Add dataprep microservice to chatQnA example and the e2e test (#589)

Signed-off-by: zhlsunshine <huailong.zhang@intel.com>
This commit is contained in:
Steve Zhang
2024-08-14 14:39:46 +08:00
committed by GitHub
parent 64bfea9054
commit 1c23d87aa2
4 changed files with 320 additions and 37 deletions

View File

@@ -0,0 +1,76 @@
# 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: 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-gaudi-svc
- name: TeiEmbeddingGaudi
internalService:
serviceName: tei-embedding-gaudi-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-gaudi-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-gaudi-svc
- name: TgiGaudi
internalService:
serviceName: tgi-gaudi-svc
config:
endpoint: /generate
isDownstreamService: true
- name: DataPrep
internalService:
serviceName: data-prep-svc
config:
endpoint: /v1/dataprep
REDIS_URL: redis-vector-db
TEI_ENDPOINT: tei-embedding-gaudi-svc
isDownstreamService: true

View File

@@ -0,0 +1,76 @@
# 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
- name: DataPrep
internalService:
serviceName: data-prep-svc
config:
endpoint: /v1/dataprep
REDIS_URL: redis-vector-db
TEI_ENDPOINT: tei-embedding-svc
isDownstreamService: true