fix: Complete the modelarts createServeic of ai

Signed-off-by: jagger <cossjie@foxmail.com>

.gitignore

@@ -25,3 +25,4 @@ configs/tenanter.yaml
 
 log/
 /cache/
+/vendor/

desc/ai/pcm-ai.api

@@ -1827,8 +1827,8 @@ service AICore-api {
 
 type (
 	ChatReq{
-		ApiUrl   string `json:"apiUrl"`
-		Method   string `json:"method,optional"`
+		id      uint `json:"id,string"`
+		Method  string `json:"method,optional"`
 		ReqData map[string]interface{} `json:"reqData"`
 	}
 	ChatResult{

desc/core/pcm-core.api

@@ -790,7 +790,14 @@ type (
 		CreateTime string `json:"createTime,omitempty" db:"create_time" gorm:"autoCreateTime"`
 	}
 	AdapterResp {
-		Data AdapterInfo `json:"data,omitempty"`
+		Id         string `json:"id,omitempty" db:"id"`
+		Name       string `json:"name,omitempty" db:"name"`
+		Type       string `json:"type,omitempty" db:"type"`
+		ResourceType string `json:"resourceType,omitempty" db:"resource_type"`
+		Nickname   string `json:"nickname,omitempty" db:"nickname"`
+		Version    string `json:"version,omitempty" db:"version"`
+		Server     string `json:"server,omitempty" db:"server"`
+		CreateTime string `json:"createTime,omitempty" db:"create_time" gorm:"autoCreateTime"`
 	}
 	AdapterListResp {
 		List []AdapterInfo `json:"list,omitempty"`

desc/inference/inference.api

@@ -1,6 +1,25 @@
 syntax = "v1"
 
 type (
+     /******************image inference*************************/
+     DeployInstance {
+          Id string `json:"id"`
+          DeployTaskId string `json:"deployTaskId"`
+          InstanceId string `json:"instanceId"`
+          InstanceName string `json:"instanceName"`
+          AdapterId string `json:"adapterId"`
+          AdapterName string `json:"adapterName"`
+          ClusterId string `json:"clusterId"`
+          ClusterName string `json:"clusterName"`
+          ModelName string `json:"modelName"`
+          ModelType string `json:"modelType"`
+          InferCard string `json:"inferCard"`
+          Status string `json:"status"`
+          CreateTime string `json:"createTime"`
+          UpdateTime string `json:"updateTime"`
+          ClusterType string `json:"clusterType"`
+     }
+
      /******************image inference*************************/
      ModelTypesResp {
           ModelTypes []string `json:"types"`
@@ -18,17 +37,10 @@ type (
      ImageInferenceReq {
           TaskName string `form:"taskName"`
           TaskDesc string `form:"taskDesc"`
-          ModelName string `form:"modelName"`
           ModelType string `form:"modelType"`
-          AdapterId string `form:"adapterId"`
-          AiClusterIds []string `form:"aiClusterIds,optional"`
-          ResourceType string `form:"resourceType,optional"`
-          ComputeCard string `form:"card,optional"`
-          Strategy string `form:"strategy"`
-          StaticWeightMap map[string]int32 `form:"staticWeightMap,optional"`
-          Params []string `form:"params,optional"`
-          Envs   []string `form:"envs,optional"`
-          Cmd string `form:"cmd,optional"`
+          InstanceIds []int64 `form:"instanceIds"`
+          Strategy string `form:"strategy,,optional"`
+          StaticWeightMap map[string]map[string]int32 `form:"staticWeightMap,optional"`
           Replica     int32     `form:"replicas,optional"`
      }
 
@@ -76,6 +88,18 @@ type (
 
      }
 
+     /******************TextToImage inference*************************/
+     TextToImageInferenceReq{
+          TaskName string `form:"taskName"`
+          TaskDesc string `form:"taskDesc"`
+          ModelName string `form:"modelName"`
+          ModelType string `form:"modelType"`
+          AiClusterIds []string `form:"aiClusterIds"`
+     }
+     TextToImageInferenceResp{
+          Result []byte `json:"result"`
+     }
+
      /******************Deploy instance*************************/
      DeployInstanceListReq{
           PageInfo
@@ -120,4 +144,70 @@ type (
           Running int32 `json:"running"`
           Total int32 `json:"total"`
      }
+
+     StartAllByDeployTaskIdReq {
+          Id      string `json:"deployTaskId"`
+     }
+
+     StartAllByDeployTaskIdResp {
+
+     }
+
+     StopAllByDeployTaskIdReq {
+          Id      string `json:"deployTaskId"`
+     }
+
+     StopAllByDeployTaskIdResp {
+
+     }
+
+     GetRunningInstanceReq {
+          Id      string `form:"deployTaskId"`
+          AdapterId      string `form:"adapterId"`
+     }
+     GetRunningInstanceResp {
+          List     interface{} `json:"list"`
+     }
+
+     GetDeployTasksByTypeReq {
+          ModelType string `form:"modelType"`
+     }
+
+     GetDeployTasksByTypeResp {
+          List     interface{} `json:"list"`
+     }
+
+     CreateDeployTaskReq {
+          TaskName string `form:"taskName"`
+          TaskDesc string `form:"taskDesc"`
+          ModelName string `form:"modelName"`
+          ModelType string `form:"modelType"`
+          AdapterClusterMap map[string][]string `form:"adapterClusterMap"`
+     }
+
+     CreateDeployTaskResp {
+
+     }
+
+     GetAdaptersByModelReq {
+          ModelName string `form:"modelName"`
+          ModelType string `form:"modelType"`
+     }
+
+     GetAdaptersByModelResp {
+          Adapters []*AdapterAvail `json:"adapters"`
+     }
+
+     AdapterAvail {
+          AdapterId string `json:"adapterId"`
+          AdapterName string `json:"taskName"`
+          Clusters []*ClusterAvail `json:"clusters"`
+     }
+
+     ClusterAvail {
+          ClusterId string `json:"clusterId"`
+          ClusterName string `json:"clusterName"`
+     }
+
+
 )

desc/pcm.api

@@ -386,8 +386,8 @@ service pcm {
 
 	/***********chat***********/
 	@doc "文本识别"
-	@handler ProxyApiHandler
-	post /ai/chat (ChatReq) returns (CommonResp)
+	@handler ChatHandler
+	post /ai/chat (ChatReq) returns (ChatResult)
 	/******chat end***********/
 }
 
@@ -959,6 +959,24 @@ service pcm {
 
 	@handler InferenceTaskStatHandler
 	get /inference/taskStat (InferenceTaskStatReq) returns (InferenceTaskStatResp)
+
+	@handler StartAllByDeployTaskId
+	post /inference/startAll (StartAllByDeployTaskIdReq) returns (StartAllByDeployTaskIdResp)
+
+	@handler StopAllByDeployTaskId
+	post /inference/stopAll (StopAllByDeployTaskIdReq) returns (StopAllByDeployTaskIdResp)
+
+	@handler GetRunningInstanceById
+	get /inference/getRunningInstanceById (GetRunningInstanceReq) returns (GetRunningInstanceResp)
+
+	@handler GetDeployTasksByType
+	get /inference/getDeployTasksByType (GetDeployTasksByTypeReq) returns (GetDeployTasksByTypeResp)
+
+	@handler CreateDeployTask
+	post /inference/createDeployTask (CreateDeployTaskReq) returns (CreateDeployTaskResp)
+
+	@handler GetAdaptersByModel
+	get /inference/getAdaptersByModel (GetAdaptersByModelReq) returns (GetAdaptersByModelResp)
 }
 
 @server(

go.mod

@@ -19,8 +19,8 @@ require (
 	github.com/robfig/cron/v3 v3.0.1
 	github.com/zeromicro/go-zero v1.6.6
 	gitlink.org.cn/JointCloud/pcm-ac v0.0.0-20240725071305-f751eec4dde1
-	gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240722092017-50d17f36d023
-	gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240718073732-bc5d687f6330
+	gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240724095608-1727d09f030c
+	gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240817071412-44397870b110
 	gitlink.org.cn/JointCloud/pcm-openstack v0.0.0-20240403033338-e7edabad4203
 	gitlink.org.cn/JointCloud/pcm-slurm v0.0.0-20240301080743-8b94bbaf57f5
 	gitlink.org.cn/jcce-pcm/pcm-participant-ceph v0.0.0-20230904090036-24fc730ec87d
@@ -37,7 +37,6 @@ require (
 
 require (
 	filippo.io/edwards25519 v1.1.0 // indirect
-	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/alecthomas/kingpin/v2 v2.4.0 // indirect
 	github.com/alecthomas/units v0.0.0-20231202071711-9a357b53e9c9 // indirect
 	github.com/armon/go-metrics v0.4.1 // indirect
@@ -51,14 +50,8 @@ require (
 	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
-	github.com/distribution/reference v0.6.0 // indirect
-	github.com/docker/distribution v2.8.3+incompatible // indirect
-	github.com/docker/docker v27.1.1+incompatible // indirect
-	github.com/docker/go-connections v0.5.0 // indirect
-	github.com/docker/go-units v0.5.0 // indirect
 	github.com/emicklei/go-restful/v3 v3.12.1 // indirect
 	github.com/fatih/color v1.17.0 // indirect
-	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/fsnotify/fsnotify v1.7.0 // indirect
 	github.com/go-kit/log v0.2.1 // indirect
 	github.com/go-logfmt/logfmt v0.6.0 // indirect
@@ -94,7 +87,6 @@ require (
 	github.com/hashicorp/golang-lru v0.6.0 // indirect
 	github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
 	github.com/hashicorp/memberlist v0.5.0 // indirect
-	github.com/huaweicloud/huaweicloud-sdk-go-v3 v0.1.106 // indirect
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
 	github.com/jmespath/go-jmespath v0.4.0 // indirect
@@ -108,15 +100,12 @@ require (
 	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
 	github.com/miekg/dns v1.1.58 // indirect
 	github.com/mitchellh/mapstructure v1.5.0 // indirect
-	github.com/moby/docker-image-spec v1.3.1 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
 	github.com/oklog/run v1.1.0 // indirect
 	github.com/oklog/ulid v1.3.1 // indirect
-	github.com/opencontainers/go-digest v1.0.0 // indirect
-	github.com/opencontainers/image-spec v1.1.0 // indirect
 	github.com/opentracing/opentracing-go v1.2.0 // indirect
 	github.com/openzipkin/zipkin-go v0.4.3 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.2 // indirect
@@ -135,7 +124,6 @@ require (
 	go.etcd.io/etcd/client/pkg/v3 v3.5.15 // indirect
 	go.etcd.io/etcd/client/v3 v3.5.15 // indirect
 	go.mongodb.org/mongo-driver v1.13.1 // indirect
-	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.53.0 // indirect
 	go.opentelemetry.io/otel v1.28.0 // indirect
 	go.opentelemetry.io/otel/exporters/jaeger v1.17.0 // indirect
 	go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.28.0 // indirect

