jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Update Code and README for GenAIComps Refactor (#1285)

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

6
SearchQnA/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -11,7 +11,7 @@ First of all, you need to build Docker Images locally. This step can be ignored
```bash
git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps
docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/tei/langchain/Dockerfile .
docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile .
```
### 2. Build Retriever Image
@@ -23,13 +23,13 @@ docker build --no-cache -t opea/web-retriever-chroma:latest --build-arg https_pr
### 3. Build Rerank Image
```bash
docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/tei/Dockerfile .
docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/reranks/src/Dockerfile .
```
### 4. Build LLM Image
```bash
docker build --no-cache -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 --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
```
### 5. Build MegaService Docker Image

43
SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -4,6 +4,7 @@
services:
tei-embedding-service:
image: ghcr.io/huggingface/tei-gaudi:1.5.0
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
container_name: tei-embedding-gaudi-server
ports:
- "3001:80"
@@ -22,12 +23,18 @@ services:
MAX_WARMUP_SEQUENCE_LENGTH: 512
INIT_HCCL_ON_ACQUIRE: 0
ENABLE_EXPERIMENTAL_FLAGS: true
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:3001/health || exit 1"]
interval: 10s
timeout: 10s
retries: 60
embedding:
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
container_name: embedding-tei-gaudi-server
depends_on:
- tei-embedding-service
tei-embedding-service:
condition: service_healthy
ports:
- "3002:6000"
ipc: host
@@ -36,6 +43,8 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
web-retriever:
image: ${REGISTRY:-opea}/web-retriever-chroma:${TAG:-latest}
@@ -53,6 +62,7 @@ services:
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${RERANK_MODEL_ID} --auto-truncate"
container_name: tei-reranking-server
ports:
- "3004:80"
@@ -63,12 +73,18 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:3004/health || exit 1"]
interval: 10s
timeout: 10s
retries: 60
reranking:
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-xeon-server
container_name: reranking-tei-gaudi-server
depends_on:
- tei-reranking-service
tei-reranking-service:
condition: service_healthy
ports:
- "3005:8000"
ipc: host
@@ -76,8 +92,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
RERANK_TYPE: ${RERANK_TYPE}
TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.0.6
@@ -99,6 +117,11 @@ services:
LIMIT_HPU_GRAPH: true
USE_FLASH_ATTENTION: true
FLASH_ATTENTION_RECOMPUTE: true
healthcheck:
test: ["CMD-SHELL", "sleep 800 && exit 0"]
interval: 1s
timeout: 805s
retries: 1
runtime: habana
cap_add:
- SYS_NICE
@@ -108,7 +131,8 @@ services:
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-gaudi-server
depends_on:
- tgi-service
tgi-service:
condition: service_healthy
ports:
- "3007:9000"
ipc: host
@@ -116,10 +140,12 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
searchqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/searchqna:${TAG:-latest}
@@ -147,6 +173,7 @@ services:
- WEB_RETRIEVER_SERVICE_PORT=${WEB_RETRIEVER_SERVICE_PORT}
- RERANK_SERVICE_PORT=${RERANK_SERVICE_PORT}
- LLM_SERVICE_PORT=${LLM_SERVICE_PORT}
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
searchqna-gaudi-ui-server: