Files
GenAIExamples/ChatQnA/kubernetes/gmc/chatQnA_xeon.yaml
dolpher c795ef2203 Add helm deployment instructions for GenAIExamples (#1373)
Add helm deployment instructions for ChatQnA, AgentQnA, AudioQnA, CodeTrans, DocSum, FaqGen and VisualQnA

Signed-off-by: Dolpher Du <dolpher.du@intel.com>
2025-01-10 09:55:31 +08:00

69 lines
1.8 KiB
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: chatqa
namespace: chatqa
spec:
routerConfig:
name: router
serviceName: router-service
nodes:
root:
routerType: Sequence
steps:
- name: Embedding
internalService:
serviceName: embedding-svc
config:
endpoint: /v1/embeddings
TEI_EMBEDDING_ENDPOINT: tei-embedding-svc
- name: TeiEmbedding
internalService:
serviceName: tei-embedding-svc
isDownstreamService: true
- name: Retriever
data: $response
internalService:
serviceName: retriever-svc
config:
endpoint: /v1/retrieval
REDIS_URL: redis-vector-db
TEI_EMBEDDING_ENDPOINT: tei-embedding-svc
- name: VectorDB
internalService:
serviceName: redis-vector-db
isDownstreamService: true
- name: Reranking
data: $response
internalService:
serviceName: reranking-svc
config:
endpoint: /v1/reranking
TEI_RERANKING_ENDPOINT: tei-reranking-svc
- name: TeiReranking
internalService:
serviceName: tei-reranking-svc
config:
endpoint: /rerank
isDownstreamService: true
- name: Llm
data: $response
internalService:
serviceName: llm-svc
config:
endpoint: /v1/chat/completions
TGI_LLM_ENDPOINT: tgi-service-m
- name: Tgi
internalService:
serviceName: tgi-service-m
config:
endpoint: /generate
isDownstreamService: true