjectByBucketAndPrefix(setting.Bucket, path)
+ if err == nil {
+ returnFileName := task.DisplayJobName + ".zip"
+ ObsDownloadManyFile(path, ctx, returnFileName, allFile)
+ } else {
+ log.Info("error,msg=" + err.Error())
+ ctx.ServerError("no file to download.", err)
+ }
+ } else if task.ComputeResource == models.GPUResource {
+ filePath := setting.CBCodePathPrefix + task.JobName + cloudbrain.ModelMountPath + "/" + parentDir
+ allFile, err := storage.GetAllObjectByBucketAndPrefixMinio(setting.Attachment.Minio.Bucket, filePath)
+ if err == nil {
+ returnFileName := task.DisplayJobName + ".zip"
+ MinioDownloadManyFile(filePath, ctx, returnFileName, allFile)
+ } else {
+ log.Info("error,msg=" + err.Error())
+ ctx.ServerError("no file to download.", err)
+ }
+ }
+
+}
+
func ModelDownload(ctx *context.Context) {
var (
err error
diff --git a/routers/routes/routes.go b/routers/routes/routes.go
index 063a20999..7bc5f08c3 100755
--- a/routers/routes/routes.go
+++ b/routers/routes/routes.go
@@ -1186,6 +1186,7 @@ func RegisterRoutes(m *macaron.Macaron) {
m.Get("/rate", reqRepoCloudBrainReader, repo.GetRate)
m.Get("/models", reqRepoCloudBrainReader, repo.CloudBrainShowModels)
m.Get("/download_model", cloudbrain.AdminOrJobCreaterRight, repo.CloudBrainDownloadModel)
+ m.Get("/download_multi_model", cloudbrain.AdminOrJobCreaterRight, repo.CloudBrainDownloadMultiModel)
})
m.Get("/create", reqWechatBind, reqRepoCloudBrainWriter, context.PointAccount(), repo.CloudBrainNew)
m.Post("/create", reqWechatBind, reqRepoCloudBrainWriter, bindIgnErr(auth.CreateCloudBrainForm{}), repo.CloudBrainCreate)
@@ -1209,6 +1210,7 @@ func RegisterRoutes(m *macaron.Macaron) {
m.Post("/del", cloudbrain.AdminOrOwnerOrJobCreaterRightForTrain, repo.CloudBrainTrainJobDel)
//m.Get("/models", reqRepoCloudBrainReader, repo.CloudBrainShowModels)
m.Get("/download_model", cloudbrain.AdminOrOwnerOrJobCreaterRightForTrain, repo.CloudBrainDownloadModel)
+ m.Get("/download_multi_model", cloudbrain.AdminOrJobCreaterRight, repo.CloudBrainDownloadMultiModel)
//m.Get("/get_log", cloudbrain.AdminOrJobCreaterRightForTrain, repo.GetLogFromModelDir)
//m.Post("/create_version", reqWechatBind, cloudbrain.AdminOrJobCreaterRightForTrain, bindIgnErr(auth.CreateModelArtsTrainJobForm{}), repo.TrainJobCreateVersion)
m.Get("/create_version", reqWechatBind, cloudbrain.AdminOrJobCreaterRightForTrain, repo.CloudBrainTrainJobVersionNew)
@@ -1221,7 +1223,7 @@ func RegisterRoutes(m *macaron.Macaron) {
m.Group("/:jobid", func() {
m.Get("", reqRepoCloudBrainReader, repo.InferenceCloudBrainJobShow)
m.Get("/result_download", cloudbrain.AdminOrJobCreaterRightForTrain, repo.CloudBrainDownloadInferenceResult)
-
+ m.Get("/download_multi_model", cloudbrain.AdminOrJobCreaterRight, repo.CloudBrainDownloadMultiModel)
m.Get("/downloadall", repo.DownloadInferenceResultFile)
})
m.Get("/create", reqWechatBind, reqRepoCloudBrainWriter, context.PointAccount(), repo.InferenceCloudBrainJobNew)
diff --git a/services/cloudbrain/cloudbrainTask/notebook.go b/services/cloudbrain/cloudbrainTask/notebook.go
index cc9563520..3526f6549 100644
--- a/services/cloudbrain/cloudbrainTask/notebook.go
+++ b/services/cloudbrain/cloudbrainTask/notebook.go
@@ -4,6 +4,9 @@ import (
"fmt"
"net/http"
"path"
+ "strings"
+