go.sum

@@ -42,8 +42,6 @@ github.com/JCCE-nudt/apigw-go-sdk v0.0.0-20230525025609-34159d6f2818 h1:QLulhUyx
 github.com/JCCE-nudt/apigw-go-sdk v0.0.0-20230525025609-34159d6f2818/go.mod h1:j+am5/1URgsvyhOAyURFR9vH3malaW7Tq6d33OyPsnM=
 github.com/Masterminds/squirrel v1.5.4 h1:uUcX/aBc8O7Fg9kaISIUsHXdKuqehiXAMQTYX8afzqM=
 github.com/Masterminds/squirrel v1.5.4/go.mod h1:NNaOrjSoIDfDA40n7sr2tPNZRfjzjA400rg+riTZj10=
-github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
-github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
 github.com/alecthomas/kingpin/v2 v2.4.0 h1:f48lwail6p8zpO1bC4TxtqACaGqHYA22qkHjHpqDjYY=
 github.com/alecthomas/kingpin/v2 v2.4.0/go.mod h1:0gyi0zQnjuFk8xrkNKamJoyUo382HRL7ATRpFZCw6tE=
 github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
@@ -100,16 +98,6 @@ github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 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/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk=
-github.com/distribution/reference v0.6.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
-github.com/docker/distribution v2.8.3+incompatible h1:AtKxIZ36LoNK51+Z6RpzLpddBirtxJnzDrHLEKxTAYk=
-github.com/docker/distribution v2.8.3+incompatible/go.mod h1:J2gT2udsDAN96Uj4KfcMRqY0/ypR+oyYUYmja8H+y+w=
-github.com/docker/docker v27.1.1+incompatible h1:hO/M4MtV36kzKldqnA37IWhebRA+LnqqcqDja6kVaKY=
-github.com/docker/docker v27.1.1+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
-github.com/docker/go-connections v0.5.0 h1:USnMq7hx7gwdVZq1L49hLXaFtUdTADjXGp+uj1Br63c=
-github.com/docker/go-connections v0.5.0/go.mod h1:ov60Kzw0kKElRwhNs9UlUHAE/F9Fe6GLaXnqyDdmEXc=
-github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4=
-github.com/docker/go-units v0.5.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
 github.com/emicklei/go-restful/v3 v3.12.1 h1:PJMDIM/ak7btuL8Ex0iYET9hxM3CI2sjZtzpL63nKAU=
 github.com/emicklei/go-restful/v3 v3.12.1/go.mod h1:6n3XBCmQQb25CM2LCACGz8ukIrRry+4bhvbpWn3mrbc=
 github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
@@ -118,8 +106,6 @@ github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1m
 github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
 github.com/fatih/color v1.17.0 h1:GlRw1BRJxkpqUCBKzKOw098ed57fEsKeNjpTe3cSjK4=
 github.com/fatih/color v1.17.0/go.mod h1:YZ7TlrGPkiz6ku9fK3TLD/pl3CpsiFyu8N92HLgmosI=
-github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
-github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
 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/ghodss/yaml v1.0.0 h1:wQHKEahhL6wmXdzwWG11gIVCkOv05bNOh+Rxn0yngAk=
@@ -253,7 +239,6 @@ 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=
 github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
 github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
-github.com/grpc-ecosystem/grpc-gateway v1.16.0 h1:gmcG1KaJ57LophUzW0Hy8NmPhnMZb4M0+kPpLofRdBo=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0 h1:bkypFPDjIYGfCYD5mRBvpqxfYX1YCS1PXdKYWi8FsN0=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0/go.mod h1:P+Lt/0by1T8bfcF3z737NnSbmxQAppXMRziHUxPOC8k=
 github.com/h2non/parth v0.0.0-20190131123155-b4df798d6542 h1:2VTzZjLZBgl62/EtslCrtky5vbi9dd7HrQPQIx6wqiw=
@@ -285,8 +270,6 @@ github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs
 github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
 github.com/hashicorp/memberlist v0.5.0 h1:EtYPN8DpAURiapus508I4n9CzHs2W+8NZGbmmR/prTM=
 github.com/hashicorp/memberlist v0.5.0/go.mod h1:yvyXLpo0QaGE59Y7hDTsTzDD25JYBZ4mHgHUZ8lrOI0=
-github.com/huaweicloud/huaweicloud-sdk-go-v3 v0.1.106 h1:qjB7sACTAlHcwYKJgJB0kivPWpt7uujl/4YHFUHLpXc=
-github.com/huaweicloud/huaweicloud-sdk-go-v3 v0.1.106/go.mod h1:JWz2ujO9X3oU5wb6kXp+DpR2UuDj2SldDbX8T0FSuhI=
 github.com/ianlancetaylor/demangle v0.0.0-20181102032728-5e5cf60278f6/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
 github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
 github.com/jackc/pgpassfile v1.0.0/go.mod h1:CEx0iS5ambNFdcRtxPj5JhEz+xB6uRky5eyVu/W2HEg=
@@ -356,8 +339,6 @@ github.com/miekg/dns v1.1.58 h1:ca2Hdkz+cDg/7eNF6V56jjzuZ4aCAE+DbVkILdQWG/4=
 github.com/miekg/dns v1.1.58/go.mod h1:Ypv+3b/KadlvW9vJfXOTf300O4UqaHFzFCuHz+rPkBY=
 github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
 github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
-github.com/moby/docker-image-spec v1.3.1 h1:jMKff3w6PgbfSa69GfNg+zN/XLhfXJGnEx3Nl2EsFP0=
-github.com/moby/docker-image-spec v1.3.1/go.mod h1:eKmb5VW8vQEh/BAr2yvVNvuiJuY6UIocYsFu/DxxRpo=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
@@ -383,10 +364,6 @@ github.com/onsi/ginkgo/v2 v2.17.2 h1:7eMhcy3GimbsA3hEnVKdw/PQM9XN9krpKVXsZdph0/g
 github.com/onsi/ginkgo/v2 v2.17.2/go.mod h1:nP2DPOQoNsQmsVyv5rDA8JkXQoCs6goXIvr/PRJ1eCc=
 github.com/onsi/gomega v1.33.1 h1:dsYjIxxSR755MDmKVsaFQTE22ChNBcuuTWgkUDSubOk=
 github.com/onsi/gomega v1.33.1/go.mod h1:U4R44UsT+9eLIaYRB2a5qajjtQYn0hauxvRm16AVYg0=
-github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
-github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM=
-github.com/opencontainers/image-spec v1.1.0 h1:8SG7/vwALn54lVB/0yZ/MMwhFrPYtpEHQb2IpWsCzug=
-github.com/opencontainers/image-spec v1.1.0/go.mod h1:W4s4sFTMaBeK1BQLXbG4AdM2szdn85PY75RI83NrTrM=
 github.com/opentracing/opentracing-go v1.2.0 h1:uEJPy/1a5RIPAJ0Ov+OIO8OxWu77jEv+1B0VhjKrZUs=
 github.com/opentracing/opentracing-go v1.2.0/go.mod h1:GxEUsuufX4nBwe+T+Wl9TAgYrxe9dPLANfrWvHYVTgc=
 github.com/openzipkin/zipkin-go v0.4.3 h1:9EGwpqkgnwdEIJ+Od7QVSEIH+ocmm5nPat0G7sjsSdg=
@@ -475,7 +452,6 @@ github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
-github.com/tjfoc/gmsm v1.4.1/go.mod h1:j4INPkHWMrhJb38G+J6W4Tw0AbuN8Thu3PbdVYhVcTE=
 github.com/tv42/httpunix v0.0.0-20150427012821-b75d8614f926/go.mod h1:9ESjWnEqriFuLhtthL60Sar/7RFoluCcXsuvEwTV5KM=
 github.com/xdg-go/pbkdf2 v1.0.0/go.mod h1:jrpuAogTd400dnrH08LKmI/xc1MbPOebTwRqcT5RDeI=
 github.com/xdg-go/scram v1.1.2/go.mod h1:RT/sEzTbU5y00aCK8UOx6R7YryM0iF1N2MOmC3kKLN4=
@@ -497,12 +473,10 @@ github.com/zeromicro/go-zero v1.6.6 h1:nZTVYObklHiBdYJ/nPoAZ8kGVAplWSDjT7DGE7ur0
 github.com/zeromicro/go-zero v1.6.6/go.mod h1:olKf1/hELbSmuIgLgJeoeNVp3tCbLqj6UmO7ATSta4A=
 gitlink.org.cn/JointCloud/pcm-ac v0.0.0-20240725071305-f751eec4dde1 h1:DicBXoQiC6mumMBeyqSPNrsjtqJIgk5Pv2hscu2xryw=
 gitlink.org.cn/JointCloud/pcm-ac v0.0.0-20240725071305-f751eec4dde1/go.mod h1:3eECiw9O2bIFkkePlloKyLNXiqBAhOxNrDoGaaGseGY=
-gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240722092017-50d17f36d023 h1:9DNobl0gvRCSXtjyMsfUwq0w0TMvds4rqNRsEqeX4j8=
-gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240722092017-50d17f36d023/go.mod h1:/eOmBFZKWGoabG3sRVkVvIbLwsd2631k4jkUBR6x1AA=
 gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240724095608-1727d09f030c h1:CodJeGgTYJwA6NDHFnw6B+4pBXUl79tvAcECq39tgZI=
 gitlink.org.cn/JointCloud/pcm-modelarts v0.0.0-20240724095608-1727d09f030c/go.mod h1:/eOmBFZKWGoabG3sRVkVvIbLwsd2631k4jkUBR6x1AA=
-gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240718073732-bc5d687f6330 h1:WxPrFSO6LjDCr+k7nmNFlPst8CtoTHQ2iSjv+D2rNnM=
-gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240718073732-bc5d687f6330/go.mod h1:QOD5+/l2D+AYBjF2h5T0mdJyfGAmF78QmeKdbBXbjLQ=
+gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240817071412-44397870b110 h1:GaXwr5sgDh0raHjUf9IewTvnRvajYea7zbLsaerYyXo=
+gitlink.org.cn/JointCloud/pcm-octopus v0.0.0-20240817071412-44397870b110/go.mod h1:QOD5+/l2D+AYBjF2h5T0mdJyfGAmF78QmeKdbBXbjLQ=
 gitlink.org.cn/JointCloud/pcm-openstack v0.0.0-20240403033338-e7edabad4203 h1:s6PsZ1+bev294IWdZRlV7mnOwI1+UzFcldVW/BqhQzI=
 gitlink.org.cn/JointCloud/pcm-openstack v0.0.0-20240403033338-e7edabad4203/go.mod h1:i2rrbMQ+Fve345BY9Heh4MUqVTAimZQElQhzzRee5B8=
 gitlink.org.cn/JointCloud/pcm-slurm v0.0.0-20240301080743-8b94bbaf57f5 h1:+/5vnzkJBfMRnya1NrhOzlroUtRa5ePiYbPKlHLoLV0=
@@ -515,7 +489,6 @@ go.etcd.io/etcd/client/pkg/v3 v3.5.15 h1:fo0HpWz/KlHGMCC+YejpiCmyWDEuIpnTDzpJLB5
 go.etcd.io/etcd/client/pkg/v3 v3.5.15/go.mod h1:mXDI4NAOwEiszrHCb0aqfAYNCrZP4e9hRca3d1YK8EU=
 go.etcd.io/etcd/client/v3 v3.5.15 h1:23M0eY4Fd/inNv1ZfU3AxrbbOdW79r9V9Rl62Nm6ip4=
 go.etcd.io/etcd/client/v3 v3.5.15/go.mod h1:CLSJxrYjvLtHsrPKsy7LmZEE+DK2ktfd2bN4RhBMwlU=
-go.mongodb.org/mongo-driver v1.12.0/go.mod h1:AZkxhPnFJUoH7kZlFkVKucV20K387miPfm7oimrSmK0=
 go.mongodb.org/mongo-driver v1.13.1 h1:YIc7HTYsKndGK4RFzJ3covLz1byri52x0IoMB0Pt/vk=
 go.mongodb.org/mongo-driver v1.13.1/go.mod h1:wcDf1JBCXy2mOW0bWHwO/IOYqdca1MPCwDtFu/Z9+eo=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
@@ -523,8 +496,6 @@ go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
 go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
 go.opencensus.io v0.22.3/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
 go.opencensus.io v0.22.4/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
-go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.53.0 h1:4K4tsIXefpVJtvA/8srF4V4y0akAoPHkIslgAkjixJA=
-go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.53.0/go.mod h1:jjdQuTGVsXV4vSs+CJ2qYDeDPf9yIJV23qlIzBm73Vg=
 go.opentelemetry.io/otel v1.28.0 h1:/SqNcYk+idO0CxKEUOtKQClMK/MimZihKYMruSMViUo=
 go.opentelemetry.io/otel v1.28.0/go.mod h1:q68ijF8Fc8CnMHKyzqL6akLO46ePnjkgfIMIjUIX9z4=
 go.opentelemetry.io/otel/exporters/jaeger v1.17.0 h1:D7UpUy2Xc2wsi1Ras6V40q806WM07rqoCWzXu7Sqy+4=
@@ -564,12 +535,10 @@ golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8U
 golang.org/x/crypto v0.0.0-20190923035154-9ee001bba392/go.mod h1:/lpIB1dKB+9EgE3H3cr1v9wB50oz8l4C4h62xy7jSTY=
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.org/x/crypto v0.0.0-20201012173705-84dcc777aaee/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
 golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
-golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
 golang.org/x/crypto v0.25.0 h1:ypSNr+bnYL2YhwoMt2zPxHFmbAN1KZs/njMG3hxUp30=
 golang.org/x/crypto v0.25.0/go.mod h1:T+wALwcMOSE0kXgUAnPAHqTLW+XHgcELELW8VaDgm/M=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
@@ -638,7 +607,6 @@ golang.org/x/net v0.0.0-20200520182314-0ba52f642ac2/go.mod h1:qpuaurCH72eLCgpAm/
 golang.org/x/net v0.0.0-20200625001655-4c5254603344/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
-golang.org/x/net v0.0.0-20201010224723-4f7140c49acb/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/net v0.0.0-20201110031124-69a78807bb2b/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
@@ -725,7 +693,6 @@ golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.22.0 h1:RI27ohtqKCnwULzJLqkv897zojh5/DwS/ENaMzUOaWI=
 golang.org/x/sys v0.22.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
@@ -734,7 +701,6 @@ golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
 golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
 golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
 golang.org/x/term v0.18.0/go.mod h1:ILwASektA3OnRv7amZ1xhE/KTR+u50pbXfZ03+6Nx58=
-golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
 golang.org/x/term v0.22.0 h1:BbsgPEJULsl2fV/AT3v15Mjva5yXKQDyKf+TbDz7QJk=
 golang.org/x/term v0.22.0/go.mod h1:F3qCibpT5AMpCRfhfT53vVJwhLtIVHhB9XDjfFvnMI4=
 golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -748,7 +714,6 @@ golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
-golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
 golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
@@ -861,12 +826,8 @@ google.golang.org/genproto v0.0.0-20200618031413-b414f8b61790/go.mod h1:jDfRM7Fc
 google.golang.org/genproto v0.0.0-20200729003335-053ba62fc06f/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
 google.golang.org/genproto v0.0.0-20200804131852-c06518451d9c/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
 google.golang.org/genproto v0.0.0-20200825200019-8632dd797987/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
-google.golang.org/genproto/googleapis/api v0.0.0-20240722135656-d784300faade h1:WxZOF2yayUHpHSbUE6NMzumUzBxYc3YGwo0YHnbzsJY=
-google.golang.org/genproto/googleapis/api v0.0.0-20240722135656-d784300faade/go.mod h1:mw8MG/Qz5wfgYr6VqVCiZcHe/GJEfI+oGGDCohaVgB0=
 google.golang.org/genproto/googleapis/api v0.0.0-20240723171418-e6d459c13d2a h1:YIa/rzVqMEokBkPtydCkx1VLmv3An1Uw7w1P1m6EhOY=
 google.golang.org/genproto/googleapis/api v0.0.0-20240723171418-e6d459c13d2a/go.mod h1:AHT0dDg3SoMOgZGnZk29b5xTbPHMoEC8qthmBLJCpys=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20240722135656-d784300faade h1:oCRSWfwGXQsqlVdErcyTt4A93Y8fo0/9D4b1gnI++qo=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20240722135656-d784300faade/go.mod h1:Ue6ibwXGpU+dqIcODieyLOcgj7z8+IcskoNIgZxtrFY=
 google.golang.org/genproto/googleapis/rpc v0.0.0-20240723171418-e6d459c13d2a h1:hqK4+jJZXCU4pW7jsAdGOVFIfLHQeV7LaizZKnZ84HI=
 google.golang.org/genproto/googleapis/rpc v0.0.0-20240723171418-e6d459c13d2a/go.mod h1:Ue6ibwXGpU+dqIcODieyLOcgj7z8+IcskoNIgZxtrFY=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
@@ -907,7 +868,6 @@ gopkg.in/h2non/gock.v1 v1.1.2 h1:jBbHXgGBK/AoPVfJh5x4r/WxIrElvbLel8TCZkkZJoY=
 gopkg.in/h2non/gock.v1 v1.1.2/go.mod h1:n7UGz/ckNChHiK05rDoiC4MYSunEC/lyaUm2WWaDva0=
 gopkg.in/inf.v0 v0.9.1 h1:73M5CoZyi3ZLMOyDlQh031Cx6N9NDJ2Vvfl76EDAgDc=
 gopkg.in/inf.v0 v0.9.1/go.mod h1:cWUDdTG/fYaXco+Dcufb5Vnc6Gp2YChqWtbxRZE0mXw=
-gopkg.in/ini.v1 v1.67.0/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
 gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=

internal/handler/ai/chathandler.go

@@ -1,24 +1,25 @@
 package ai
 
 import (
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/repository/result"
+	"net/http"
+
 	"github.com/zeromicro/go-zero/rest/httpx"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/logic/ai"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
-	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/repository/result"
-	"net/http"
 )
 
-func ProxyApiHandler(svcCtx *svc.ServiceContext) http.HandlerFunc {
+func ChatHandler(svcCtx *svc.ServiceContext) http.HandlerFunc {
 	return func(w http.ResponseWriter, r *http.Request) {
 		var req types.ChatReq
 		if err := httpx.Parse(r, &req); err != nil {
-			result.ParamErrorResult(r, w, err)
+			httpx.ErrorCtx(r.Context(), w, err)
 			return
 		}
 
-		l := ai.NewProxyApiLogic(r.Context(), svcCtx)
-		resp, err := l.ProxyApi(&req)
+		l := ai.NewChatLogic(r.Context(), svcCtx)
+		resp, err := l.Chat(&req)
 		result.HttpResult(r, w, resp, err)
 	}
 }

internal/handler/inference/createdeploytaskhandler.go

@@ -0,0 +1,25 @@
+package inference
+
+import (
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/repository/result"
+	"net/http"
+
+	"github.com/zeromicro/go-zero/rest/httpx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/logic/inference"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+)
+
+func CreateDeployTaskHandler(svcCtx *svc.ServiceContext) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		var req types.CreateDeployTaskReq
+		if err := httpx.Parse(r, &req); err != nil {
+			result.ParamErrorResult(r, w, err)
+			return
+		}
+
+		l := inference.NewCreateDeployTaskLogic(r.Context(), svcCtx)
+		resp, err := l.CreateDeployTask(&req)
+		result.HttpResult(r, w, resp, err)
+	}
+}

internal/handler/inference/getadaptersbymodelhandler.go

@@ -0,0 +1,25 @@
+package inference
+
+import (
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/repository/result"
+	"net/http"
+
+	"github.com/zeromicro/go-zero/rest/httpx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/logic/inference"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+)
+
+func GetAdaptersByModelHandler(svcCtx *svc.ServiceContext) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		var req types.GetAdaptersByModelReq
+		if err := httpx.Parse(r, &req); err != nil {
+			result.ParamErrorResult(r, w, err)
+			return
+		}
+
+		l := inference.NewGetAdaptersByModelLogic(r.Context(), svcCtx)
+		resp, err := l.GetAdaptersByModel(&req)
+		result.HttpResult(r, w, resp, err)
+	}
+}

internal/handler/inference/getdeploytasksbytypehandler.go

@@ -0,0 +1,25 @@
+package inference
+
+import (
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/repository/result"
+	"net/http"
+
+	"github.com/zeromicro/go-zero/rest/httpx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/logic/inference"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+)
+
+func GetDeployTasksByTypeHandler(svcCtx *svc.ServiceContext) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		var req types.GetDeployTasksByTypeReq
+		if err := httpx.Parse(r, &req); err != nil {
+			result.ParamErrorResult(r, w, err)
+			return
+		}
+
+		l := inference.NewGetDeployTasksByTypeLogic(r.Context(), svcCtx)
+		resp, err := l.GetDeployTasksByType(&req)
+		result.HttpResult(r, w, resp, err)
+	}
+}

internal/handler/inference/getrunninginstancebyidhandler.go

@@ -0,0 +1,26 @@
+package inference
+
+import (
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/repository/result"
+	"net/http"
+
+	"github.com/zeromicro/go-zero/rest/httpx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/logic/inference"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+)
+
+func GetRunningInstanceByIdHandler(svcCtx *svc.ServiceContext) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		var req types.GetRunningInstanceReq
+		if err := httpx.Parse(r, &req); err != nil {
+			result.ParamErrorResult(r, w, err)
+			return
+		}
+
+		l := inference.NewGetRunningInstanceByIdLogic(r.Context(), svcCtx)
+		resp, err := l.GetRunningInstanceById(&req)
+		result.HttpResult(r, w, resp, err)
+
+	}
+}

internal/handler/inference/startallbydeploytaskidhandler.go

@@ -0,0 +1,26 @@
+package inference
+
+import (
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/repository/result"
+	"net/http"
+
+	"github.com/zeromicro/go-zero/rest/httpx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/logic/inference"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+)
+
+func StartAllByDeployTaskIdHandler(svcCtx *svc.ServiceContext) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		var req types.StartAllByDeployTaskIdReq
+		if err := httpx.Parse(r, &req); err != nil {
+			result.ParamErrorResult(r, w, err)
+			return
+		}
+
+		l := inference.NewStartAllByDeployTaskIdLogic(r.Context(), svcCtx)
+		resp, err := l.StartAllByDeployTaskId(&req)
+		result.HttpResult(r, w, resp, err)
+
+	}
+}

internal/handler/inference/stopallbydeploytaskidhandler.go

@@ -0,0 +1,26 @@
+package inference
+
+import (
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/repository/result"
+	"net/http"
+
+	"github.com/zeromicro/go-zero/rest/httpx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/logic/inference"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+)
+
+func StopAllByDeployTaskIdHandler(svcCtx *svc.ServiceContext) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		var req types.StopAllByDeployTaskIdReq
+		if err := httpx.Parse(r, &req); err != nil {
+			result.ParamErrorResult(r, w, err)
+			return
+		}
+
+		l := inference.NewStopAllByDeployTaskIdLogic(r.Context(), svcCtx)
+		resp, err := l.StopAllByDeployTaskId(&req)
+		result.HttpResult(r, w, resp, err)
+
+	}
+}

