f5f1e323bb
* revert the LLM model to meta-llama/CodeLlama-7b-hf Signed-off-by: zhlsunshine <huailong.zhang@intel.com>
35 lines
841 B
YAML
35 lines
841 B
YAML
# 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: codegen
|
|
namespace: codegen
|
|
spec:
|
|
routerConfig:
|
|
name: router
|
|
serviceName: router-service
|
|
nodes:
|
|
root:
|
|
routerType: Sequence
|
|
steps:
|
|
- name: Llm
|
|
data: $response
|
|
internalService:
|
|
serviceName: llm-service
|
|
config:
|
|
endpoint: /v1/chat/completions
|
|
TGI_LLM_ENDPOINT: tgi-service
|
|
- name: Tgi
|
|
internalService:
|
|
serviceName: tgi-service
|
|
config:
|
|
MODEL_ID: meta-llama/CodeLlama-7b-hf
|
|
endpoint: /generate
|
|
isDownstreamService: true
|