+ "code.gitea.io/gitea/modules/notebook"
"code.gitea.io/gitea/modules/modelarts"
"code.gitea.io/gitea/modules/modelarts_cd"
@@ -29,6 +32,9 @@ import (
)
const NoteBookExtension = ".ipynb"
+const CPUType = 0
+const GPUType = 1
+const NPUType = 2
func FileNotebookCreate(ctx *context.Context, option api.CreateFileNotebookJobOption) {
@@ -66,7 +72,7 @@ func FileNotebookCreate(ctx *context.Context, option api.CreateFileNotebookJobOp
}
//create repo if not exist
- repo, err := models.GetRepositoryByName(ctx.User.ID, setting.FileNoteBook.ProjectName)
+ repo, _ := models.GetRepositoryByName(ctx.User.ID, setting.FileNoteBook.ProjectName)
if repo == nil {
repo, err = repo_service.CreateRepository(ctx.User, ctx.User, models.CreateRepoOptions{
Name: setting.FileNoteBook.ProjectName,
@@ -80,19 +86,222 @@ func FileNotebookCreate(ctx *context.Context, option api.CreateFileNotebookJobOp
AutoInit: true,
DefaultBranch: "master",
})
+ if err != nil {
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("repo.failed_to_create_notebook_repo", setting.FileNoteBook.ProjectName)))
+ return
+ }
+ } else {
+
+ noteBook, _ := models.GetWaitOrRunFileNotebookByRepo(repo.ID, getCloudbrainType(option.Type))
+ if noteBook != nil {
+
+ if isRepoConfilcts(option, noteBook) {
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("repo.notebook_repo_conflict")))
+ return
+ }
+
+ if isNotebookSpecMath(option, noteBook) {
+ if !isRepoMatch(option, noteBook) {
+ err = downloadCode(sourceRepo, getCodePath(noteBook.JobName, sourceRepo), option.BranchName)
+ if err != nil {
+ log.Error("download code failed", err)
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("cloudbrain.load_code_failed")))
+ return
+ }
+ }
+ if !isRepoFileMatch(option, noteBook) {
+ noteBook.BootFile += ";" + getBootFile(option.File, option.OwnerName, option.ProjectName)
+ noteBook.BranchName += ";" + option.BranchName
+ noteBook.Description += ";" + getDescription(option)
+
+ err := models.UpdateJob(noteBook)
+ if err != nil {
+ log.Error("GenerateNotebook2 failed, %v", err, ctx.Data["MsgID"])
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(err.Error()))
+ return
+ }
+ }
+
+ ctx.JSON(http.StatusOK, models.BaseMessageApi{
+ Code: 0,
+ Message: noteBook.JobID,
+ })
+ return
+ }
+
+ }
+ }
+
+ if option.Type <= GPUType {
+ cloudBrainFileNoteBookCreate(ctx, option, repo, sourceRepo)
+ } else {
+ modelartsFileNoteBookCreate(ctx, option, repo, sourceRepo)
+ }
+
+}
+func FileNotebookStatus(ctx *context.Context, option api.CreateFileNotebookJobOption) {
+ if ctx.Written() {
+ return
}
+
+ if path.Ext(option.File) != NoteBookExtension {
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("repo.notebook_select_wrong")))
+ return
+ }
+
+ isNotebookFileExist, _ := isNoteBookFileExist(ctx, option)
+ if !isNotebookFileExist {
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("repo.notebook_file_not_exist")))
+ return
+ }
+
+ task, err := models.GetCloudbrainByJobID(option.JobId)
if err != nil {
- ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("repo.failed_to_create_notebook_repo", setting.FileNoteBook.ProjectName)))
+ log.Error("job not found:"+option.JobId, err)
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi("Job id may not be right. can not find job."))