internal/handler/routes.go

@@ -460,7 +460,7 @@ func RegisterHandlers(server *rest.Server, serverCtx *svc.ServiceContext) {
 			{
 				Method:  http.MethodPost,
 				Path:    "/ai/chat",
-				Handler: ai.ProxyApiHandler(serverCtx),
+				Handler: ai.ChatHandler(serverCtx),
 			},
 		},
 		rest.WithPrefix("/pcm/v1"),
@@ -1213,6 +1213,36 @@ func RegisterHandlers(server *rest.Server, serverCtx *svc.ServiceContext) {
 				Path:    "/inference/taskStat",
 				Handler: inference.InferenceTaskStatHandler(serverCtx),
 			},
+			{
+				Method:  http.MethodPost,
+				Path:    "/inference/startAll",
+				Handler: inference.StartAllByDeployTaskIdHandler(serverCtx),
+			},
+			{
+				Method:  http.MethodPost,
+				Path:    "/inference/stopAll",
+				Handler: inference.StopAllByDeployTaskIdHandler(serverCtx),
+			},
+			{
+				Method:  http.MethodGet,
+				Path:    "/inference/getRunningInstanceById",
+				Handler: inference.GetRunningInstanceByIdHandler(serverCtx),
+			},
+			{
+				Method:  http.MethodGet,
+				Path:    "/inference/getDeployTasksByType",
+				Handler: inference.GetDeployTasksByTypeHandler(serverCtx),
+			},
+			{
+				Method:  http.MethodPost,
+				Path:    "/inference/createDeployTask",
+				Handler: inference.CreateDeployTaskHandler(serverCtx),
+			},
+			{
+				Method:  http.MethodGet,
+				Path:    "/inference/getAdaptersByModel",
+				Handler: inference.GetAdaptersByModelHandler(serverCtx),
+			},
 		},
 		rest.WithPrefix("/pcm/v1"),
 	)

internal/logic/adapters/createadapterlogic.go

@@ -27,11 +27,14 @@ func NewCreateAdapterLogic(ctx context.Context, svcCtx *svc.ServiceContext) *Cre
 
 func (l *CreateAdapterLogic) CreateAdapter(req *types.AdapterCreateReq) (resp *types.AdapterResp, err error) {
 	adapter := types.AdapterInfo{}
+	existAdapter := types.AdapterResp{}
+	resp = &types.AdapterResp{}
 	utils.Convert(req, &adapter)
 	//check name
-	exist := l.svcCtx.DbEngin.Table("t_adapter").Where("name = ?", req.Name).First(&types.AdapterInfo{}).Error
+	exist := l.svcCtx.DbEngin.Table("t_adapter").Where("name = ?", req.Name).First(&existAdapter).Error
 	if !errors.Is(exist, gorm.ErrRecordNotFound) {
-		return nil, errors.New("name already exists")
+		resp = &existAdapter
+		return resp, errors.New("name already exists")
 	}
 	//check type
 	var arr = [...]string{"0", "1", "2"}
@@ -60,8 +63,10 @@ func (l *CreateAdapterLogic) CreateAdapter(req *types.AdapterCreateReq) (resp *t
 	adapter.CreateTime = time.Now().Format("2006-01-02 15:04:05")
 	result := l.svcCtx.DbEngin.Table("t_adapter").Create(&adapter)
 	if result.Error != nil {
-		return nil, result.Error
+		return resp, result.Error
 	}
 
-	return
+	_ = l.svcCtx.DbEngin.Table("t_adapter").Where("name = ?", req.Name).First(&existAdapter).Error
+	resp = &existAdapter
+	return resp, nil
 }

internal/logic/ai/chatlogic.go

@@ -0,0 +1,94 @@
+package ai
+
+import (
+	"bytes"
+	"context"
+	"crypto/tls"
+	"github.com/go-resty/resty/v2"
+	"github.com/pkg/errors"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/constants"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/models"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/utils/hws"
+	"k8s.io/apimachinery/pkg/util/json"
+	"net/http"
+	"strings"
+
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+
+	"github.com/zeromicro/go-zero/core/logx"
+)
+
+type ChatLogic struct {
+	logx.Logger
+	ctx    context.Context
+	svcCtx *svc.ServiceContext
+}
+
+func NewChatLogic(ctx context.Context, svcCtx *svc.ServiceContext) *ChatLogic {
+	return &ChatLogic{
+		Logger: logx.WithContext(ctx),
+		ctx:    ctx,
+		svcCtx: svcCtx,
+	}
+}
+
+func (l *ChatLogic) Chat(req *types.ChatReq) (resp *types.ChatResult, err error) {
+	resp = &types.ChatResult{}
+	jsonBytes, err := json.Marshal(&req.ReqData)
+	if err != nil {
+		logx.Errorf("【序列化请求数据失败: %v】", err)
+		return nil, errors.New("请求数据序列化失败")
+	}
+
+	taskAi := models.TaskAi{}
+	l.svcCtx.DbEngin.Model(models.TaskAi{}).Where("id", req.Id).Scan(&taskAi)
+	logx.Infof("【开始处理请求，目标URL: %s】", taskAi.InferUrl)
+
+	// 构建 HTTP 请求
+	request, err := http.NewRequest("POST", taskAi.InferUrl, bytes.NewBuffer(jsonBytes))
+	if err != nil {
+		logx.Errorf("【构建 HTTP 请求失败: %v】", err)
+		return nil, errors.New("网络错误，请稍后重试")
+	}
+	client := resty.New().SetTLSClientConfig(&tls.Config{InsecureSkipVerify: true})
+	restReq := client.R()
+
+	//ModelArts
+	cluster := models.CloudModel{}
+	l.svcCtx.DbEngin.Table("t_cluster").Where("id", taskAi.ClusterId).Scan(&cluster)
+	if strings.EqualFold(cluster.Label, constants.MODELARTS) {
+		signer := &hws.Signer{
+			Key:    cluster.Ak,
+			Secret: cluster.Sk,
+		}
+		if err := signer.Sign(request); err != nil {
+			logx.Errorf("【接口签名错误: %v】", err)
+			return nil, errors.New("网络错误，请稍后重试")
+		}
+		restReq.
+			SetHeader("X-Project-Id", cluster.ProjectId).
+			SetHeader("x-stage", "RELEASE").
+			SetHeader("Authorization", request.Header.Get(hws.HeaderXAuthorization)).
+			SetHeader("X-Sdk-Date", request.Header.Get(hws.HeaderXDateTime))
+	}
+
+	response, err := restReq.
+		SetHeader("Content-Type", "application/json").
+		SetBody(jsonBytes).
+		SetResult(&resp).
+		Post(taskAi.InferUrl)
+
+	if err != nil {
+		logx.Errorf("【远程调用接口URL:%s， 返回错误: %s】", taskAi.InferUrl, err.Error())
+		return nil, errors.New("网络错误，请稍后重试")
+	}
+
+	if response.StatusCode() != 200 {
+		logx.Errorf("【远程调用接口URL:%s， 返回错误: %s】", taskAi.InferUrl, response.Body())
+		return nil, errors.New("网络错误，请稍后重试")
+	}
+
+	logx.Infof("【请求处理成功，目标URL: %s】", taskAi.InferUrl)
+	return resp, nil
+}

internal/logic/ai/proxyapilogic.go

@@ -1,91 +0,0 @@
-package ai
-
-import (
-	"bytes"
-	"context"
-	"crypto/tls"
-	"encoding/json"
-	"github.com/go-resty/resty/v2"
-	"github.com/pkg/errors"
-	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/utils/hws"
-	"net/http"
-
-	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
-	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
-
-	"github.com/zeromicro/go-zero/core/logx"
-)
-
-type ProxyApiLogic struct {
-	logx.Logger
-	ctx    context.Context
-	svcCtx *svc.ServiceContext
-}
-
-func NewProxyApiLogic(ctx context.Context, svcCtx *svc.ServiceContext) *ProxyApiLogic {
-	return &ProxyApiLogic{
-		Logger: logx.WithContext(ctx),
-		ctx:    ctx,
-		svcCtx: svcCtx,
-	}
-}
-
-const (
-	XProjectID  = "d18190e28e3f45a281ef0b0696ec9d52"
-	XStage      = "RELEASE"
-	ContentType = "application/json"
-)
-
-func (l *ProxyApiLogic) ProxyApi(req *types.ChatReq) (resp *types.ChatResult, err error) {
-	logx.Infof("【开始处理请求，目标URL: %s】", req.ApiUrl)
-
-	jsonBytes, err := json.Marshal(&req.ReqData)
-	if err != nil {
-		logx.Errorf("【序列化请求数据失败: %v】", err)
-		return nil, errors.New("请求数据序列化失败")
-	}
-
-	resp = &types.ChatResult{}
-
-	// 构建 HTTP 请求
-	request, err := http.NewRequest("POST", req.ApiUrl, bytes.NewBuffer(jsonBytes))
-	if err != nil {
-		logx.Errorf("【构建 HTTP 请求失败: %v】", err)
-		return nil, errors.New("网络错误，请稍后重试")
-	}
-
-	signer := &hws.Signer{
-		Key:    "UNEHPHO4Z7YSNPKRXFE4",
-		Secret: "JWXCE9qcYbc7RjpSRIWt4WgG3ZKF6Q4lPzkJReX9",
-	}
-
-	if err := signer.Sign(request); err != nil {
-		logx.Errorf("【接口签名错误: %v】", err)
-		return nil, errors.New("网络错误，请稍后重试")
-	}
-
-	client := resty.New().SetTLSClientConfig(&tls.Config{InsecureSkipVerify: true})
-
-	response, err := client.R().
-		SetHeader("X-Project-Id", XProjectID).
-		SetHeader("x-stage", XStage).
-		SetHeader("Content-Type", ContentType).
-		SetHeader("Authorization", request.Header.Get(hws.HeaderXAuthorization)).
-		SetHeader("X-Sdk-Date", request.Header.Get(hws.HeaderXDateTime)).
-		SetBody(jsonBytes).
-		SetResult(&resp).
-		Post(req.ApiUrl)
-
-	if err != nil {
-		logx.Errorf("【远程调用接口URL:%s， 返回错误: %s】", req.ApiUrl, err.Error())
-		return nil, errors.New("网络错误，请稍后重试")
-	}
-
-	if response.StatusCode() != 200 {
-		logx.Errorf("【远程调用接口URL:%s， 返回错误: %s】", req.ApiUrl, response.Body())
-		return nil, errors.New("网络错误，请稍后重试")
-	}
-
-	logx.Infof("【请求处理成功，目标URL: %s】", req.ApiUrl)
-	return resp, nil
-}

internal/logic/ai/trainingtaskstatlogic.go

@@ -2,8 +2,6 @@ package ai
 
 import (
 	"context"
-	"errors"
-
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
 
@@ -37,10 +35,6 @@ func (l *TrainingTaskStatLogic) TrainingTaskStat() (resp *types.TrainingTaskStat
 		return nil, err
 	}
 
-	if total == 0 {
-		return nil, errors.New("get statistics failed")
-	}
-
 	resp.Total = total
 	resp.Running = running
 	return resp, nil

internal/logic/inference/createdeploytasklogic.go

@@ -0,0 +1,104 @@
+package inference
+
+import (
+	"context"
+	"errors"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/schedulers/option"
+	"strconv"
+
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+
+	"github.com/zeromicro/go-zero/core/logx"
+)
+
+type CreateDeployTaskLogic struct {
+	logx.Logger
+	ctx    context.Context
+	svcCtx *svc.ServiceContext
+}
+
+func NewCreateDeployTaskLogic(ctx context.Context, svcCtx *svc.ServiceContext) *CreateDeployTaskLogic {
+	return &CreateDeployTaskLogic{
+		Logger: logx.WithContext(ctx),
+		ctx:    ctx,
+		svcCtx: svcCtx,
+	}
+}
+
+func (l *CreateDeployTaskLogic) CreateDeployTask(req *types.CreateDeployTaskReq) (resp *types.CreateDeployTaskResp, err error) {
+	resp = &types.CreateDeployTaskResp{}
+
+	if len(req.AdapterClusterMap) == 0 {
+		return nil, errors.New("adapters are empty")
+	}
+
+	opt := &option.InferOption{
+		TaskName:  req.TaskName,
+		ModelType: req.ModelType,
+		ModelName: req.ModelName,
+		Cmd:       "",
+	}
+
+	taskId, err := l.svcCtx.Scheduler.AiStorages.SaveInferDeployTask(req.TaskName, req.ModelName, req.ModelType, req.TaskDesc)
+	if err != nil {
+		return nil, err
+	}
+
+	for aid, v := range req.AdapterClusterMap {
+		for _, cid := range v {
+			err = l.createDeployInstance(taskId, aid, cid, opt)
+			if err != nil {
+				return nil, err
+			}
+		}
+	}
+
+	return
+}
+
+func (l *CreateDeployTaskLogic) createDeployInstance(taskId int64, adapterId string, clusterId string, opt *option.InferOption) error {
+	cmap, found := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[adapterId]
+	if !found {
+		return errors.New("adapterId not exist: " + adapterId)
+	}
+	iCluster, found := cmap[clusterId]
+	if !found {
+		return errors.New("clusterId not exist: " + clusterId)
+	}
+	insId, err := iCluster.CreateInferDeployInstance(l.ctx, opt)
+	if err != nil {
+		return err
+	}
+
+	aid, err := strconv.ParseInt(adapterId, 10, 64)
+	if err != nil {
+		return err
+	}
+	cid, err := strconv.ParseInt(clusterId, 10, 64)
+	if err != nil {
+		return err
+	}
+
+	adapterName, err := l.svcCtx.Scheduler.AiStorages.GetAdapterNameById(adapterId)
+	if err != nil {
+		return err
+	}
+
+	clusterName, err := l.svcCtx.Scheduler.AiStorages.GetClusterNameById(clusterId)
+	if err != nil {
+		return err
+	}
+
+	ins, err := iCluster.GetInferDeployInstance(l.ctx, insId)
+	if err != nil {
+		return err
+	}
+
+	_, err = l.svcCtx.Scheduler.AiStorages.SaveInferDeployInstance(taskId, ins.InstanceId, ins.InstanceName, aid, adapterName, cid, clusterName, ins.ModelName, ins.ModelType, ins.InferCard)
+	if err != nil {
+		return err
+	}
+
+	return nil
+}

internal/logic/inference/deployinstancelistlogic.go

@@ -4,9 +4,12 @@ import (
 	"context"
 	"errors"
 	"github.com/zeromicro/go-zero/core/logx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/common"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/updater"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/models"
+	"time"
 )
 
 type DeployInstanceListLogic struct {
@@ -28,9 +31,8 @@ func (l *DeployInstanceListLogic) DeployInstanceList(req *types.DeployInstanceLi
 	offset := req.PageSize * (req.PageNum - 1)
 	resp = &types.DeployInstanceListResp{}
 
-	var list []*models.AiInferDeployInstance
-
-	tx := l.svcCtx.DbEngin.Raw("select * from ai_infer_deploy_instance").Scan(&list)
+	var tasklist []*models.AiDeployInstanceTask
+	tx := l.svcCtx.DbEngin.Raw("select * from ai_deploy_instance_task").Scan(&tasklist)
 	if tx.Error != nil {
 		logx.Errorf(tx.Error.Error())
 		return nil, tx.Error
@@ -45,14 +47,66 @@ func (l *DeployInstanceListLogic) DeployInstanceList(req *types.DeployInstanceLi
 		return resp, err
 	}
 
-	err = tx.Order("create_time desc").Find(&list).Error
+	err = tx.Order("create_time desc").Find(&tasklist).Error
 	if err != nil {
 		return nil, errors.New(err.Error())
 	}
-	resp.List = &list
+
+	deployTasks := l.GenerateDeployTasks(tasklist)
+	slices := make([][]*models.AiInferDeployInstance, len(deployTasks))
+	for i := 0; i < len(deployTasks); i++ {
+		slices[i] = deployTasks[i].Instances
+	}
+	list := common.ConcatMultipleSlices(slices)
+
+	if len(list) == 0 {
+		return
+	}
+
+	go updater.UpdateDeployInstanceStatusBatch(l.svcCtx, list)
+
+	ins := list[0]
+	for i := range list {
+		uTime, _ := time.Parse(time.RFC3339, ins.UpdateTime)
+		latest, _ := time.Parse(time.RFC3339, list[i].UpdateTime)
+		if latest.After(uTime) {
+			ins = list[i]
+		}
+	}
+
+	go updater.UpdateDeployInstanceStatus(l.svcCtx, ins, true)
+	go updater.UpdateDeployTaskStatus(l.svcCtx)
+
+	resp.List = &deployTasks
 	resp.PageSize = req.PageSize
 	resp.PageNum = req.PageNum
 	resp.Total = total
 
 	return
 }
+
+func (l *DeployInstanceListLogic) GenerateDeployTasks(tasklist []*models.AiDeployInstanceTask) []*DeployTask {
+	var tasks []*DeployTask
+	for _, t := range tasklist {
+		list, err := l.svcCtx.Scheduler.AiStorages.GetInstanceListByDeployTaskId(t.Id)
+		if err != nil {
+			logx.Errorf("db GetInstanceListByDeployTaskId error")
+			continue
+		}
+		deployTask := &DeployTask{
+			Id:        t.Id,
+			Name:      t.Name,
+			Desc:      t.Desc,
+			Instances: list,
+		}
+		tasks = append(tasks, deployTask)
+	}
+	return tasks
+}
+
+type DeployTask struct {
+	Id        int64                           `json:"id,string"`
+	Name      string                          `json:"name,string"`
+	Desc      string                          `json:"desc,string"`
+	Instances []*models.AiInferDeployInstance `json:"instances,string"`
+}

internal/logic/inference/deployinstancestatlogic.go

@@ -2,8 +2,6 @@ package inference
 
 import (
 	"context"
-	"errors"
-
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
 
