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

Use fixed version of TEI Gaudi for stability (#1101)

Browse Source 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: Malini Bhandaru <malini.bhandaru@intel.com>
This commit is contained in:
lvliang-intel
2024-11-14 02:45:50 +08:00
committed by GitHub
parent b5f95f735e
commit 9ff7df9202
25 changed files with 30 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ChatQnA/benchmark/performance-deprecated/oob/with_rerank/eight_gaudi/oob_eight_gaudi_with_rerank.yaml
View File

@@ -327,7 +327,7 @@ spec:
envFrom:
- configMapRef:
name: qna-config
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
imagePullPolicy: IfNotPresent
name: reranking-dependency-deploy
ports:

2
ChatQnA/benchmark/performance-deprecated/oob/with_rerank/four_gaudi/oob_four_gaudi_with_rerank.yaml
View File

@@ -327,7 +327,7 @@ spec:
envFrom:
- configMapRef:
name: qna-config
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
imagePullPolicy: IfNotPresent
name: reranking-dependency-deploy
ports:

2
ChatQnA/benchmark/performance-deprecated/oob/with_rerank/single_gaudi/oob_single_gaudi_with_rerank.yaml
View File

@@ -327,7 +327,7 @@ spec:
envFrom:
- configMapRef:
name: qna-config
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
imagePullPolicy: IfNotPresent
name: reranking-dependency-deploy
ports:

2
ChatQnA/benchmark/performance-deprecated/oob/with_rerank/two_gaudi/oob_two_gaudi_with_rerank.yaml
View File

@@ -327,7 +327,7 @@ spec:
envFrom:
- configMapRef:
name: qna-config
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
imagePullPolicy: IfNotPresent
name: reranking-dependency-deploy
ports:

2
ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/eight_gaudi/eight_gaudi_with_rerank.yaml
View File

@@ -345,7 +345,7 @@ spec:
envFrom:
- configMapRef:
name: qna-config
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
imagePullPolicy: IfNotPresent
name: reranking-dependency-deploy
ports:

2
ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/four_gaudi/tuned_four_gaudi_with_rerank.yaml
View File

@@ -345,7 +345,7 @@ spec:
envFrom:
- configMapRef:
name: qna-config
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
imagePullPolicy: IfNotPresent
name: reranking-dependency-deploy
ports:

2
ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/single_gaudi/tuned_single_gaudi_with_rerank.yaml
View File

@@ -345,7 +345,7 @@ spec:
envFrom:
- configMapRef:
name: qna-config
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
imagePullPolicy: IfNotPresent
name: reranking-dependency-deploy
ports:

2
ChatQnA/benchmark/performance-deprecated/tuned/with_rerank/two_gaudi/tuned_two_gaudi_with_rerank.yaml
View File

@@ -345,7 +345,7 @@ spec:
envFrom:
- configMapRef:
name: qna-config
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
imagePullPolicy: IfNotPresent
name: reranking-dependency-deploy
ports:

2
ChatQnA/chatqna.yaml
View File

@@ -19,7 +19,7 @@ opea_micro_services:
tei-embedding-service:
host: ${TEI_EMBEDDING_SERVICE_IP}
ports: ${TEI_EMBEDDING_SERVICE_PORT}
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
volumes:
- "./data:/data"
runtime: habana

2
ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -57,7 +57,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
container_name: tei-reranking-gaudi-server
ports:
- "8808:80"

2
ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml
View File

@@ -96,7 +96,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
container_name: tei-reranking-gaudi-server
ports:
- "8808:80"

2
ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml
View File

@@ -57,7 +57,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
container_name: tei-reranking-gaudi-server
ports:
- "8808:80"