return
}
- if option.Type <= 1 {
- cloudBrainFileNoteBookCreate(ctx, option, repo, sourceRepo)
+ if task.BootFile == "" || task.Status != string(models.ModelArtsRunning) {
+ log.Warn("Boot file is empty or status is running. ")
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi("Boot file is empty or status is running."))
+ return
+ }
+ if !isRepoFileMatch(option, task) {
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi("can not math repo file."))
+ return
+ }
+ debugBaseUrl, token, err := getBaseUrlAndToken(task)
+ if err != nil {
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(err.Error()))
+ return
+ }
+
+ if uploadNotebookFileIfCannotBroswer(debugBaseUrl, getBootFile(option.File, option.OwnerName, option.ProjectName), task, token) {
+ ctx.JSON(http.StatusOK, models.BaseOKMessageApi)
} else {
- modelartsFileNoteBookCreate(ctx, option, repo, sourceRepo)
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi("upload failed."))
+
+ }
+
+}
+
+func getBaseUrlAndToken(task *models.Cloudbrain) (string, string, error) {
+ var debugBaseUrl string
+ var token string
+ if task.Type == models.TypeCloudBrainOne {
+ debugBaseUrl = setting.DebugServerHost + "jpylab_" + task.JobID + "_" + task.SubTaskName + "/lab"
+
+ } else {
+ var result *models.GetNotebook2Result
+ var err error
+ if task.Type == models.TypeCloudBrainTwo {
+ result, err = modelarts.GetNotebook2(task.JobID)
+ } else if task.Type == models.TypeCDCenter {
+ result, err = modelarts_cd.GetNotebook(task.JobID)
+ }
+ if err != nil || result == nil || result.Status != string(models.ModelArtsRunning) || result.Url == "" {
+ log.Error("notebook job not found:"+task.JobID, err)
+ return "", "", fmt.Errorf("can not get job or job is invalid.")
+ }
+
+ debugBaseUrl = result.Url
+ token = result.Token
+
}
+ return debugBaseUrl, token, nil
+}
+
+func uploadNotebookFileIfCannotBroswer(debugBaseUrl string, bootFile string, task *models.Cloudbrain, token string) bool {
+ c := ¬ebook.NotebookContent{
+ Url: debugBaseUrl,
+ Path: bootFile,
+ PathType: "file",
+ Token: token,
+ }
+ if c.IsNotebookFileCanBrowser() {
+ return true
+ } else {
+ c.SetCookiesAndCsrf()
+ c.UploadNoteBookFile(task)
+ return c.IsNotebookFileCanBrowser()
+ }
+
+}
+
+func isNotebookSpecMath(option api.CreateFileNotebookJobOption, book *models.Cloudbrain) bool {
+ if option.Type == NPUType || option.Type == CPUType {
+ return true
+ }
+ spec, err := models.GetCloudbrainSpecByID(book.ID)
+ if err != nil {
+ log.Warn("can not get spec ", err)
+ return false
+ }
+ return spec.AccCardsNum > 0
+}
+
+func isRepoConfilcts(option api.CreateFileNotebookJobOption, book *models.Cloudbrain) bool {
+ bootFiles := strings.Split(book.BootFile, ";")
+ branches := strings.Split(book.BranchName, ";")
+
+ for i, bootFile := range bootFiles {
+ splits := strings.Split(bootFile, "/")
+ if len(splits) >= 3 {
+ if splits[0] == option.OwnerName && splits[1] == option.ProjectName && branches[i] != option.BranchName {
+ return true
+ }
+ }
+ }
+
+ return false
}
+func isRepoMatch(option api.CreateFileNotebookJobOption, book *models.Cloudbrain) bool {
+ bootFiles := strings.Split(book.BootFile, ";")