@@ -37,10 +35,6 @@ func (l *DeployInstanceStatLogic) DeployInstanceStat(req *types.DeployInstanceSt
 		return nil, err
 	}
 
-	if total == 0 {
-		return nil, errors.New("get statistics failed")
-	}
-
 	resp.Total = total
 	resp.Running = running
 	return resp, nil

internal/logic/inference/getadaptersbymodellogic.go

@@ -0,0 +1,65 @@
+package inference
+
+import (
+	"context"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+
+	"github.com/zeromicro/go-zero/core/logx"
+)
+
+type GetAdaptersByModelLogic struct {
+	logx.Logger
+	ctx    context.Context
+	svcCtx *svc.ServiceContext
+}
+
+func NewGetAdaptersByModelLogic(ctx context.Context, svcCtx *svc.ServiceContext) *GetAdaptersByModelLogic {
+	return &GetAdaptersByModelLogic{
+		Logger: logx.WithContext(ctx),
+		ctx:    ctx,
+		svcCtx: svcCtx,
+	}
+}
+
+func (l *GetAdaptersByModelLogic) GetAdaptersByModel(req *types.GetAdaptersByModelReq) (resp *types.GetAdaptersByModelResp, err error) {
+	resp = &types.GetAdaptersByModelResp{}
+
+	adapterList, err := l.svcCtx.Scheduler.AiStorages.GetAdaptersByType("1")
+	if err != nil {
+		return nil, err
+	}
+
+	for _, adapter := range adapterList {
+		var clusterAvail []*types.ClusterAvail
+		clusters, err := l.svcCtx.Scheduler.AiStorages.GetClustersByAdapterId(adapter.Id)
+		if err != nil {
+			return nil, err
+		}
+
+		for _, cluster := range clusters.List {
+			exist := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[adapter.Id][cluster.Id].CheckModelExistence(l.ctx, req.ModelName, req.ModelType)
+			if exist {
+				c := &types.ClusterAvail{
+					ClusterId:   cluster.Id,
+					ClusterName: cluster.Name,
+				}
+				clusterAvail = append(clusterAvail, c)
+			}
+		}
+
+		if len(clusterAvail) == 0 {
+			continue
+		}
+
+		adapterAvail := &types.AdapterAvail{
+			AdapterId:   adapter.Id,
+			AdapterName: adapter.Name,
+			Clusters:    clusterAvail,
+		}
+
+		resp.Adapters = append(resp.Adapters, adapterAvail)
+	}
+
+	return resp, nil
+}

internal/logic/inference/getdeploytasksbytypelogic.go

@@ -0,0 +1,41 @@
+package inference
+
+import (
+	"context"
+	"github.com/pkg/errors"
+
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+
+	"github.com/zeromicro/go-zero/core/logx"
+)
+
+type GetDeployTasksByTypeLogic struct {
+	logx.Logger
+	ctx    context.Context
+	svcCtx *svc.ServiceContext
+}
+
+func NewGetDeployTasksByTypeLogic(ctx context.Context, svcCtx *svc.ServiceContext) *GetDeployTasksByTypeLogic {
+	return &GetDeployTasksByTypeLogic{
+		Logger: logx.WithContext(ctx),
+		ctx:    ctx,
+		svcCtx: svcCtx,
+	}
+}
+
+func (l *GetDeployTasksByTypeLogic) GetDeployTasksByType(req *types.GetDeployTasksByTypeReq) (resp *types.GetDeployTasksByTypeResp, err error) {
+	resp = &types.GetDeployTasksByTypeResp{}
+
+	list, err := l.svcCtx.Scheduler.AiStorages.GetDeployTaskListByType(req.ModelType)
+	if err != nil {
+		return nil, err
+	}
+
+	if len(list) == 0 {
+		return nil, errors.New("实列不存在")
+	}
+
+	resp.List = list
+	return resp, nil
+}

internal/logic/inference/getrunninginstancebyidlogic.go

@@ -0,0 +1,38 @@
+package inference
+
+import (
+	"context"
+	"strconv"
+
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+
+	"github.com/zeromicro/go-zero/core/logx"
+)
+
+type GetRunningInstanceByIdLogic struct {
+	logx.Logger
+	ctx    context.Context
+	svcCtx *svc.ServiceContext
+}
+
+func NewGetRunningInstanceByIdLogic(ctx context.Context, svcCtx *svc.ServiceContext) *GetRunningInstanceByIdLogic {
+	return &GetRunningInstanceByIdLogic{
+		Logger: logx.WithContext(ctx),
+		ctx:    ctx,
+		svcCtx: svcCtx,
+	}
+}
+
+func (l *GetRunningInstanceByIdLogic) GetRunningInstanceById(req *types.GetRunningInstanceReq) (resp *types.GetRunningInstanceResp, err error) {
+	resp = &types.GetRunningInstanceResp{}
+
+	id, err := strconv.ParseInt(req.Id, 10, 64)
+	if err != nil {
+		return nil, err
+	}
+	list, err := l.svcCtx.Scheduler.AiStorages.GetRunningDeployInstanceById(id, req.AdapterId)
+
+	resp.List = list
+	return
+}

internal/logic/inference/imageinferencelogic.go

@@ -10,7 +10,9 @@ import (
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/strategy"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/models"
 	"net/http"
+	"strconv"
 )
 
 type ImageInferenceLogic struct {
@@ -34,17 +36,24 @@ func NewImageInferenceLogic(ctx context.Context, svcCtx *svc.ServiceContext) *Im
 
 func (l *ImageInferenceLogic) ImageInfer(r *http.Request, req *types.ImageInferenceReq) (resp *types.ImageInferenceResp, err error) {
 	resp = &types.ImageInferenceResp{}
-	opt := &option.InferOption{
-		TaskName:        req.TaskName,
-		TaskDesc:        req.TaskDesc,
-		AdapterId:       req.AdapterId,
-		AiClusterIds:    req.AiClusterIds,
-		ModelName:       req.ModelName,
-		ModelType:       req.ModelType,
-		Strategy:        req.Strategy,
-		StaticWeightMap: req.StaticWeightMap,
+	if len(req.InstanceIds) == 0 {
+		return nil, errors.New("instances are empty")
 	}
 
+	var instanceList []*models.AiInferDeployInstance
+	for _, id := range req.InstanceIds {
+		instance, err := l.svcCtx.Scheduler.AiStorages.GetInferDeployInstanceById(id)
+		if err != nil {
+			return nil, err
+		}
+		instanceList = append(instanceList, instance)
+	}
+
+	if len(instanceList) == 0 {
+		return nil, errors.New("instances are empty")
+	}
+
+	// process uploaded images
 	var ts []*imageInference.ImageFile
 
 	uploadedFiles := r.MultipartForm.File
@@ -72,9 +81,37 @@ func (l *ImageInferenceLogic) ImageInfer(r *http.Request, req *types.ImageInfere
 		ts = append(ts, &t)
 	}
 
-	_, ok := l.svcCtx.Scheduler.AiService.AiCollectorAdapterMap[opt.AdapterId]
+	//single adapter logic
+	if len(req.StaticWeightMap) != 1 {
+		return nil, errors.New("staticWeightMap != 1")
+	}
+
+	adapterId := strconv.FormatInt(instanceList[0].AdapterId, 10)
+	staticWeightMap, ok := req.StaticWeightMap[adapterId]
 	if !ok {
-		return nil, errors.New("AdapterId does not exist")
+		return nil, errors.New("set staticWeightMap failed")
+	}
+
+	// create InferOption
+	opt := &option.InferOption{
+		TaskName:  req.TaskName,
+		TaskDesc:  req.TaskDesc,
+		AdapterId: adapterId,
+		//AiClusterIds:    req.AiClusterIds,
+		//ModelName:       req.ModelName,
+		ModelType:       req.ModelType,
+		Strategy:        req.Strategy,
+		StaticWeightMap: staticWeightMap,
+	}
+
+	adapterName, err := l.svcCtx.Scheduler.AiStorages.GetAdapterNameById(opt.AdapterId)
+	if err != nil {
+		return nil, err
+	}
+
+	// set strategy
+	if opt.Strategy != "" {
+		return nil, errors.New("strategy is empty")
 	}
 
 	var strat strategy.Strategy
@@ -102,12 +139,8 @@ func (l *ImageInferenceLogic) ImageInfer(r *http.Request, req *types.ImageInfere
 		}
 	}
 
-	adapterName, err := l.svcCtx.Scheduler.AiStorages.GetAdapterNameById(opt.AdapterId)
-	if err != nil {
-		return nil, err
-	}
-
-	imageInfer, err := imageInference.New(imageInference.NewImageClassification(), ts, clusters, opt, l.svcCtx.Scheduler.AiStorages, l.svcCtx.Scheduler.AiService.InferenceAdapterMap, adapterName)
+	// create inference struct
+	imageInfer, err := imageInference.New(imageInference.NewImageClassification(), ts, clusters, instanceList, opt, l.svcCtx.Scheduler.AiStorages, l.svcCtx.Scheduler.AiService.InferenceAdapterMap, adapterName)
 	if err != nil {
 		return nil, err
 	}

internal/logic/inference/inferencetaskstatlogic.go

@@ -2,8 +2,6 @@ package inference
 
 import (
 	"context"
-	"errors"
-
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
 
@@ -37,10 +35,6 @@ func (l *InferenceTaskStatLogic) InferenceTaskStat(req *types.InferenceTaskStatR
 		return nil, err
 	}
 
-	if total == 0 {
-		return nil, errors.New("get statistics failed")
-	}
-
 	resp.Total = total
 	resp.Running = running
 	return resp, nil

internal/logic/inference/startallbydeploytaskidlogic.go

@@ -0,0 +1,85 @@
+package inference
+
+import (
+	"context"
+	"errors"
+	"github.com/zeromicro/go-zero/core/logx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/inference"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/storeLink"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+	"strconv"
+)
+
+type StartAllByDeployTaskIdLogic struct {
+	logx.Logger
+	ctx    context.Context
+	svcCtx *svc.ServiceContext
+}
+
+func NewStartAllByDeployTaskIdLogic(ctx context.Context, svcCtx *svc.ServiceContext) *StartAllByDeployTaskIdLogic {
+	return &StartAllByDeployTaskIdLogic{
+		Logger: logx.WithContext(ctx),
+		ctx:    ctx,
+		svcCtx: svcCtx,
+	}
+}
+
+func (l *StartAllByDeployTaskIdLogic) StartAllByDeployTaskId(req *types.StartAllByDeployTaskIdReq) (resp *types.StartAllByDeployTaskIdResp, err error) {
+	resp = &types.StartAllByDeployTaskIdResp{}
+
+	id, err := strconv.ParseInt(req.Id, 10, 64)
+
+	list, err := l.svcCtx.Scheduler.AiStorages.GetInstanceListByDeployTaskId(id)
+	if err != nil {
+		return nil, err
+	}
+
+	for _, ins := range list {
+		in, err := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].GetInferDeployInstance(l.ctx, ins.InstanceId)
+		if err != nil {
+			return nil, err
+		}
+		if checkStopStatus(in) {
+			success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].StartInferDeployInstance(l.ctx, ins.InstanceId)
+			if !success {
+				return nil, errors.New(ins.InstanceName + " start failed")
+			}
+		}
+	}
+
+	err = l.svcCtx.Scheduler.AiStorages.UpdateDeployTaskById(id)
+	if err != nil {
+		return nil, err
+	}
+
+	return resp, nil
+}
+
+func checkStopStatus(in *inference.DeployInstance) bool {
+	switch in.ClusterType {
+	case storeLink.TYPE_OCTOPUS:
+		switch in.Status {
+		case "stopped":
+			return true
+		default:
+			return false
+		}
+	case storeLink.TYPE_MODELARTS:
+		switch in.Status {
+		case "stopped":
+			return true
+		default:
+			return false
+		}
+	case storeLink.TYPE_SHUGUANGAI:
+		switch in.Status {
+		case "Terminated":
+			return true
+		default:
+			return false
+		}
+	default:
+		return false
+	}
+}

internal/logic/inference/startdeployinstancelistlogic.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"github.com/zeromicro/go-zero/core/logx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/updater"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
 	"strconv"
@@ -25,18 +26,19 @@ func NewStartDeployInstanceListLogic(ctx context.Context, svcCtx *svc.ServiceCon
 
 func (l *StartDeployInstanceListLogic) StartDeployInstanceList(req *types.StartDeployInstanceReq) (resp *types.StartDeployInstanceResp, err error) {
 	resp = &types.StartDeployInstanceResp{}
-	success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[req.AdapterId][req.ClusterId].StartInferDeployInstance(l.ctx, req.InstanceId)
+
 	id, err := strconv.ParseInt(req.Id, 10, 64)
 	ins, err := l.svcCtx.Scheduler.AiStorages.GetInferDeployInstanceById(id)
 	if err != nil {
 		return nil, err
 	}
 
-	l.svcCtx.Scheduler.AiStorages.UpdateInferDeployInstance(ins)
-
+	success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[req.AdapterId][req.ClusterId].StartInferDeployInstance(l.ctx, req.InstanceId)
 	if !success {
 		return nil, errors.New("start instance failed")
 	}
 
+	go updater.UpdateDeployInstanceStatus(l.svcCtx, ins, true)
+
 	return resp, nil
 }

internal/logic/inference/stopallbydeploytaskidlogic.go

@@ -0,0 +1,86 @@
+package inference
+
+import (
+	"context"
+	"errors"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/inference"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/storeLink"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
+	"strconv"
+
+	"github.com/zeromicro/go-zero/core/logx"
+)
+
+type StopAllByDeployTaskIdLogic struct {
+	logx.Logger
+	ctx    context.Context
+	svcCtx *svc.ServiceContext
+}
+
+func NewStopAllByDeployTaskIdLogic(ctx context.Context, svcCtx *svc.ServiceContext) *StopAllByDeployTaskIdLogic {
+	return &StopAllByDeployTaskIdLogic{
+		Logger: logx.WithContext(ctx),
+		ctx:    ctx,
+		svcCtx: svcCtx,
+	}
+}
+
+func (l *StopAllByDeployTaskIdLogic) StopAllByDeployTaskId(req *types.StopAllByDeployTaskIdReq) (resp *types.StopAllByDeployTaskIdResp, err error) {
+	resp = &types.StopAllByDeployTaskIdResp{}
+
+	id, err := strconv.ParseInt(req.Id, 10, 64)
+
+	list, err := l.svcCtx.Scheduler.AiStorages.GetInstanceListByDeployTaskId(id)
+	if err != nil {
+		return nil, err
+	}
+
+	for _, ins := range list {
+		in, err := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].GetInferDeployInstance(l.ctx, ins.InstanceId)
+		if err != nil {
+			return nil, err
+		}
+		if checkStatus(in) {
+			success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(ins.AdapterId, 10)][strconv.FormatInt(ins.ClusterId, 10)].StopInferDeployInstance(l.ctx, ins.InstanceId)
+			if !success {
+				return nil, errors.New(ins.InstanceName + " stop failed")
+			}
+		}
+	}
+
+	err = l.svcCtx.Scheduler.AiStorages.UpdateDeployTaskById(id)
+	if err != nil {
+		return nil, err
+	}
+
+	return resp, nil
+}
+
+func checkStatus(in *inference.DeployInstance) bool {
+	switch in.ClusterType {
+	case storeLink.TYPE_OCTOPUS:
+		switch in.Status {
+		case "running":
+			return true
+		default:
+			return false
+		}
+	case storeLink.TYPE_MODELARTS:
+		switch in.Status {
+		case "running":
+			return true
+		default:
+			return false
+		}
+	case storeLink.TYPE_SHUGUANGAI:
+		switch in.Status {
+		case "Running":
+			return true
+		default:
+			return false
+		}
+	default:
+		return false
+	}
+}

internal/logic/inference/stopdeployinstancelogic.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"github.com/zeromicro/go-zero/core/logx"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/updater"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/svc"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
 	"strconv"
@@ -25,17 +26,19 @@ func NewStopDeployInstanceLogic(ctx context.Context, svcCtx *svc.ServiceContext)
 
 func (l *StopDeployInstanceLogic) StopDeployInstance(req *types.StopDeployInstanceReq) (resp *types.StopDeployInstanceResp, err error) {
 	resp = &types.StopDeployInstanceResp{}
-	success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[req.AdapterId][req.ClusterId].StopInferDeployInstance(l.ctx, req.InstanceId)
+
 	id, err := strconv.ParseInt(req.Id, 10, 64)
 	ins, err := l.svcCtx.Scheduler.AiStorages.GetInferDeployInstanceById(id)
 	if err != nil {
 		return nil, err
 	}
 
