示例配置文件
{
"SupportedInstanceTypes": [
"ecs.gn7i-c16g1.4xlarge",
"ecs.gn7i-c32g1.16xlarge",
"ecs.gn7i-c32g1.32xlarge",
"ecs.gn7i-c32g1.8xlarge",
"ecs.gn7i-c8g1.2xlarge",
"ecs.gn7i-c8g1.2xlarge.limit",
"ecs.gn8is-2x.8xlarge",
"ecs.gn8is-4x.16xlarge",
"ecs.gn8is-8x.32xlarge",
"ecs.gn8is.2xlarge",
"ecs.gn8is.4xlarge",
"ecs.gn8v.6xlarge",
"ecs.gn8v-2x.12xlarge",
"ecs.gn8v-4x.24xlarge",
"ecs.gn8v-8x.48xlarge",
"ml.gu7i.c128m752.4-gu30",
"ml.gu7i.c16m60.1-gu30",
"ml.gu7i.c32m188.1-gu30",
"ml.gu7i.c64m376.2-gu30",
"ml.gu7i.c8m30.1-gu30",
"ml.gu8is.c128m1024.8-gu60",
"ml.gu8is.c16m128.1-gu60",
"ml.gu8is.c32m256.2-gu60",
"ml.gu8is.c64m512.4-gu60",
"ml.gu8v.c192m1024.8-gu120",
"ml.gu8v.c24m128.1-gu120",
"ml.gu8v.c48m256.2-gu120",
"ml.gu8v.c96m512.4-gu120"
],
"cloud": {
"computing": {
"instances": [
{
"type": "ecs.gn7i-c16g1.4xlarge"
}
]
},
"networking": {
"security_group_id": "sg-bp****************dj",
"vpc_id": "vpc-bp*****************po",
"vswitch_id": "vsw-bp*****************eu"
}
},
"containers": [
{
"image": "eas-registry-vpc.cn-hangzhou.cr.aliyuncs.com/pai-eas/pai-rag:0.2.0-nginx",
"port": 8680,
"script": "/docker-entrypoint.sh nginx"
},
{
"env": [
{
"name": "PAIRAG_RAG__SETTING__interactive",
"value": "false"
}
],
"image": "eas-registry-vpc.cn-hangzhou.cr.aliyuncs.com/pai-eas/pai-rag:0.2.0-ui",
"port": 8002,
"script": "pai_rag ui"
},
{
"env": [
{
"name": "PAIRAG_RAG__INDEX__VECTOR_STORE__type",
"value": "tablestore"
},
{
"name": "PAIRAG_RAG__INDEX__VECTOR_STORE__endpoint",
"value": "https://d0********9c.cn-hangzhou.vpc.tablestore.aliyuncs.com"
},
{
"name": "PAIRAG_RAG__INDEX__VECTOR_STORE__instance_name",
"value": "d0********9c"
},
{
"name": "PAIRAG_RAG__INDEX__VECTOR_STORE__access_key_id",
"value": "LT********************u7"
},
{
"name": "PAIRAG_RAG__INDEX__VECTOR_STORE__access_key_secret",
"value": "nI**************************GF"
},
{
"name": "PAIRAG_RAG__INDEX__VECTOR_STORE__table_name",
"value": "pai_rag"
},
{
"name": "PAIRAG_RAG__DATA_READER__enable_image_ocr",
"value": "false"
},
{
"name": "PAIRAG_RAG__LLM__source",
"value": "PaiEas"
},
{
"name": "PAIRAG_RAG__LLM__endpoint",
"value": "http://127.0.0.1:8000"
},
{
"name": "PAIRAG_RAG__LLM__token",
"value": "abc"
},
{
"name": "PAIRAG_RAG__EMBEDDING__source",
"value": "HuggingFace"
},
{
"name": "PAIRAG_RAG__EMBEDDING__model_name",
"value": "bge-small-zh-v1.5"
}
],
"image": "eas-registry-vpc.cn-hangzhou.cr.aliyuncs.com/pai-eas/pai-rag:0.2.0",
"port": 8001,
"script": "pai_rag serve"
},
{
"image": "eas-registry-vpc.cn-hangzhou.cr.aliyuncs.com/pai-eas/sglang:v0.4.1.post6-cu124_netcat_accelerated",
"port": 8000,
"script": "gpu_count=$(nvidia-smi --query-gpu=count --format=csv,noheader | wc -l); python3 -m sglang.launch_server --model-path /model_dir --host 0.0.0.0 --port 8000 --tp $gpu_count --trust-remote-code --enable-metrics --served-model-name DeepSeek-R1-Distill-Qwen-1.5B"
}
],
"labels": {
"PAI_RAG_VERSION": "0.1_custom",
"system_eas_deployment_type": "rag",
"system_eas_rag_open_source_model_acc_type": "SGLang-Accelerate:Single-Node-Standard",
"system_eas_rag_open_source_model_name": "DeepSeek-R1-Distill-Qwen-1.5B"
},
"metadata": {
"cpu": 16,
"enable_webservice": true,
"gpu": 1,
"instance": 1,
"memory": 60000,
"name": "rag_tablestore",
"rpc": {
"keepalive": 900000000
},
"shm_size": 100
},
"storage": [
{
"mount_path": "/model_dir/",
"oss": {
"endpoint": "cn-hangzhou-internal.oss-data-acc.aliyuncs.com",
"path": "oss://pai-quickstart-cn-hangzhou/modelscope/models/DeepSeek-R1-Distill-Qwen-1.5B/"
},
"properties": {
"resource_type": "model",
"resource_use": "base"
}
}
]
}
参数说明
如果您想了解EAS部署的其它参数，请参见JSON部署参数说明。