+
+ for _, bootFile := range bootFiles {
+ splits := strings.Split(bootFile, "/")
+ if len(splits) >= 3 {
+ if splits[0] == option.OwnerName && splits[1] == option.ProjectName {
+ return true
+ }
+ }
+ }
+ return false
+
+}
+
+func isRepoFileMatch(option api.CreateFileNotebookJobOption, book *models.Cloudbrain) bool {
+ bootFiles := strings.Split(book.BootFile, ";")
+ branches := strings.Split(book.BranchName, ";")
+
+ for i, bootFile := range bootFiles {
+ if branches[i] == option.BranchName && getBootFile(option.File, option.OwnerName, option.ProjectName) == bootFile {
+ return true
+ }
+ }
+
+ return false
+
+}
+func UploadNotebookFiles(task *models.Cloudbrain) {
+ if task.Status == string(models.JobRunning) && task.BootFile != "" {
+
+ debugBaseUrl, token, err := getBaseUrlAndToken(task)
+ if err != nil {
+ log.Error("can not get base url:", err)
+ return
+ }
+ bootFiles := strings.Split(task.BootFile, ";")
+
+ for _, bootFile := range bootFiles {
+ uploadNotebookFileIfCannotBroswer(debugBaseUrl, bootFile, task, token)
+ }
+
+ }
+}
+
func cloudBrainFileNoteBookCreate(ctx *context.Context, option api.CreateFileNotebookJobOption, repo *models.Repository, sourceRepo *models.Repository) {
displayJobName := cloudbrainService.GetDisplayJobName(ctx.User.Name)
@@ -131,17 +340,18 @@ func cloudBrainFileNoteBookCreate(ctx *context.Context, option api.CreateFileNot
} else {
if count >= 1 {
log.Error("the user already has running or waiting task", ctx.Data["MsgID"])
- ctx.JSON(http.StatusOK,models.BaseMessageApi{
- Code: 2,
+ ctx.JSON(http.StatusOK, models.BaseMessageApi{
+ Code: 2,
Message: ctx.Tr("repo.cloudbrain.morethanonejob"),
})
return
}
}
- errStr := uploadCodeFile(sourceRepo, getCodePath(jobName), option.BranchName, option.File, jobName)
- if errStr != "" {
- ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("repo.notebook_file_not_exist")))
+ err = downloadCode(sourceRepo, getCodePath(jobName, sourceRepo), option.BranchName)
+ if err != nil {
+ log.Error("download code failed", err)
+ ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("cloudbrain.load_code_failed")))
return
}
command := cloudbrain.GetCloudbrainDebugCommand()
@@ -185,7 +395,7 @@ func cloudBrainFileNoteBookCreate(ctx *context.Context, option api.CreateFileNot
JobType: jobType,
Description: getDescription(option),
BranchName: option.BranchName,
- BootFile: option.File,
+ BootFile: getBootFile(option.File, option.OwnerName, option.ProjectName),
Params: "{\"parameter\":[]}",
CommitID: "",
BenchmarkTypeID: 0,
@@ -206,8 +416,18 @@ func cloudBrainFileNoteBookCreate(ctx *context.Context, option api.CreateFileNot
}
-func getCodePath(jobName string) string {
- return setting.JobPath + jobName + cloudbrain.CodeMountPath
+func getCloudbrainType(optionType int) int {
+ if optionType < 1 {
+ return models.TypeCloudBrainOne
+ }
+ if setting.ModelartsCD.Enabled {
+ return models.TypeCDCenter
+ }
+ return models.TypeCloudBrainTwo
+}
+
+func getCodePath(jobName string, repo *models.Repository) string {
+ return setting.JobPath + jobName + cloudbrain.CodeMountPath + "/" + repo.OwnerName + "/" + repo.Name