-	l.svcCtx.Scheduler.AiStorages.UpdateInferDeployInstance(ins)
-
+	success := l.svcCtx.Scheduler.AiService.InferenceAdapterMap[req.AdapterId][req.ClusterId].StopInferDeployInstance(l.ctx, req.InstanceId)
 	if !success {
 		return nil, errors.New("stop instance failed")
 	}
+
+	go updater.UpdateDeployInstanceStatus(l.svcCtx, ins, true)
+
 	return resp, nil
 }

internal/scheduler/common/common.go

@@ -97,3 +97,21 @@ func Contains(s []string, e string) bool {
 	}
 	return false
 }
+
+func ConcatMultipleSlices[T any](slices [][]T) []T {
+	var totalLen int
+
+	for _, s := range slices {
+		totalLen += len(s)
+	}
+
+	result := make([]T, totalLen)
+
+	var i int
+
+	for _, s := range slices {
+		i += copy(result[i:], s)
+	}
+
+	return result
+}

internal/scheduler/database/aiStorage.go

@@ -373,23 +373,24 @@ func (s *AiStorage) AddNoticeInfo(adapterId string, adapterName string, clusterI
 	}
 }
 
-func (s *AiStorage) SaveInferDeployInstance(instanceId string, instanceName string, adapterId int64,
+func (s *AiStorage) SaveInferDeployInstance(taskId int64, instanceId string, instanceName string, adapterId int64,
 	adapterName string, clusterId int64, clusterName string, modelName string, modelType string, inferCard string) (int64, error) {
 	startTime := time.Now().Format(time.RFC3339)
 	// 构建主任务结构体
 	insModel := models.AiInferDeployInstance{
-		InstanceId:   instanceId,
-		InstanceName: instanceName,
-		AdapterId:    adapterId,
-		AdapterName:  adapterName,
-		ClusterId:    clusterId,
-		ClusterName:  clusterName,
-		ModelName:    modelName,
-		ModelType:    modelType,
-		InferCard:    inferCard,
-		Status:       constants.Saved,
-		CreateTime:   startTime,
-		UpdateTime:   startTime,
+		DeployInstanceTaskId: taskId,
+		InstanceId:           instanceId,
+		InstanceName:         instanceName,
+		AdapterId:            adapterId,
+		AdapterName:          adapterName,
+		ClusterId:            clusterId,
+		ClusterName:          clusterName,
+		ModelName:            modelName,
+		ModelType:            modelType,
+		InferCard:            inferCard,
+		Status:               constants.Stopped,
+		CreateTime:           startTime,
+		UpdateTime:           startTime,
 	}
 	// 保存任务数据到数据库
 	tx := s.DbEngin.Table("ai_infer_deploy_instance").Create(&insModel)
@@ -399,8 +400,10 @@ func (s *AiStorage) SaveInferDeployInstance(instanceId string, instanceName stri
 	return insModel.Id, nil
 }
 
-func (s *AiStorage) UpdateInferDeployInstance(instance *models.AiInferDeployInstance) error {
-	instance.UpdateTime = time.Now().Format(time.RFC3339)
+func (s *AiStorage) UpdateInferDeployInstance(instance *models.AiInferDeployInstance, needUpdateTime bool) error {
+	if needUpdateTime {
+		instance.UpdateTime = time.Now().Format(time.RFC3339)
+	}
 	tx := s.DbEngin.Table("ai_infer_deploy_instance").Updates(instance)
 	if tx.Error != nil {
 		logx.Errorf(tx.Error.Error())
@@ -419,6 +422,70 @@ func (s *AiStorage) GetInferDeployInstanceById(id int64) (*models.AiInferDeployI
 	return &deployIns, nil
 }
 
+func (s *AiStorage) GetDeployTaskById(id int64) (*models.AiDeployInstanceTask, error) {
+	var task models.AiDeployInstanceTask
+	tx := s.DbEngin.Raw("select * from ai_deploy_instance_task where `id` = ?", id).Scan(&task)
+	if tx.Error != nil {
+		logx.Errorf(tx.Error.Error())
+		return nil, tx.Error
+	}
+	return &task, nil
+}
+
+func (s *AiStorage) GetDeployTaskListByType(modelType string) ([]*models.AiDeployInstanceTask, error) {
+	var tasks []*models.AiDeployInstanceTask
+	tx := s.DbEngin.Raw("select * from ai_deploy_instance_task where `model_type` = ?", modelType).Scan(&tasks)
+	if tx.Error != nil {
+		logx.Errorf(tx.Error.Error())
+		return nil, tx.Error
+	}
+	return tasks, nil
+}
+
+func (s *AiStorage) GetAllDeployTasks() ([]*models.AiDeployInstanceTask, error) {
+	var tasks []*models.AiDeployInstanceTask
+	tx := s.DbEngin.Raw("select * from ai_deploy_instance_task").Scan(&tasks)
+	if tx.Error != nil {
+		logx.Errorf(tx.Error.Error())
+		return nil, tx.Error
+	}
+	return tasks, nil
+}
+
+func (s *AiStorage) UpdateDeployTask(task *models.AiDeployInstanceTask, needUpdateTime bool) error {
+	if needUpdateTime {
+		task.UpdateTime = time.Now().Format(time.RFC3339)
+	}
+	tx := s.DbEngin.Table("ai_deploy_instance_task").Updates(task)
+	if tx.Error != nil {
+		logx.Errorf(tx.Error.Error())
+		return tx.Error
+	}
+	return nil
+}
+
+func (s *AiStorage) UpdateDeployTaskById(id int64) error {
+	task, err := s.GetDeployTaskById(id)
+	if err != nil {
+		return err
+	}
+	err = s.UpdateDeployTask(task, true)
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+func (s *AiStorage) GetInstanceListByDeployTaskId(id int64) ([]*models.AiInferDeployInstance, error) {
+	var list []*models.AiInferDeployInstance
+	tx := s.DbEngin.Raw("select * from ai_infer_deploy_instance where `deploy_instance_task_id` = ?", id).Scan(&list)
+	if tx.Error != nil {
+		logx.Errorf(tx.Error.Error())
+		return nil, tx.Error
+	}
+	return list, nil
+}
+
 func (s *AiStorage) GetInferDeployInstanceList() ([]*models.AiInferDeployInstance, error) {
 	var list []*models.AiInferDeployInstance
 	tx := s.DbEngin.Raw("select * from ai_infer_deploy_instance").Scan(&list)
@@ -429,6 +496,16 @@ func (s *AiStorage) GetInferDeployInstanceList() ([]*models.AiInferDeployInstanc
 	return list, nil
 }
 
+func (s *AiStorage) GetDeployTaskList() ([]*models.AiDeployInstanceTask, error) {
+	var list []*models.AiDeployInstanceTask
+	tx := s.DbEngin.Raw("select * from ai_deploy_instance_task").Scan(&list)
+	if tx.Error != nil {
+		logx.Errorf(tx.Error.Error())
+		return nil, tx.Error
+	}
+	return list, nil
+}
+
 func (s *AiStorage) GetInferDeployInstanceTotalNum() (int32, error) {
 	var total int32
 	tx := s.DbEngin.Raw("select count(*) from ai_infer_deploy_instance").Scan(&total)
@@ -441,7 +518,7 @@ func (s *AiStorage) GetInferDeployInstanceTotalNum() (int32, error) {
 
 func (s *AiStorage) GetInferDeployInstanceRunningNum() (int32, error) {
 	var total int32
-	tx := s.DbEngin.Raw("select count(*) from ai_infer_deploy_instance where `status` = 'running'").Scan(&total)
+	tx := s.DbEngin.Raw("select count(*) from ai_infer_deploy_instance where `status` = 'Running'").Scan(&total)
 	if tx.Error != nil {
 		logx.Errorf(tx.Error.Error())
 		return 0, tx.Error
@@ -481,10 +558,39 @@ func (s *AiStorage) GetTrainingTaskTotalNum() (int32, error) {
 
 func (s *AiStorage) GetTrainingTaskRunningNum() (int32, error) {
 	var total int32
-	tx := s.DbEngin.Raw("select count(*) from task where `task_type_dict` = 11 and `status` = 'Running'").Scan(&total)
+	tx := s.DbEngin.Raw("select count(*) from task where `task_type_dict` = 10 and `status` = 'Running'").Scan(&total)
 	if tx.Error != nil {
 		logx.Errorf(tx.Error.Error())
 		return 0, tx.Error
 	}
 	return total, nil
 }
+
+func (s *AiStorage) SaveInferDeployTask(taskName string, modelName string, modelType string, desc string) (int64, error) {
+	startTime := time.Now().Format(time.RFC3339)
+	// 构建主任务结构体
+	taskModel := models.AiDeployInstanceTask{
+		Name:       taskName,
+		ModelName:  modelName,
+		ModelType:  modelType,
+		Desc:       desc,
+		CreateTime: startTime,
+		UpdateTime: startTime,
+	}
+	// 保存任务数据到数据库
+	tx := s.DbEngin.Table("ai_deploy_instance_task").Create(&taskModel)
+	if tx.Error != nil {
+		return 0, tx.Error
+	}
+	return taskModel.Id, nil
+}
+
+func (s *AiStorage) GetRunningDeployInstanceById(id int64, adapterId string) ([]*models.AiInferDeployInstance, error) {
+	var list []*models.AiInferDeployInstance
+	tx := s.DbEngin.Raw("select * from ai_infer_deploy_instance where `deploy_instance_task_id` = ? and `adapter_id` = ? and `status` = 'Running'", id, adapterId).Scan(&list)
+	if tx.Error != nil {
+		logx.Errorf(tx.Error.Error())
+		return nil, tx.Error
+	}
+	return list, nil
+}

internal/scheduler/schedulers/option/inferOption.go

@@ -15,6 +15,17 @@ type InferOption struct {
 	Envs            []string         `json:"envs,optional"`
 	Cmd             string           `json:"cmd,optional"`
 	Replica         int32            `json:"replicas,optional"`
+
+	ResourceId  string
+	AlgorithmId string
+	ImageId     string
+
+	//modelarts
+	InferType     string
+	Specification string
+	Weight        int32
+	ModelId       string
+	InstanceCount int32
 }
 
 func (a InferOption) GetOptionType() string {

internal/scheduler/service/inference/imageInference/imageInference.go

@@ -9,6 +9,7 @@ import (
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/schedulers/option"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/inference"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/strategy"
+	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/storeLink"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/constants"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/models"
@@ -37,6 +38,7 @@ type FilteredCluster struct {
 	urls        []*inference.InferUrl
 	clusterId   string
 	clusterName string
+	clusterType string
 	imageNum    int32
 }
 
@@ -44,6 +46,7 @@ type ImageInference struct {
 	inference    IImageInference
 	files        []*ImageFile
 	clusters     []*strategy.AssignedCluster
+	instances    []*models.AiInferDeployInstance
 	opt          *option.InferOption
 	storage      *database.AiStorage
 	inferAdapter map[string]map[string]inference.ICluster
@@ -55,6 +58,7 @@ func New(
 	inference IImageInference,
 	files []*ImageFile,
 	clusters []*strategy.AssignedCluster,
+	instances []*models.AiInferDeployInstance,
 	opt *option.InferOption,
 	storage *database.AiStorage,
 	inferAdapter map[string]map[string]inference.ICluster,
@@ -64,6 +68,7 @@ func New(
 		inference:    inference,
 		files:        files,
 		clusters:     clusters,
+		instances:    instances,
 		opt:          opt,
 		storage:      storage,
 		inferAdapter: inferAdapter,
@@ -126,7 +131,7 @@ func (i *ImageInference) saveTask() (int64, error) {
 		return 0, err
 	}
 
-	i.storage.AddNoticeInfo(i.opt.AdapterId, i.adapterName, "", "", i.opt.TaskName, "create", "任务创建中")
+	i.storage.AddNoticeInfo("", "", "", "", i.opt.TaskName, "create", "任务创建中")
 
 	return id, nil
 }
@@ -143,7 +148,7 @@ func (i *ImageInference) saveAiTask(id int64) error {
 	return nil
 }
 
-func (i *ImageInference) filterClusters() ([]*FilteredCluster, error) {
+func (i *ImageInference) filterClustersTemp() ([]*FilteredCluster, error) {
 	var wg sync.WaitGroup
 	var ch = make(chan *FilteredCluster, len(i.clusters))
 	var cs []*FilteredCluster
@@ -156,7 +161,7 @@ func (i *ImageInference) filterClusters() ([]*FilteredCluster, error) {
 		c := cluster
 		go func() {
 			r := http.Request{}
-			imageUrls, err := inferMap[c.ClusterId].GetInferUrl(r.Context(), i.opt)
+			clusterInferUrl, err := inferMap[c.ClusterId].GetClusterInferUrl(r.Context(), i.opt)
 			if err != nil {
 				mutex.Lock()
 				i.errMap[c.ClusterId] = err.Error()
@@ -165,14 +170,13 @@ func (i *ImageInference) filterClusters() ([]*FilteredCluster, error) {
 				return
 			}
 
-			i.inference.AppendRoute(imageUrls)
-
-			clusterName, _ := i.storage.GetClusterNameById(c.ClusterId)
+			i.inference.AppendRoute(clusterInferUrl.InferUrls)
 
 			var f FilteredCluster
-			f.urls = imageUrls
+			f.urls = clusterInferUrl.InferUrls
 			f.clusterId = c.ClusterId
-			f.clusterName = clusterName
+			f.clusterName = clusterInferUrl.ClusterName
+			f.clusterType = clusterInferUrl.ClusterType
 			f.imageNum = c.Replicas
 
 			ch <- &f
@@ -189,6 +193,45 @@ func (i *ImageInference) filterClusters() ([]*FilteredCluster, error) {
 	return cs, nil
 }
 
+func (i *ImageInference) filterClusters() ([]*FilteredCluster, error) {
+	var cs []*FilteredCluster
+	for _, cluster := range i.clusters {
+		var inferurls []*inference.InferUrl
+		var clustertype string
+		for _, instance := range i.instances {
+			clusterId := strconv.FormatInt(instance.ClusterId, 10)
+			adapterId := strconv.FormatInt(instance.AdapterId, 10)
+
+			if cluster.ClusterId == clusterId {
+				r := http.Request{}
+				deployInstance, err := i.inferAdapter[adapterId][clusterId].GetInferDeployInstance(r.Context(), instance.InstanceId)
+				if err != nil {
+					continue
+				}
+				var url inference.InferUrl
+				url.Url = deployInstance.InferUrl
+				url.Card = deployInstance.InferCard
+				inferurls = append(inferurls, &url)
+
+				clustertype = deployInstance.ClusterType
+			}
+		}
+		if len(inferurls) == 0 {
+			continue
+		}
+
+		i.inference.AppendRoute(inferurls)
+
+		var f FilteredCluster
+		f.urls = inferurls
+		f.clusterName = cluster.ClusterName
+		f.clusterType = clustertype
+		f.imageNum = cluster.Replicas
+		cs = append(cs, &f)
+	}
+	return cs, nil
+}
+
 func (i *ImageInference) inferImages(cs []*FilteredCluster) ([]*types.ImageResult, error) {
 	var wg sync.WaitGroup
 	var ch = make(chan *types.ImageResult, len(i.files))
@@ -206,7 +249,7 @@ func (i *ImageInference) inferImages(cs []*FilteredCluster) ([]*types.ImageResul
 		imageNumIdx = imageNumIdx + c.imageNum
 
 		wg.Add(len(new_images))
-		go sendInferReq(new_images, c, &wg, ch, limit)
+		go i.sendInferReq(new_images, c, &wg, ch, limit)
 	}
 	wg.Wait()
 	close(ch)
@@ -300,12 +343,12 @@ func (i *ImageInference) updateStatus(aiTaskList []*models.TaskAi, cs []*Filtere
 	return nil
 }
 
-func sendInferReq(images []*ImageFile, cluster *FilteredCluster, wg *sync.WaitGroup, ch chan<- *types.ImageResult, limit chan bool) {
+func (i *ImageInference) sendInferReq(images []*ImageFile, cluster *FilteredCluster, wg *sync.WaitGroup, ch chan<- *types.ImageResult, limit chan bool) {
 	for _, image := range images {
 		limit <- true
 		go func(t *ImageFile, c *FilteredCluster) {
 			if len(c.urls) == 1 {
-				r, err := getInferResult(c.urls[0].Url, t.File, t.ImageResult.ImageName, c.clusterName)
+				r, err := getInferResult(c.urls[0].Url, t.File, t.ImageResult.ImageName, c.clusterId, c.clusterType, i.inferAdapter, i.opt.AdapterId)
 				if err != nil {
 					t.ImageResult.ImageResult = err.Error()
 					t.ImageResult.ClusterId = c.clusterId
@@ -327,7 +370,7 @@ func sendInferReq(images []*ImageFile, cluster *FilteredCluster, wg *sync.WaitGr
 				return
 			} else {
 				idx := rand.Intn(len(c.urls))
-				r, err := getInferResult(c.urls[idx].Url, t.File, t.ImageResult.ImageName, c.clusterName)
+				r, err := getInferResult(c.urls[idx].Url, t.File, t.ImageResult.ImageName, c.clusterId, c.clusterType, i.inferAdapter, i.opt.AdapterId)
 				if err != nil {
 					t.ImageResult.ImageResult = err.Error()
 					t.ImageResult.ClusterId = c.clusterId
@@ -404,24 +447,35 @@ func (i *ImageInference) saveAiSubTasks(id int64, aiTaskList []*models.TaskAi, c
 	return nil
 }
 
