jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

Enable dataprep health check for examples (#1800)

Browse Source 
Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Letong Han
2025-04-17 15:52:06 +08:00
committed by GitHub
parent ae31e4fb75
commit 7c6189cf43
12 changed files with 201 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -20,7 +20,7 @@ services:
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
@@ -42,7 +42,7 @@ services:
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
@@ -84,7 +84,10 @@ services:
image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
container_name: codegen-xeon-backend-server
depends_on:
- llm-base
llm-base:
condition: service_started
dataprep-redis-server:
condition: service_healthy
ports:
- "7778:7778"
environment:
@@ -139,6 +142,11 @@ services:
INDEX_NAME: ${INDEX_NAME}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_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: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -156,7 +164,7 @@ services:
host_ip: ${host_ip}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
healthcheck:
test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_EMBEDDER_PORT}/health"]
test: ["CMD", "curl", "-f", "http://localhost:80/health"]
interval: 10s
timeout: 6s
retries: 48

16
CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -23,7 +23,7 @@ services:
USE_FLASH_ATTENTION: true
FLASH_ATTENTION_RECOMPUTE: true
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
@@ -53,7 +53,7 @@ services:
NUM_CARDS: ${NUM_CARDS:-1}
VLLM_TORCH_PROFILER_DIR: "/mnt"
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
@@ -99,7 +99,10 @@ services:
image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
container_name: codegen-gaudi-backend-server
depends_on:
- llm-base
llm-base:
condition: service_started
dataprep-redis-server:
condition: service_healthy
ports:
- "7778:7778"
environment:
@@ -155,6 +158,11 @@ services:
INDEX_NAME: ${INDEX_NAME}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_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: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -172,7 +180,7 @@ services:
host_ip: ${host_ip}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
healthcheck:
test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_EMBEDDER_PORT}/health"]
test: ["CMD", "curl", "-f", "http://localhost:80/health"]
interval: 10s
timeout: 6s
retries: 48