}
func getDescription(option api.CreateFileNotebookJobOption) string {
@@ -237,8 +457,8 @@ func modelartsFileNoteBookCreate(ctx *context.Context, option api.CreateFileNote
} else {
if count >= 1 {
log.Error("the user already has running or waiting task", ctx.Data["MsgID"])
- ctx.JSON(http.StatusOK,models.BaseMessageApi{
- Code: 2,
+ ctx.JSON(http.StatusOK, models.BaseMessageApi{
+ Code: 2,
Message: ctx.Tr("repo.cloudbrain.morethanonejob"),
})
return
@@ -260,7 +480,7 @@ func modelartsFileNoteBookCreate(ctx *context.Context, option api.CreateFileNote
}
}
- err = downloadCode(sourceRepo, getCodePath(jobName), option.BranchName)
+ err = downloadCode(sourceRepo, getCodePath(jobName, sourceRepo), option.BranchName)
if err != nil {
ctx.JSON(http.StatusOK, models.BaseErrorMessageApi(ctx.Tr("cloudbrain.load_code_failed")))
return
@@ -297,8 +517,9 @@ func modelartsFileNoteBookCreate(ctx *context.Context, option api.CreateFileNote
Description: getDescription(option),
ImageId: setting.FileNoteBook.ImageIdNPU,
Spec: spec,
- BootFile: "",
+ BootFile: getBootFile(option.File, option.OwnerName, option.ProjectName),
AutoStopDurationMs: modelarts.AutoStopDurationMs / 4,
+ BranchName: option.BranchName,
}
if setting.ModelartsCD.Enabled {
@@ -347,17 +568,8 @@ func isNoteBookFileExist(ctx *context.Context, option api.CreateFileNotebookJobO
return true, nil
}
-func uploadCodeFile(repo *models.Repository, codePath string, branchName string, filePath string, jobName string) string {
- err := downloadCode(repo, codePath, branchName)
- if err != nil {
- return "cloudbrain.load_code_failed"
- }
-
- err = uploadOneFileToMinio(codePath, filePath, jobName, cloudbrain.CodeMountPath+"/")
- if err != nil {
- return "cloudbrain.load_code_failed"
- }
- return ""
+func getBootFile(filePath string, ownerName string, projectName string) string {
+ return ownerName + "/" + projectName + "/" + filePath
}
func fileExists(gitRepo *git.Repository, path string, branch string) (bool, error) {
diff --git a/web_src/vuepages/apis/modules/notobook.js b/web_src/vuepages/apis/modules/notobook.js
index 4c59a253b..1dd35e337 100644
--- a/web_src/vuepages/apis/modules/notobook.js
+++ b/web_src/vuepages/apis/modules/notobook.js
@@ -29,7 +29,7 @@ export const getCb1Notebook = (path,jobid) => {
});
};
-// Notebook获取云脑I调试任务状态
+// Notebook获取云脑II调试任务状态
export const getCb2Notebook = (path,jobid) => {
return service({
url: `/api/v1/${path}/modelarts/notebook/${jobid}`,
@@ -37,7 +37,16 @@ export const getCb2Notebook = (path,jobid) => {
params: {},
});
};
-
+// Notebook查询文件在环境中是否已准备好
+// type, file, branch_name, owner_name, project_name,job_id
+export const getFileInfoNotebook = (data) => {
+ return service({
+ url: "/api/v1/file_notebook/status",
+ method: "post",
+ data,
+ params: {},
+ });
+};
export const stopNotebook = (url) => {
return service({
url: url,
diff --git a/web_src/vuepages/pages/notebook/debug/index.vue b/web_src/vuepages/pages/notebook/debug/index.vue
index 20af220f5..a4c93529a 100644
--- a/web_src/vuepages/pages/notebook/debug/index.vue
+++ b/web_src/vuepages/pages/notebook/debug/index.vue
@@ -178,9 +178,9 @@