-func getInferResult(url string, file multipart.File, fileName string, clusterName string) (string, error) {
-	if clusterName == "鹏城云脑II-modelarts" {
+func getInferResult(url string, file multipart.File, fileName string, clusterId string, clusterType string, inferAdapter map[string]map[string]inference.ICluster, adapterId string) (string, error) {
+	inferMap := inferAdapter[adapterId]
+
+	switch clusterType {
+	case storeLink.TYPE_OCTOPUS:
+		r := http.Request{}
+		result, err := inferMap[clusterId].GetInferResult(r.Context(), url, file, fileName)
+		if err != nil {
+			return "", err
+		}
+		return result, nil
+	case storeLink.TYPE_MODELARTS:
 		r, err := getInferResultModelarts(url, file, fileName)
 		if err != nil {
 			return "", err
 		}
 		return r, nil
+	default:
+		var res Res
+		req := GetRestyRequest(20)
+		_, err := req.
+			SetFileReader("file", fileName, file).
+			SetResult(&res).
+			Post(url)
+		if err != nil {
+			return "", err
+		}
+		return res.Result, nil
 	}
-	var res Res
-	req := GetRestyRequest(20)
-	_, err := req.
-		SetFileReader("file", fileName, file).
-		SetResult(&res).
-		Post(url)
-	if err != nil {
-		return "", err
-	}
-	return res.Result, nil
 }
 
 func getInferResultModelarts(url string, file multipart.File, fileName string) (string, error) {

internal/scheduler/service/inference/imageInference/imageToText.go

@@ -3,7 +3,7 @@ package imageInference
 import "gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/inference"
 
 const (
-	IMAGETOTEXT        = "image-to-text"
+	IMAGETOTEXT        = "image"
 	IMAGETOTEXT_AiTYPE = "13"
 )
 

internal/scheduler/service/inference/inference.go

@@ -3,6 +3,7 @@ package inference
 import (
 	"context"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/schedulers/option"
+	"mime/multipart"
 )
 
 const (
@@ -10,11 +11,14 @@ const (
 )
 
 type ICluster interface {
-	GetInferUrl(ctx context.Context, option *option.InferOption) ([]*InferUrl, error)
+	GetClusterInferUrl(ctx context.Context, option *option.InferOption) (*ClusterInferUrl, error)
+	GetInferResult(ctx context.Context, url string, file multipart.File, fileName string) (string, error)
 	GetInferDeployInstanceList(ctx context.Context) ([]*DeployInstance, error)
 	StartInferDeployInstance(ctx context.Context, id string) bool
 	StopInferDeployInstance(ctx context.Context, id string) bool
 	GetInferDeployInstance(ctx context.Context, id string) (*DeployInstance, error)
+	CreateInferDeployInstance(ctx context.Context, option *option.InferOption) (string, error)
+	CheckModelExistence(ctx context.Context, modelName string, modelType string) bool
 }
 
 type IInference interface {
@@ -26,6 +30,12 @@ type Inference struct {
 	In IInference
 }
 
+type ClusterInferUrl struct {
+	ClusterName string
+	ClusterType string
+	InferUrls   []*InferUrl
+}
+
 type InferUrl struct {
 	Url  string
 	Card string
@@ -37,7 +47,9 @@ type DeployInstance struct {
 	ModelName    string
 	ModelType    string
 	InferCard    string
+	InferUrl     string
 	ClusterName  string
+	ClusterType  string
 	Status       string
 	CreatedTime  string
 }

internal/scheduler/service/inference/textInference/textToImage.go

@@ -9,7 +9,7 @@ import (
 )
 
 const (
-	TEXTTOIMAGE        = "text-to-image"
+	TEXTTOIMAGE        = "generate_image"
 	TEXTTOIMAGE_AiTYPE = "14"
 )
 

internal/scheduler/service/inference/textInference/textToText.go

@@ -74,18 +74,20 @@ func filterClusters(opt *option.InferOption, storage *database.AiStorage, inferA
 		wg.Add(1)
 		go func(cId string) {
 			r := http.Request{}
-			urls, err := inferMap[cId].GetInferUrl(r.Context(), opt)
+			clusterInferUrl, err := inferMap[cId].GetClusterInferUrl(r.Context(), opt)
 			if err != nil {
 				wg.Done()
 				return
 			}
-			for i, _ := range urls {
-				urls[i].Url = urls[i].Url + inference.FORWARD_SLASH + CHAT
+
+			for i, _ := range clusterInferUrl.InferUrls {
+				clusterInferUrl.InferUrls[i].Url = clusterInferUrl.InferUrls[i].Url + inference.FORWARD_SLASH + CHAT
 			}
+
 			clusterName, _ := storage.GetClusterNameById(cId)
 
 			var f FilteredCluster
-			f.urls = urls
+			f.urls = clusterInferUrl.InferUrls
 			f.clusterId = cId
 			f.clusterName = clusterName
 

internal/scheduler/service/updater/deployInstance.go

@@ -7,9 +7,52 @@ import (
 	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/models"
 	"net/http"
 	"strconv"
+	"time"
 )
 
-func UpdateDeployInstanceStatus(svc *svc.ServiceContext, instance *models.AiInferDeployInstance) {
+func UpdateDeployInstanceStatusBatch(svc *svc.ServiceContext, insList []*models.AiInferDeployInstance) {
+	list := make([]*models.AiInferDeployInstance, len(insList))
+	copy(list, insList)
+	for i := len(list) - 1; i >= 0; i-- {
+		if list[i].Status == constants.Running || list[i].Status == constants.Stopped {
+			list = append(list[:i], list[i+1:]...)
+		}
+	}
+
+	if len(list) == 0 {
+		return
+	}
+
+	for _, instance := range list {
+		go UpdateDeployInstanceStatus(svc, instance, false)
+	}
+}
+
+func UpdateDeployTaskStatus(svc *svc.ServiceContext) {
+	list, err := svc.Scheduler.AiStorages.GetAllDeployTasks()
+	if err != nil {
+		return
+	}
+
+	ins := list[0]
+	for i := range list {
+		uTime, _ := time.Parse(time.RFC3339, ins.UpdateTime)
+		latest, _ := time.Parse(time.RFC3339, list[i].UpdateTime)
+		if latest.After(uTime) {
+			ins = list[i]
+		}
+	}
+	inslist, err := svc.Scheduler.AiStorages.GetInstanceListByDeployTaskId(ins.Id)
+	if err != nil {
+		return
+	}
+
+	for _, instance := range inslist {
+		go UpdateDeployInstanceStatus(svc, instance, false)
+	}
+}
+
+func UpdateDeployInstanceStatus(svc *svc.ServiceContext, instance *models.AiInferDeployInstance, updatetime bool) {
 	amap, found := svc.Scheduler.AiService.InferenceAdapterMap[strconv.FormatInt(instance.AdapterId, 10)]
 	if !found {
 		return
@@ -27,24 +70,51 @@ func UpdateDeployInstanceStatus(svc *svc.ServiceContext, instance *models.AiInfe
 	case storeLink.TYPE_OCTOPUS:
 		switch ins.Status {
 		case "running":
+			if instance.Status == constants.Running {
+				return
+			}
 			instance.Status = constants.Running
 		case "stopped":
+			if instance.Status == constants.Stopped {
+				return
+			}
 			instance.Status = constants.Stopped
 		default:
 			instance.Status = ins.Status
 		}
-
-	case storeLink.TYPE_SHUGUANGAI:
+	case storeLink.TYPE_MODELARTS:
 		switch ins.Status {
 		case "running":
+			if instance.Status == constants.Running {
+				return
+			}
+			instance.Status = constants.Running
+		case "stopped":
+			if instance.Status == constants.Stopped {
+				return
+			}
+			instance.Status = constants.Stopped
+		default:
+			instance.Status = ins.Status
+		}
+	case storeLink.TYPE_SHUGUANGAI:
+		switch ins.Status {
+		case "Running":
+			if instance.Status == constants.Running {
+				return
+			}
 			instance.Status = constants.Running
 		case "Terminated":
+			if instance.Status == constants.Stopped {
+				return
+			}
 			instance.Status = constants.Stopped
 		default:
 			instance.Status = ins.Status
 		}
 	}
-	err = svc.Scheduler.AiStorages.UpdateInferDeployInstance(instance)
+
+	err = svc.Scheduler.AiStorages.UpdateInferDeployInstance(instance, updatetime)
 	if err != nil {
 		return
 	}

internal/storeLink/modelarts.go

@@ -27,6 +27,7 @@ import (
 	"gitlink.org.cn/JointCloud/pcm-modelarts/client/modelartsservice"
 	"gitlink.org.cn/JointCloud/pcm-modelarts/modelarts"
 	modelartsclient "gitlink.org.cn/JointCloud/pcm-modelarts/modelarts"
+	"mime/multipart"
 	"strconv"
 	"strings"
 	"time"
@@ -201,10 +202,11 @@ func (m *ModelArtsLink) GetResourceStats(ctx context.Context) (*collector.Resour
 	num32, _ := strconv.Atoi(resp1.Items[0].Spec.Npu.Size)
 	var cards []*collector.Card
 	card := &collector.Card{
-		Platform: MODELARTS,
-		Type:     CARD,
-		Name:     Npu,
-		CardNum:  int32(num32),
+		Platform:   MODELARTS,
+		Type:       CARD,
+		Name:       Npu,
+		CardNum:    int32(num32),
+		TOpsAtFp16: float64(num32 * 320),
 	}
 	cards = append(cards, card)
 	resourceStats.CardsAvail = cards
@@ -258,6 +260,28 @@ func (m *ModelArtsLink) UploadAlgorithmCode(ctx context.Context, resourceType st
 	return nil
 }
 
+func (m *ModelArtsLink) GetModelId(ctx context.Context, option *option.AiOption, ifoption *option.InferOption) error {
+	req := &modelarts.ListModelReq{
+		Platform:  m.platform,
+		Limit:     int64(m.pageIndex),
+		Offset:    int64(m.pageSize),
+		ModelName: option.ModelName,
+		//ModelType: option.ModelType,
+	}
+	ListResp, err := m.modelArtsRpc.ListModels(ctx, req)
+	for _, Models := range ListResp.Models {
+		if Models.ModelName == option.ModelName {
+			ifoption.ModelId = Models.ModelId
+			return nil
+		}
+	}
+	if err != nil {
+		return err
+	}
+
+	return errors.New("failed to set ModelId")
+}
+
 func (m *ModelArtsLink) GetTrainingTaskLog(ctx context.Context, taskId string, instanceNum string) (string, error) {
 	req := &modelartsservice.GetTrainingJobLogsPreviewReq{
 		Platform:      m.platform,
@@ -335,7 +359,7 @@ func (m *ModelArtsLink) Execute(ctx context.Context, option *option.AiOption) (i
 }
 
 func (m *ModelArtsLink) GenerateSubmitParams(ctx context.Context, option *option.AiOption) error {
-	err := m.generateResourceId(ctx, option)
+	err := m.generateResourceId(ctx, option, nil)
 	if err != nil {
 		return err
 	}
@@ -362,7 +386,7 @@ func (m *ModelArtsLink) GenerateSubmitParams(ctx context.Context, option *option
 	return nil
 }
 
-func (m *ModelArtsLink) generateResourceId(ctx context.Context, option *option.AiOption) error {
+func (m *ModelArtsLink) generateResourceId(ctx context.Context, option *option.AiOption, ifoption *option.InferOption) error {
 	option.ResourceId = "modelarts.kat1.xlarge"
 	return nil
 }
@@ -426,7 +450,7 @@ func (m *ModelArtsLink) generateAlgorithmId(ctx context.Context, option *option.
 	return errors.New("failed to get AlgorithmId")
 }
 
-func (m *ModelArtsLink) GetInferUrl(ctx context.Context, option *option.InferOption) ([]*inference.InferUrl, error) {
+func (m *ModelArtsLink) GetClusterInferUrl(ctx context.Context, option *option.InferOption) (*inference.ClusterInferUrl, error) {
 	var imageUrls []*inference.InferUrl
 	urlReq := &modelartsclient.ImageReasoningUrlReq{
 		ServiceName: option.ModelName,
@@ -443,7 +467,12 @@ func (m *ModelArtsLink) GetInferUrl(ctx context.Context, option *option.InferOpt
 	}
 	imageUrls = append(imageUrls, imageUrl)
 
-	return imageUrls, nil
+	clusterWithUrl := &inference.ClusterInferUrl{
+		ClusterName: m.platform,
+		ClusterType: TYPE_MODELARTS,
+		InferUrls:   imageUrls,
+	}
+	return clusterWithUrl, nil
 }
 
 func (m *ModelArtsLink) GetInferDeployInstanceList(ctx context.Context) ([]*inference.DeployInstance, error) {
@@ -470,6 +499,7 @@ func (m *ModelArtsLink) GetInferDeployInstanceList(ctx context.Context) ([]*infe
 		ins.InferCard = "NPU"
 		ins.ClusterName = m.platform
 		ins.CreatedTime = string(services.StartTime)
+		ins.ClusterType = TYPE_MODELARTS
 		insList = append(insList, ins)
 	}
 
@@ -524,5 +554,52 @@ func (m *ModelArtsLink) GetInferDeployInstance(ctx context.Context, id string) (
 	ins.InferCard = "NPU"
 	ins.ClusterName = m.platform
 	ins.CreatedTime = string(resp.StartTime)
+	ins.ClusterType = TYPE_MODELARTS
 	return ins, nil
 }
+
+func (m *ModelArtsLink) GetInferResult(ctx context.Context, url string, file multipart.File, fileName string) (string, error) {
+	return "", nil
+}
+
+func (m *ModelArtsLink) CreateInferDeployInstance(ctx context.Context, option *option.InferOption) (string, error) {
+
+	err := m.GetModelId(ctx, nil, option)
+	if err != nil {
+		return "", err
+	}
+
+	configParam := &modelarts.ServiceConfig{
+		Specification: "modelarts.kat1.xlarge.al",
+		Weight:        option.Weight,
+		ModelId:       option.ModelId,
+		InstanceCount: option.InstanceCount,
+	}
+	var configItems []*modelarts.ServiceConfig
+	configItems = append(configItems, configParam)
+	req := &modelarts.CreateServiceReq{
+		Platform:    m.platform,
+		Config:      configItems,
+		InferType:   option.InferType,
+		ServiceName: option.TaskName,
+	}
+	resp, err := m.modelArtsRpc.CreateService(ctx, req)
+	if err != nil {
+		return "", err
+	}
+
+	return resp.ServiceId, nil
+}
+
+func (m *ModelArtsLink) CheckModelExistence(ctx context.Context, name string, mtype string) bool {
+	ifoption := &option.InferOption{
+		ModelName: name,
+		ModelType: mtype,
+	}
+	err := m.GetModelId(ctx, nil, ifoption)
+	if err != nil {
+		return false
+	}
+
+	return true
+}

internal/storeLink/octopus.go

@@ -15,6 +15,7 @@
 package storeLink
 
 import (
+	"bufio"
 	"context"
 	"errors"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/schedulers/option"
@@ -24,7 +25,9 @@ import (
 	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/utils"
 	"gitlink.org.cn/JointCloud/pcm-octopus/octopus"
 	"gitlink.org.cn/JointCloud/pcm-octopus/octopusclient"
+	"io"
 	"math"
+	"mime/multipart"
 	"strconv"
 	"strings"
 	"time"
@@ -78,6 +81,14 @@ var (
 		MLU: CAMBRICONMLU290,
 		GCU: EnflameT20,
 	}
+	CardModelNameCmdMap = map[string]map[string]string{
+		BIV100: {"blip-image-captioning-base": "pip install -U transformers; pip install fastapi uvicorn[standard]; pip install python-multipart; cd /code; python infer_biv100.py",
+			"imagenet_resnet50": "pip install -U transformers; pip install fastapi uvicorn[standard]; pip install python-multipart; cd /code/infer; python infer_biv100.py",
+			"chatGLM_6B":        "su root; pip install transformers==4.33.2; pip install fastapi uvicorn[standard]; cd /code; python infer_biv100.py"},
+		MLU: {"blip-image-captioning-base": "",
+			"imagenet_resnet50": "su root; . /torch/venv3/pytorch/bin/activate; pip install fastapi uvicorn[standard]; pip install python-multipart; cd /code/infer; python infer_mlu.py",
+			"chatGLM_6B":        ""},
+	}
 )
 
 func NewOctopusLink(octopusRpc octopusclient.Octopus, name string, id int64) *OctopusLink {
@@ -558,7 +569,7 @@ func (o *OctopusLink) Execute(ctx context.Context, option *option.AiOption) (int
 }
 
 func (o *OctopusLink) GenerateSubmitParams(ctx context.Context, option *option.AiOption) error {
-	err := o.generateResourceId(ctx, option)
+	err := o.generateResourceId(ctx, option, nil)
 	if err != nil {
 		return err
 	}
@@ -566,15 +577,15 @@ func (o *OctopusLink) GenerateSubmitParams(ctx context.Context, option *option.A
 	if err != nil {
 		return err
 	}
-	err = o.generateImageId(ctx, option)
+	err = o.generateImageId(ctx, option, nil)
 	if err != nil {
 		return err
 	}
-	err = o.generateAlgorithmId(ctx, option)
+	err = o.generateAlgorithmId(ctx, option, nil)
 	if err != nil {
 		return err
 	}
-	err = o.generateCmd(option)
+	err = o.generateCmd(option, nil)
 	if err != nil {
 		return err
 	}
@@ -589,10 +600,7 @@ func (o *OctopusLink) GenerateSubmitParams(ctx context.Context, option *option.A
 	return nil
 }
 
-func (o *OctopusLink) generateResourceId(ctx context.Context, option *option.AiOption) error {
-	if option.ResourceType == "" {
-		return errors.New("ResourceType not set")
-	}
+func (o *OctopusLink) generateResourceId(ctx context.Context, option *option.AiOption, ifoption *option.InferOption) error {
 	req := &octopus.GetResourceSpecsReq{
 		Platform:     o.platform,
 		ResourcePool: RESOURCE_POOL,
@@ -605,6 +613,30 @@ func (o *OctopusLink) generateResourceId(ctx context.Context, option *option.AiO
 		return errors.New(specResp.Error.Message)
 	}
 
+	if option != nil {
+		err = generateResourceIdForTraining(option, specResp)
+		if err != nil {
+			return err
+		}
+		return nil
+	}
+
+	if ifoption != nil {
+		err = generateResourceIdForInferDeployInstance(ifoption, specResp)
+		if err != nil {
+			return err
+		}
+		return nil
+	}
+
+	return errors.New("failed to set ResourceId")
+}
+
+func generateResourceIdForTraining(option *option.AiOption, specResp *octopus.GetResourceSpecsResp) error {
+	if option.ResourceType == "" {
+		return errors.New("ResourceType not set")
+	}
+
 	if option.ResourceType == CPU {
 		for _, spec := range specResp.TrainResourceSpecs {
 			if spec.Price == 0 {
@@ -618,14 +650,44 @@ func (o *OctopusLink) generateResourceId(ctx context.Context, option *option.AiO
 		if option.ComputeCard == "" {
 			option.ComputeCard = GCU
 		}
-		err = setResourceIdByCard(option, specResp, option.ComputeCard)
+		err := setResourceIdByCard(option, specResp, option.ComputeCard)
 		if err != nil {
 			return err
 		}
 		return nil
 	}
 
-	return errors.New("failed to get ResourceId")
+	return errors.New("ResourceType not set")
+}
+
+func generateResourceIdForInferDeployInstance(option *option.InferOption, specResp *octopus.GetResourceSpecsResp) error {
+	// temporarily use bi-v100
+	cardName, ok := cardCnMap[BIV100]
+	if !ok {
+		errors.New("computeCard not set")
+	}
+
+	// set computeCard
+	option.ComputeCard = BIV100
+
+	for _, spec := range specResp.TrainResourceSpecs {
+		names := strings.Split(spec.Name, COMMA)
+		if len(names) != 4 {
+			continue
+		}
+
+		ns := strings.Split(names[0], STAR)
+		if len(ns) != 2 {
+			continue
+		}
+
+		if ns[0] == "1" && ns[1] == cardName {
+			option.ResourceId = spec.Id
+			return nil
+		}
+	}
+
+	return errors.New("failed to set ResourceId")
 }
 
 func (o *OctopusLink) generateDatasetsId(ctx context.Context, option *option.AiOption) error {
@@ -653,33 +715,7 @@ func (o *OctopusLink) generateDatasetsId(ctx context.Context, option *option.AiO
 	return errors.New("failed to get DatasetsId")
 }
 
-func (o *OctopusLink) generateImageId(ctx context.Context, option *option.AiOption) error {
-	if option.TaskType == "" {
-		return errors.New("TaskType not set")
-	}
-
-	req := &octopus.GetUserImageListReq{
-		Platform:  o.platform,
-		PageIndex: o.pageIndex,
-		PageSize:  o.pageSize,
-	}
-	resp, err := o.octopusRpc.GetUserImageList(ctx, req)
-	if err != nil {
-		return err
-	}
-	if !resp.Success {
-		return errors.New("failed to get imageId")
-	}
-
-	if option.ResourceType == CPU {
-		for _, img := range resp.Payload.Images {
-			if img.Image.ImageName == "test-image" {
-				option.ImageId = img.Image.Id
-				return nil
-			}
-		}
-	}
-
+func (o *OctopusLink) generateImageId(ctx context.Context, option *option.AiOption, ifoption *option.InferOption) error {
 	preImgReq := &octopus.GetPresetImageListReq{
 		Platform:  o.platform,
 		PageIndex: o.pageIndex,
@@ -693,6 +729,52 @@ func (o *OctopusLink) generateImageId(ctx context.Context, option *option.AiOpti
 		return errors.New("failed to get PresetImages")
 	}
 
+	if option != nil {
+		if option.TaskType == "" {
+			return errors.New("TaskType not set")
+		}
+
+		req := &octopus.GetUserImageListReq{
+			Platform:  o.platform,
+			PageIndex: o.pageIndex,
+			PageSize:  o.pageSize,
+		}
+		resp, err := o.octopusRpc.GetUserImageList(ctx, req)
+		if err != nil {
+			return err
+		}
+		if !resp.Success {
+			return errors.New("failed to get imageId")
+		}
+
+		if option.ResourceType == CPU {
+			for _, img := range resp.Payload.Images {
+				if img.Image.ImageName == "test-image" {
+					option.ImageId = img.Image.Id
+					return nil
+				}
+			}
+		}
+
+		err = generateImageIdForTraining(option, preImgResp)
+		if err != nil {
+			return err
+		}
+		return nil
+	}
+
+	if ifoption != nil {
+		err = generateImageIdForInferDeployInstance(ifoption, preImgResp)
+		if err != nil {
+			return err
+		}
+		return nil
+	}
+
+	return errors.New("failed to get ImageId")
+}
+
+func generateImageIdForTraining(option *option.AiOption, preImgResp *octopus.GetPresetImageListResp) error {
 	if option.ResourceType == CARD {
 		for _, image := range preImgResp.Payload.Images {
 			if strings.Contains(image.ImageName, cardAliasMap[strings.ToUpper(option.ComputeCard)]) {
@@ -714,11 +796,35 @@ func (o *OctopusLink) generateImageId(ctx context.Context, option *option.AiOpti
 			}
 		}
 	}
-
-	return errors.New("failed to get ImageId")
+	return errors.New("failed to set ImageId")
 }
 
-func (o *OctopusLink) generateAlgorithmId(ctx context.Context, option *option.AiOption) error {
+func generateImageIdForInferDeployInstance(option *option.InferOption, preImgResp *octopus.GetPresetImageListResp) error {
+	for _, image := range preImgResp.Payload.Images {
+		// temporarily use bi-v100
+		if strings.Contains(image.ImageName, cardAliasMap[strings.ToUpper(BIV100)]) {
+			switch strings.ToUpper(BIV100) {
+			case GCU:
+				if strings.HasPrefix(image.ImageVersion, "t20_") {
+					option.ImageId = image.Id
+					return nil
+				}
+			case BIV100:
+				if strings.HasPrefix(image.ImageVersion, "bi_") {
+					option.ImageId = image.Id
+					return nil
+				}
+			case MLU:
+				option.ImageId = image.Id
+				return nil
+			}
+		}
+	}
+
+	return errors.New("failed to set ImageId")
+}
+
+func (o *OctopusLink) generateAlgorithmId(ctx context.Context, option *option.AiOption, ifoption *option.InferOption) error {
 	req := &octopus.GetMyAlgorithmListReq{
 		Platform:  o.platform,
 		PageIndex: o.pageIndex,
@@ -732,6 +838,26 @@ func (o *OctopusLink) generateAlgorithmId(ctx context.Context, option *option.Ai
 		return errors.New("failed to get algorithmId")
 	}
 
+	if option != nil {
+		err = generateAlgorithmIdForTraining(option, resp)
+		if err != nil {
+			return err
+		}
+		return nil
+	}
+
+	if ifoption != nil {
+		err = generateAlgorithmIdForInferDeployInstance(ifoption, resp)
+		if err != nil {
+			return err
+		}
+		return nil
+	}
+
+	return errors.New("failed to set AlgorithmId")
+}
+
+func generateAlgorithmIdForTraining(option *option.AiOption, resp *octopus.GetMyAlgorithmListResp) error {
 	for _, algorithm := range resp.Payload.Algorithms {
 		if algorithm.FrameworkName == strings.Title(option.TaskType) {
 			ns := strings.Split(algorithm.AlgorithmName, UNDERSCORE)
@@ -757,14 +883,48 @@ func (o *OctopusLink) generateAlgorithmId(ctx context.Context, option *option.Ai
 		}
 	}
 
-	if option.AlgorithmId == "" {
-		return errors.New("Algorithm does not exist")
-	}
-
-	return errors.New("failed to get AlgorithmId")
+	return errors.New("Algorithm does not exist")
 }
 
-func (o *OctopusLink) generateCmd(option *option.AiOption) error {
+func generateAlgorithmIdForInferDeployInstance(option *option.InferOption, resp *octopus.GetMyAlgorithmListResp) error {
+	if option.ModelType == "" {
+		return errors.New("ModelType not set")
+	}
+
+	if option.ModelName == "" {
+		return errors.New("ModelName not set")
+	}
+
+	for _, algorithm := range resp.Payload.Algorithms {
+		if strings.Contains(algorithm.AlgorithmName, option.ModelName) {
+			option.AlgorithmId = algorithm.AlgorithmId
+			return nil
+		}
+	}
+	return errors.New("ModelName does not exist")
+}
+
+func (o *OctopusLink) generateCmd(option *option.AiOption, ifoption *option.InferOption) error {
+	if option != nil {
+		err := generateCmdForTraining(option)
+		if err != nil {
+			return err
+		}
+		return nil
+	}
+
+	if ifoption != nil {
+		err := generateCmdForInferDeployInstance(ifoption)
+		if err != nil {
+			return err
+		}
+		return nil
+	}
+
+	return errors.New("failed to set cmd")
+}
+
+func generateCmdForTraining(option *option.AiOption) error {
 	if option.Cmd == "" {
 		switch option.ComputeCard {
 		case GCU:
@@ -779,6 +939,23 @@ func (o *OctopusLink) generateCmd(option *option.AiOption) error {
 	return nil
 }
 
+func generateCmdForInferDeployInstance(option *option.InferOption) error {
+	if option.Cmd == "" {
+		nameCmd, ok := CardModelNameCmdMap[option.ComputeCard]
+		if !ok {
+			return errors.New("failed to set cmd, ComputeCard not exist")
+		}
+		cmd, ok := nameCmd[option.ModelName]
+		if !ok {
+			return errors.New("failed to set cmd, ModelName not exist")
+		}
+		option.Cmd = cmd
+		return nil
+	}
+
+	return nil
+}
+
 func (o *OctopusLink) generateEnv(option *option.AiOption) error {
 
 	return nil
@@ -872,7 +1049,7 @@ func setResourceIdByCard(option *option.AiOption, specs *octopus.GetResourceSpec
 	return errors.New("set ResourceId error")
 }
 
-func (o *OctopusLink) GetInferUrl(ctx context.Context, option *option.InferOption) ([]*inference.InferUrl, error) {
+func (o *OctopusLink) GetClusterInferUrl(ctx context.Context, option *option.InferOption) (*inference.ClusterInferUrl, error) {
 	req := &octopus.GetNotebookListReq{
 		Platform:  o.platform,
 		PageIndex: o.pageIndex,
@@ -902,7 +1079,13 @@ func (o *OctopusLink) GetInferUrl(ctx context.Context, option *option.InferOptio
 	if len(imageUrls) == 0 {
 		return nil, errors.New("no infer url available")
 	}
-	return imageUrls, nil
+
+	clusterWithUrl := &inference.ClusterInferUrl{
+		ClusterName: o.platform,
+		ClusterType: TYPE_OCTOPUS,
+		InferUrls:   imageUrls,
+	}
+	return clusterWithUrl, nil
 }
 
 func (o *OctopusLink) GetInferDeployInstanceList(ctx context.Context) ([]*inference.DeployInstance, error) {
@@ -926,6 +1109,7 @@ func (o *OctopusLink) GetInferDeployInstanceList(ctx context.Context) ([]*infere
 		ins.InstanceId = notebook.Id
 		ins.ClusterName = o.platform
 		ins.Status = notebook.Status
+		ins.ClusterType = TYPE_OCTOPUS
 		insList = append(insList, ins)
 	}
 	return insList, nil
@@ -970,9 +1154,113 @@ func (o *OctopusLink) GetInferDeployInstance(ctx context.Context, id string) (*i
 	if resp.Payload == nil {
 		return nil, errors.New("instance does not exist")
 	}
+
+	url := strings.Replace(resp.Payload.Notebook.Tasks[0].Url, FORWARD_SLASH, "", -1)
+	inferUrl := DOMAIN + url
+
 	ins.InstanceName = resp.Payload.Notebook.Name
 	ins.InstanceId = resp.Payload.Notebook.Id
 	ins.ClusterName = o.platform
 	ins.Status = resp.Payload.Notebook.Status
+	ins.ClusterType = TYPE_OCTOPUS
+	ins.InferUrl = inferUrl
+
 	return ins, nil
 }
+
+func (o *OctopusLink) GetInferResult(ctx context.Context, url string, file multipart.File, fileName string) (string, error) {
+	stream, err := o.octopusRpc.GetInferResult(ctx)
+	if err != nil {
+		return "", err
+	}
+
+	buffer := make([]byte, 2048)
+	bufferedReader := bufio.NewReader(file)
+	for {
+		_, err = bufferedReader.Read(buffer)
+		if err != nil {
+			if err != io.EOF {
+				return "", err
+			}
+			break
+		}
+		err = stream.Send(&octopus.InferResultReq{
+			Platform:  o.platform,
+			InferUrl:  url,
+			FileName:  fileName,
+			FileBytes: buffer,
+		})
+	}
+
+	recv, err := stream.CloseAndRecv()
+	if err != nil {
+		return "", err
+	}
+
+	return recv.Result, nil
+}
+
+func (o *OctopusLink) CreateInferDeployInstance(ctx context.Context, option *option.InferOption) (string, error) {
+	err := o.generateResourceId(ctx, nil, option)
+	if err != nil {
+		return "", err
+	}
+
+	err = o.generateAlgorithmId(ctx, nil, option)
+	if err != nil {
+		return "", err
+	}
+
+	err = o.generateImageId(ctx, nil, option)
+	if err != nil {
+		return "", err
+	}
+
+	err = o.generateCmd(nil, option)
+	if err != nil {
+		return "", err
+	}
+
+	desc := option.ModelType + FORWARD_SLASH + option.ModelName + FORWARD_SLASH + strings.ToLower(BIV100)
+	param := &octopus.CreateNotebookParam{
+		Name:             option.TaskName,
+		ResourcePool:     RESOURCE_POOL,
+		ResourceSpecId:   option.ResourceId,
+		AlgorithmId:      option.AlgorithmId,
+		AlgorithmVersion: VERSION,
+		ImageId:          option.ImageId,
+		DatasetId:        "",
+		DatasetVersion:   "",
+		Command:          option.Cmd,
+		Desc:             desc,
+		TaskNumber:       1,
+	}
+	req := &octopus.CreateNotebookReq{
+		Platform: o.platform,
+		Params:   param,
+	}
+
+	resp, err := o.octopusRpc.CreateNotebook(ctx, req)
+	if err != nil {
+		return "", err
+	}
+
+	if !resp.Success {
+		return "", errors.New(resp.Error.Message)
+	}
+
+	return resp.Payload.Id, nil
+}
+
+func (o *OctopusLink) CheckModelExistence(ctx context.Context, name string, mtype string) bool {
+	ifoption := &option.InferOption{
+		ModelName: name,
+		ModelType: mtype,
+	}
+	err := o.generateAlgorithmId(ctx, nil, ifoption)
+	if err != nil {
+		return false
+	}
+
+	return true
+}

internal/storeLink/shuguangai.go

@@ -25,6 +25,7 @@ import (
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/service/inference"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/types"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/pkg/utils"
+	"mime/multipart"
 	"strconv"
 	"strings"
 	"sync"
@@ -768,7 +769,7 @@ func (s *ShuguangAi) generateParams(option *option.AiOption) error {
 	return errors.New("failed to set params")
 }
 
-func (s *ShuguangAi) GetInferUrl(ctx context.Context, option *option.InferOption) ([]*inference.InferUrl, error) {
+func (s *ShuguangAi) GetClusterInferUrl(ctx context.Context, option *option.InferOption) (*inference.ClusterInferUrl, error) {
 	var imageUrls []*inference.InferUrl
 
 	urlReq := &hpcAC.GetInferUrlReq{
@@ -787,7 +788,12 @@ func (s *ShuguangAi) GetInferUrl(ctx context.Context, option *option.InferOption
 	}
 	imageUrls = append(imageUrls, imageUrl)
 
-	return imageUrls, nil
+	clusterWithUrl := &inference.ClusterInferUrl{
+		ClusterName: s.platform,
+		ClusterType: TYPE_SHUGUANGAI,
+		InferUrls:   imageUrls,
+	}
+	return clusterWithUrl, nil
 }
 
 func (s *ShuguangAi) GetInferDeployInstanceList(ctx context.Context) ([]*inference.DeployInstance, error) {
@@ -815,6 +821,8 @@ func (s *ShuguangAi) GetInferDeployInstanceList(ctx context.Context) ([]*inferen
 		ins.Status = datum.Status
 		ins.InferCard = DCU
 		ins.CreatedTime = datum.CreateTime
+		ins.ClusterType = TYPE_SHUGUANGAI
+
 		insList = append(insList, ins)
 	}
 
