add docsum example e2e test for GMC. (#347)
* add docsum example e2e test for GMC. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * fix curl error for docsum. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * change the manifest e2e yaml. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * change the image format. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * fixing image mapping error. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * change the gmc e2e test. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * accelarate the e2e test. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * change the gmc e2e configuration. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * retrigger. Signed-off-by: zhlsunshine <huailong.zhang@intel.com> Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: Yingchun Guo <yingchun.guo@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Malini Bhandaru <malini.bhandaru@intel.com>
This commit is contained in:
35
DocSum/kubernetes/docsum_gaudi.yaml
Normal file
35
DocSum/kubernetes/docsum_gaudi.yaml
Normal file
@@ -0,0 +1,35 @@
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: gmc.opea.io/v1alpha3
|
||||
kind: GMConnector
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: gmconnector
|
||||
app.kubernetes.io/managed-by: kustomize
|
||||
gmc/platform: gaudi
|
||||
name: docsum
|
||||
namespace: docsum
|
||||
spec:
|
||||
routerConfig:
|
||||
name: router
|
||||
serviceName: router-service
|
||||
nodes:
|
||||
root:
|
||||
routerType: Sequence
|
||||
steps:
|
||||
- name: DocSumGaudi
|
||||
data: $response
|
||||
internalService:
|
||||
serviceName: docsum-llm-uservice
|
||||
config:
|
||||
endpoint: /v1/chat/docsum
|
||||
PORT: "9009"
|
||||
- name: TgiGaudi
|
||||
internalService:
|
||||
serviceName: tgi-gaudi-svc
|
||||
config:
|
||||
LANGCHAIN_TRACING_V2: "false"
|
||||
LANGCHAIN_PROJECT: "opea-llm-service"
|
||||
endpoint: /generate
|
||||
isDownstreamService: true
|
||||
35
DocSum/kubernetes/docsum_xeon.yaml
Normal file
35
DocSum/kubernetes/docsum_xeon.yaml
Normal file
@@ -0,0 +1,35 @@
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
apiVersion: gmc.opea.io/v1alpha3
|
||||
kind: GMConnector
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: gmconnector
|
||||
app.kubernetes.io/managed-by: kustomize
|
||||
gmc/platform: xeon
|
||||
name: docsum
|
||||
namespace: docsum
|
||||
spec:
|
||||
routerConfig:
|
||||
name: router
|
||||
serviceName: router-service
|
||||
nodes:
|
||||
root:
|
||||
routerType: Sequence
|
||||
steps:
|
||||
- name: DocSum
|
||||
data: $response
|
||||
internalService:
|
||||
serviceName: docsum-llm-uservice
|
||||
config:
|
||||
endpoint: /v1/chat/docsum
|
||||
PORT: "9009"
|
||||
- name: Tgi
|
||||
internalService:
|
||||
serviceName: tgi-svc
|
||||
config:
|
||||
LANGCHAIN_TRACING_V2: "false"
|
||||
LANGCHAIN_PROJECT: "opea-llm-service"
|
||||
endpoint: /generate
|
||||
isDownstreamService: true
|
||||
Reference in New Issue
Block a user