Update Code and README for GenAIComps Refactor (#1285)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
Signed-off-by: letonghan <letong.han@intel.com>
Signed-off-by: ZePan110 <ze.pan@intel.com>
Signed-off-by: WenjiaoYue <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>
This commit is contained in:
chen, suyue
2025-01-02 20:03:26 +08:00
committed by GitHub
parent 72f8079289
commit 5c7a5bd850
103 changed files with 655 additions and 438 deletions

View File

@@ -10,7 +10,7 @@ git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps
### Build Docker image
docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
```
### Build the MegaService Docker Image

View File

@@ -15,6 +15,12 @@ services:
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:${CODEGEN_TGI_SERVICE_PORT:-8028}/health || exit 1"]
interval: 10s
timeout: 10s
retries: 100
shm_size: 1g
devices:
- /dev/kfd:/dev/kfd
@@ -31,7 +37,8 @@ services:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: codegen-llm-server
depends_on:
- codegen-tgi-service
codegen-tgi-service:
condition: service_healthy
ports:
- "${CODEGEN_LLM_SERVICE_PORT:-9000}:9000"
ipc: host
@@ -39,7 +46,8 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: "http://codegen-tgi-service"
LLM_ENDPOINT: "http://codegen-tgi-service"
LLM_MODEL_ID: ${CODEGEN_LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codegen-backend-server: