-
Notifications
You must be signed in to change notification settings - Fork 339
Expand file tree
/
Copy pathcompose_tgi_openeuler.yaml
More file actions
174 lines (172 loc) · 5.35 KB
/
compose_tgi_openeuler.yaml
File metadata and controls
174 lines (172 loc) · 5.35 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
# Copyright (C) 2025 Huawei Technologies Co., Ltd.
# SPDX-License-Identifier: Apache-2.0
services:
tgi-service:
image: openeuler/text-generation-inference-cpu:2.4.0-oe2403lts
container_name: tgi-server
ports:
- "8028:80"
volumes:
- "${MODEL_CACHE:-./data}:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
llm-base:
image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}-openeuler
container_name: llm-textgen-server
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HF_TOKEN: ${HF_TOKEN}
restart: unless-stopped
llm-tgi-service:
extends: llm-base
container_name: llm-codegen-tgi-server
ports:
- "9000:9000"
ipc: host
depends_on:
tgi-service:
condition: service_healthy
codegen-xeon-backend-server:
image: ${REGISTRY:-opea}/codegen:${TAG:-latest}-openeuler
container_name: codegen-xeon-backend-server
depends_on:
llm-base:
condition: service_started
dataprep-redis-server:
condition: service_healthy
ports:
- "7778:7778"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- LLM_SERVICE_HOST_IP=${LLM_SERVICE_HOST_IP}
- RETRIEVAL_SERVICE_HOST_IP=${RETRIEVAL_SERVICE_HOST_IP}
- REDIS_RETRIEVER_PORT=${REDIS_RETRIEVER_PORT}
- TEI_EMBEDDING_HOST_IP=${TEI_EMBEDDING_HOST_IP}
- EMBEDDER_PORT=${EMBEDDER_PORT}
ipc: host
restart: always
codegen-xeon-ui-server:
image: ${REGISTRY:-opea}/codegen-ui:${TAG:-latest}-openeuler
container_name: codegen-xeon-ui-server
depends_on:
- codegen-xeon-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- BASIC_URL=${BACKEND_SERVICE_ENDPOINT}
- MEGA_SERVICE_PORT=${MEGA_SERVICE_PORT}
- host_ip=${host_ip}
- DATAPREP_ENDPOINT=${DATAPREP_ENDPOINT}
- DATAPREP_REDIS_PORT=${DATAPREP_REDIS_PORT}
ipc: host
restart: always
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
container_name: redis-vector-db
ports:
- "${REDIS_DB_PORT}:${REDIS_DB_PORT}"
- "${REDIS_INSIGHTS_PORT}:${REDIS_INSIGHTS_PORT}"
dataprep-redis-server:
image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}-openeuler
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
ports:
- "${DATAPREP_REDIS_PORT}:5000"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_HOST: ${host_ip}
INDEX_NAME: ${INDEX_NAME}
HF_TOKEN: ${HF_TOKEN}
LOGFLAG: true
healthcheck:
test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
interval: 10s
timeout: 5s
retries: 10
restart: unless-stopped
tei-embedding-serving:
image: openeuler/text-embeddings-inference-cpu:1.7.0-oe2403lts
container_name: tei-embedding-serving
entrypoint: /bin/sh -c "yum update -y && yum install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
ports:
- "${TEI_EMBEDDER_PORT:-12000}:80"
volumes:
- "./data:/data"
shm_size: 1g
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
host_ip: ${host_ip}
HF_TOKEN: ${HF_TOKEN}
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:80/health"]
interval: 10s
timeout: 6s
retries: 48
tei-embedding-server:
image: ${REGISTRY:-opea}/embedding:${TAG:-latest}-openeuler
container_name: tei-embedding-server
ports:
- "${EMBEDDER_PORT:-10201}:6000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
EMBEDDING_COMPONENT_NAME: "OPEA_TEI_EMBEDDING"
depends_on:
tei-embedding-serving:
condition: service_healthy
restart: unless-stopped
retriever-redis:
image: ${REGISTRY:-opea}/retriever:${TAG:-latest}-openeuler
container_name: retriever-redis
depends_on:
- redis-vector-db
ports:
- "${REDIS_RETRIEVER_PORT}:${REDIS_RETRIEVER_PORT}"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_DB_PORT: ${REDIS_DB_PORT}
REDIS_INSIGHTS_PORT: ${REDIS_INSIGHTS_PORT}
REDIS_RETRIEVER_PORT: ${REDIS_RETRIEVER_PORT}
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HF_TOKEN: ${HF_TOKEN}
LOGFLAG: ${LOGFLAG}
RETRIEVER_COMPONENT_NAME: ${RETRIEVER_COMPONENT_NAME:-OPEA_RETRIEVER_REDIS}
restart: unless-stopped
networks:
default:
driver: bridge