2
ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md
View File

@@ -48,8 +48,8 @@ f810f3b4d329 opea/embedding-tei:latest "python e
2fa17d84605f opea/dataprep-redis:latest "python prepare_doc_…" 2 minutes ago Up 2 minutes 0.0.0.0:6007->6007/tcp, :::6007->6007/tcp dataprep-redis-server
69e1fb59e92c opea/retriever-redis:latest "/home/user/comps/re…" 2 minutes ago Up 2 minutes 0.0.0.0:7000->7000/tcp, :::7000->7000/tcp retriever-redis-server
313b9d14928a opea/reranking-tei:latest "python reranking_te…" 2 minutes ago Up 2 minutes 0.0.0.0:8000->8000/tcp, :::8000->8000/tcp reranking-tei-gaudi-server
174bd43fa6b5 ghcr.io/huggingface/tei-gaudi:1.5.0 "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8090->80/tcp, :::8090->80/tcp tei-embedding-gaudi-server
05c40b636239 ghcr.io/huggingface/tgi-gaudi:2.0.6 "text-generation-lau…" 2 minutes ago Exited (1) About a minute ago tgi-gaudi-server
174bd43fa6b5 ghcr.io/huggingface/tei-gaudi:latest "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8090->80/tcp, :::8090->80/tcp tei-embedding-gaudi-server
74084469aa33 redis/redis-stack:7.2.0-v9 "/entrypoint.sh" 2 minutes ago Up 2 minutes 0.0.0.0:6379->6379/tcp, :::6379->6379/tcp, 0.0.0.0:8001->8001/tcp, :::8001->8001/tcp redis-vector-db
88399dbc9e43 ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8808->80/tcp, :::8808->80/tcp tei-reranking-gaudi-server
```

5
ChatQnA/kubernetes/intel/README_gmc.md
View File

@@ -24,8 +24,9 @@ The ChatQnA uses the below prebuilt images if you choose a Xeon deployment
Should you desire to use the Gaudi accelerator, two alternate images are used for the embedding and llm services.
For Gaudi:
- tei-embedding-service: ghcr.io/huggingface/tei-gaudi:latest
- tgi-service: gghcr.io/huggingface/tgi-gaudi:2.0.6
tei-embedding-service: ghcr.io/huggingface/tei-gaudi:1.5.0
tgi-service: gghcr.io/huggingface/tgi-gaudi:2.0.6
> [NOTE]
> Please refer to [Xeon README](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/docker_compose/intel/cpu/xeon/README.md) or [Gaudi README](https://github.com/opea-project/GenAIExamples/blob/main/ChatQnA/docker_compose/intel/hpu/gaudi/README.md) to build the OPEA images. These too will be available on Docker Hub soon to simplify use.

4
ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml
View File

@@ -920,8 +920,8 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/tei-gaudi:latest"
imagePullPolicy: Always
image: "ghcr.io/huggingface/tei-gaudi:1.5.0"
imagePullPolicy: IfNotPresent
args:
- "--auto-truncate"
volumeMounts:

4
ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml
View File

@@ -1106,8 +1106,8 @@ spec:
privileged: true
capabilities:
add: ["SYS_NICE"]
image: "ghcr.io/huggingface/tei-gaudi:latest"
imagePullPolicy: Always
image: "ghcr.io/huggingface/tei-gaudi:1.5.0"
imagePullPolicy: IfNotPresent
args:
- "--auto-truncate"
volumeMounts:

4
ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml
View File

@@ -741,8 +741,8 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/tei-gaudi:latest"
imagePullPolicy: Always
image: "ghcr.io/huggingface/tei-gaudi:1.5.0"
imagePullPolicy: IfNotPresent
args:
- "--auto-truncate"
volumeMounts:

2
ChatQnA/tests/test_compose_guardrails_on_gaudi.sh
View File

@@ -24,7 +24,7 @@ function build_docker_images() {
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker pull ghcr.io/huggingface/tei-gaudi:latest
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s
}

2
ChatQnA/tests/test_compose_on_gaudi.sh
View File

@@ -24,7 +24,7 @@ function build_docker_images() {
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker pull ghcr.io/huggingface/tei-gaudi:latest
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s
}

2
ChatQnA/tests/test_compose_vllm_on_gaudi.sh
View File

@@ -24,7 +24,7 @@ function build_docker_images() {
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker pull ghcr.io/huggingface/tei-gaudi:latest
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s
}

2
ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh
View File

@@ -24,7 +24,7 @@ function build_docker_images() {
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker pull ghcr.io/huggingface/tei-gaudi:latest
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s
}

2
DocIndexRetriever/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -28,7 +28,7 @@ services:
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
container_name: tei-embedding-gaudi-server
ports:
- "8090:80"

2
DocIndexRetriever/tests/test_compose_on_gaudi.sh
View File

@@ -24,7 +24,7 @@ function build_docker_images() {
docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull redis/redis-stack:7.2.0-v9
docker pull ghcr.io/huggingface/tei-gaudi:latest
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s
}

2
SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -3,7 +3,7 @@
services:
tei-embedding-service:
image: ghcr.io/huggingface/tei-gaudi:latest
image: ghcr.io/huggingface/tei-gaudi:1.5.0
container_name: tei-embedding-gaudi-server
ports:
- "3001:80"

2
SearchQnA/tests/test_compose_on_gaudi.sh
View File

@@ -23,8 +23,8 @@ function build_docker_images() {
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
docker pull ghcr.io/huggingface/tei-gaudi:latest
docker images && sleep 1s
}