@@ -865,5 +873,20 @@ func (s *ShuguangAi) GetInferDeployInstance(ctx context.Context, id string) (*in
 	ins.Status = resp.Data.Status
 	ins.InferCard = DCU
 	ins.CreatedTime = resp.Data.CreateTime
+	ins.ClusterType = TYPE_SHUGUANGAI
+
 	return ins, nil
 }
+
+func (s *ShuguangAi) GetInferResult(ctx context.Context, url string, file multipart.File, fileName string) (string, error) {
+	return "", nil
+}
+
+func (s *ShuguangAi) CreateInferDeployInstance(ctx context.Context, option *option.InferOption) (string, error) {
+
+	return "", nil
+}
+
+func (s *ShuguangAi) CheckModelExistence(ctx context.Context, name string, mtype string) bool {
+	return false
+}

internal/storeLink/storeLink.go

@@ -81,6 +81,8 @@ var (
 	ModelTypeMap = map[string][]string{
 		"image_classification": {"imagenet_resnet50"},
 		"text_to_text":         {"chatGLM_6B"},
+		"image_to_text":        {"blip-image-captioning-base"},
+		"text_to_image":        {"stable-diffusion-xl-base-1.0"},
 	}
 	AITYPE = map[string]string{
 		"1": OCTOPUS,

internal/svc/servicecontext.go

@@ -21,7 +21,7 @@ import (
 	"github.com/robfig/cron/v3"
 	"github.com/zeromicro/go-zero/core/logx"
 	"github.com/zeromicro/go-zero/zrpc"
-	hpcacclient "gitlink.org.cn/JointCloud/pcm-ac/hpcacclient"
+	"gitlink.org.cn/JointCloud/pcm-ac/hpcacclient"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/config"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler"
 	"gitlink.org.cn/JointCloud/pcm-coordinator/internal/scheduler/database"

internal/types/types.go

@@ -722,7 +722,14 @@ type AdapterInfo struct {
 }
 
 type AdapterResp struct {
-	Data AdapterInfo `json:"data,omitempty"`
+	Id           string `json:"id,omitempty" db:"id"`
+	Name         string `json:"name,omitempty" db:"name"`
+	Type         string `json:"type,omitempty" db:"type"`
+	ResourceType string `json:"resourceType,omitempty" db:"resource_type"`
+	Nickname     string `json:"nickname,omitempty" db:"nickname"`
+	Version      string `json:"version,omitempty" db:"version"`
+	Server       string `json:"server,omitempty" db:"server"`
+	CreateTime   string `json:"createTime,omitempty" db:"create_time" gorm:"autoCreateTime"`
 }
 
 type AdapterListResp struct {
@@ -2908,7 +2915,7 @@ type TrainingTaskStatResp struct {
 }
 
 type ChatReq struct {
-	ApiUrl  string                 `json:"apiUrl"`
+	Id      uint                   `json:"id,string"`
 	Method  string                 `json:"method,optional"`
 	ReqData map[string]interface{} `json:"reqData"`
 }
@@ -5897,6 +5904,24 @@ type Category struct {
 	Name string `json:"name"`
 }
 
+type DeployInstance struct {
+	Id           string `json:"id"`
+	DeployTaskId string `json:"deployTaskId"`
+	InstanceId   string `json:"instanceId"`
+	InstanceName string `json:"instanceName"`
+	AdapterId    string `json:"adapterId"`
+	AdapterName  string `json:"adapterName"`
+	ClusterId    string `json:"clusterId"`
+	ClusterName  string `json:"clusterName"`
+	ModelName    string `json:"modelName"`
+	ModelType    string `json:"modelType"`
+	InferCard    string `json:"inferCard"`
+	Status       string `json:"status"`
+	CreateTime   string `json:"createTime"`
+	UpdateTime   string `json:"updateTime"`
+	ClusterType  string `json:"clusterType"`
+}
+
 type ModelTypesResp struct {
 	ModelTypes []string `json:"types"`
 }
@@ -5910,20 +5935,13 @@ type ModelNamesResp struct {
 }
 
 type ImageInferenceReq struct {
-	TaskName        string           `form:"taskName"`
-	TaskDesc        string           `form:"taskDesc"`
-	ModelName       string           `form:"modelName"`
-	ModelType       string           `form:"modelType"`
-	AdapterId       string           `form:"adapterId"`
-	AiClusterIds    []string         `form:"aiClusterIds,optional"`
-	ResourceType    string           `form:"resourceType,optional"`
-	ComputeCard     string           `form:"card,optional"`
-	Strategy        string           `form:"strategy"`
-	StaticWeightMap map[string]int32 `form:"staticWeightMap,optional"`
-	Params          []string         `form:"params,optional"`
-	Envs            []string         `form:"envs,optional"`
-	Cmd             string           `form:"cmd,optional"`
-	Replica         int32            `form:"replicas,optional"`
+	TaskName        string                      `form:"taskName"`
+	TaskDesc        string                      `form:"taskDesc"`
+	ModelType       string                      `form:"modelType"`
+	InstanceIds     []int64                     `form:"instanceIds"`
+	Strategy        string                      `form:"strategy,,optional"`
+	StaticWeightMap map[string]map[string]int32 `form:"staticWeightMap,optional"`
+	Replica         int32                       `form:"replicas,optional"`
 }
 
 type ImageInferenceResp struct {
@@ -5969,6 +5987,18 @@ type TextToTextInferenceReq struct {
 type TextToTextInferenceResp struct {
 }
 
+type TextToImageInferenceReq struct {
+	TaskName     string   `form:"taskName"`
+	TaskDesc     string   `form:"taskDesc"`
+	ModelName    string   `form:"modelName"`
+	ModelType    string   `form:"modelType"`
+	AiClusterIds []string `form:"aiClusterIds"`
+}
+
+type TextToImageInferenceResp struct {
+	Result []byte `json:"result"`
+}
+
 type DeployInstanceListReq struct {
 	PageInfo
 }
@@ -6012,3 +6042,65 @@ type InferenceTaskStatResp struct {
 	Running int32 `json:"running"`
 	Total   int32 `json:"total"`
 }
+
+type StartAllByDeployTaskIdReq struct {
+	Id string `json:"deployTaskId"`
+}
+
+type StartAllByDeployTaskIdResp struct {
+}
+
+type StopAllByDeployTaskIdReq struct {
+	Id string `json:"deployTaskId"`
+}
+
+type StopAllByDeployTaskIdResp struct {
+}
+
+type GetRunningInstanceReq struct {
+	Id        string `form:"deployTaskId"`
+	AdapterId string `form:"adapterId"`
+}
+
+type GetRunningInstanceResp struct {
+	List interface{} `json:"list"`
+}
+
+type GetDeployTasksByTypeReq struct {
+	ModelType string `form:"modelType"`
+}
+
+type GetDeployTasksByTypeResp struct {
+	List interface{} `json:"list"`
+}
+
+type CreateDeployTaskReq struct {
+	TaskName          string              `form:"taskName"`
+	TaskDesc          string              `form:"taskDesc"`
+	ModelName         string              `form:"modelName"`
+	ModelType         string              `form:"modelType"`
+	AdapterClusterMap map[string][]string `form:"adapterClusterMap"`
+}
+
+type CreateDeployTaskResp struct {
+}
+
+type GetAdaptersByModelReq struct {
+	ModelName string `form:"modelName"`
+	ModelType string `form:"modelType"`
+}
+
+type GetAdaptersByModelResp struct {
+	Adapters []*AdapterAvail `json:"adapters"`
+}
+
+type AdapterAvail struct {
+	AdapterId   string          `json:"adapterId"`
+	AdapterName string          `json:"taskName"`
+	Clusters    []*ClusterAvail `json:"clusters"`
+}
+
+type ClusterAvail struct {
+	ClusterId   string `json:"clusterId"`
+	ClusterName string `json:"clusterName"`
+}

pkg/constants/task.go

@@ -28,4 +28,5 @@ const (
 	WaitStart   = "WaitStart"
 	Pending     = "Pending"
 	Stopped     = "Stopped"
+	Deploying   = "Deploying"
 )

pkg/models/aideployinstancetaskmodel.go

@@ -0,0 +1,29 @@
+package models
+
+import "github.com/zeromicro/go-zero/core/stores/sqlx"
+
+var _ AiDeployInstanceTaskModel = (*customAiDeployInstanceTaskModel)(nil)
+
+type (
+	// AiDeployInstanceTaskModel is an interface to be customized, add more methods here,
+	// and implement the added methods in customAiDeployInstanceTaskModel.
+	AiDeployInstanceTaskModel interface {
+		aiDeployInstanceTaskModel
+		withSession(session sqlx.Session) AiDeployInstanceTaskModel
+	}
+
+	customAiDeployInstanceTaskModel struct {
+		*defaultAiDeployInstanceTaskModel
+	}
+)
+
+// NewAiDeployInstanceTaskModel returns a model for the database table.
+func NewAiDeployInstanceTaskModel(conn sqlx.SqlConn) AiDeployInstanceTaskModel {
+	return &customAiDeployInstanceTaskModel{
+		defaultAiDeployInstanceTaskModel: newAiDeployInstanceTaskModel(conn),
+	}
+}
+
+func (m *customAiDeployInstanceTaskModel) withSession(session sqlx.Session) AiDeployInstanceTaskModel {
+	return NewAiDeployInstanceTaskModel(sqlx.NewSqlConnFromSession(session))
+}

pkg/models/aideployinstancetaskmodel_gen.go

@@ -0,0 +1,89 @@
+// Code generated by goctl. DO NOT EDIT.
+
+package models
+
+import (
+	"context"
+	"database/sql"
+	"fmt"
+	"strings"
+
+	"github.com/zeromicro/go-zero/core/stores/builder"
+	"github.com/zeromicro/go-zero/core/stores/sqlc"
+	"github.com/zeromicro/go-zero/core/stores/sqlx"
+	"github.com/zeromicro/go-zero/core/stringx"
+)
+
+var (
+	aiDeployInstanceTaskFieldNames          = builder.RawFieldNames(&AiDeployInstanceTask{})
+	aiDeployInstanceTaskRows                = strings.Join(aiDeployInstanceTaskFieldNames, ",")
+	aiDeployInstanceTaskRowsExpectAutoSet   = strings.Join(stringx.Remove(aiDeployInstanceTaskFieldNames, "`id`", "`create_at`", "`create_time`", "`created_at`", "`update_at`", "`update_time`", "`updated_at`"), ",")
+	aiDeployInstanceTaskRowsWithPlaceHolder = strings.Join(stringx.Remove(aiDeployInstanceTaskFieldNames, "`id`", "`create_at`", "`create_time`", "`created_at`", "`update_at`", "`update_time`", "`updated_at`"), "=?,") + "=?"
+)
+
+type (
+	aiDeployInstanceTaskModel interface {
+		Insert(ctx context.Context, data *AiDeployInstanceTask) (sql.Result, error)
+		FindOne(ctx context.Context, id int64) (*AiDeployInstanceTask, error)
+		Update(ctx context.Context, data *AiDeployInstanceTask) error
+		Delete(ctx context.Context, id int64) error
+	}
+
+	defaultAiDeployInstanceTaskModel struct {
+		conn  sqlx.SqlConn
+		table string
+	}
+
+	AiDeployInstanceTask struct {
+		Id         int64  `db:"id"`
+		Name       string `db:"name"`
+		ModelName  string `db:"model_name"`
+		ModelType  string `db:"model_type"`
+		Desc       string `db:"desc"`
+		CreateTime string `db:"create_time"`
+		UpdateTime string `db:"update_time"`
+	}
+)
+
+func newAiDeployInstanceTaskModel(conn sqlx.SqlConn) *defaultAiDeployInstanceTaskModel {
+	return &defaultAiDeployInstanceTaskModel{
+		conn:  conn,
+		table: "`ai_deploy_instance_task`",
+	}
+}
+
+func (m *defaultAiDeployInstanceTaskModel) Delete(ctx context.Context, id int64) error {
+	query := fmt.Sprintf("delete from %s where `id` = ?", m.table)
+	_, err := m.conn.ExecCtx(ctx, query, id)
+	return err
+}
+
+func (m *defaultAiDeployInstanceTaskModel) FindOne(ctx context.Context, id int64) (*AiDeployInstanceTask, error) {
+	query := fmt.Sprintf("select %s from %s where `id` = ? limit 1", aiDeployInstanceTaskRows, m.table)
+	var resp AiDeployInstanceTask
+	err := m.conn.QueryRowCtx(ctx, &resp, query, id)
+	switch err {
+	case nil:
+		return &resp, nil
+	case sqlc.ErrNotFound:
+		return nil, ErrNotFound
+	default:
+		return nil, err
+	}
+}
+
+func (m *defaultAiDeployInstanceTaskModel) Insert(ctx context.Context, data *AiDeployInstanceTask) (sql.Result, error) {
+	query := fmt.Sprintf("insert into %s (%s) values (?, ?, ?, ?)", m.table, aiDeployInstanceTaskRowsExpectAutoSet)
+	ret, err := m.conn.ExecCtx(ctx, query, data.Name, data.ModelName, data.ModelType, data.Desc)
+	return ret, err
+}
+
+func (m *defaultAiDeployInstanceTaskModel) Update(ctx context.Context, data *AiDeployInstanceTask) error {
+	query := fmt.Sprintf("update %s set %s where `id` = ?", m.table, aiDeployInstanceTaskRowsWithPlaceHolder)
+	_, err := m.conn.ExecCtx(ctx, query, data.Name, data.ModelName, data.ModelType, data.Desc, data.Id)
+	return err
+}
+
+func (m *defaultAiDeployInstanceTaskModel) tableName() string {
+	return m.table
+}

pkg/models/aiinferdeployinstancemodel_gen.go

@@ -35,20 +35,21 @@ type (
 	}
 
 	AiInferDeployInstance struct {
-		Id           int64  `db:"id"`
-		InstanceId   string `db:"instance_id"`
-		InstanceName string `db:"instance_name"`
-		AdapterId    int64  `db:"adapter_id"`
-		AdapterName  string `db:"adapter_name"`
-		ClusterId    int64  `db:"cluster_id"`
-		ClusterName  string `db:"cluster_name"`
-		ModelName    string `db:"model_name"`
-		ModelType    string `db:"model_type"`
-		InferCard    string `db:"infer_card"`
-		Status       string `db:"status"`
-		CreateTime   string `db:"create_time"`
-		UpdateTime   string `db:"update_time"`
-		ClusterType  string `db:"cluster_type"`
+		Id                   int64  `db:"id" json:"id,string"`
+		DeployInstanceTaskId int64  `db:"deploy_instance_task_id" json:"deployTaskId,string"`
+		InstanceId           string `db:"instance_id" json:"instanceId"`
+		InstanceName         string `db:"instance_name" json:"instanceName"`
+		AdapterId            int64  `db:"adapter_id" json:"adapterId,string"`
+		AdapterName          string `db:"adapter_name" json:"adapterName"	`
+		ClusterId            int64  `db:"cluster_id" json:"clusterId,string"`
+		ClusterName          string `db:"cluster_name" json:"clusterName"`
+		ModelName            string `db:"model_name" json:"modelName"`
+		ModelType            string `db:"model_type" json:"modelType"`
+		InferCard            string `db:"infer_card" json:"inferCard"`
+		Status               string `db:"status" json:"status"`
+		CreateTime           string `db:"create_time" json:"createTime"`
+		UpdateTime           string `db:"update_time" json:"updateTime"`
+		ClusterType          string `db:"cluster_type" json:"clusterType"`
 	}
 )
 

pkg/repository/result/httpResult.go

@@ -78,8 +78,18 @@ func HttpResult(r *http.Request, w http.ResponseWriter, resp interface{}, err er
 		}
 
 		logx.WithContext(r.Context()).Errorf("【API-ERR】 : %+v ", err)
-
-		httpx.WriteJson(w, http.StatusBadRequest, Error(errcode, errmsg, r.Context()))
+		// 判断如果err内容为"name already exists"，则将resp作为body.Data的信息返回
+		if errmsg == "name already exists" {
+			body := Body{
+				Code:    409,
+				Msg:     errmsg,
+				TraceID: traceIDFromContext(r.Context()),
+				Data:    resp,
+			}
+			httpx.WriteJson(w, http.StatusBadRequest, body)
+		} else {
+			httpx.WriteJson(w, http.StatusBadRequest, Error(errcode, errmsg, r.Context()))
+		}
 	}
 }
 

pkg/utils/httputils/http.go

@@ -206,7 +206,11 @@ func HttpClientWithBodyAndCode(method string, url string, payload io.Reader, tok
 func HttpClientWithScreen(method string, url string, payload io.Reader) (int, []byte, error) {
 	request, err := http.NewRequest(method, url, payload)
 
-	client := &http.Client{}
+	client := &http.Client{
+		Transport: &http.Transport{
+			TLSClientConfig: &tls.Config{InsecureSkipVerify: true},
+		},
+	}
 	res, err := client.Do(request)
 	if err != nil {
 		log.Fatal(err)