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

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

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.

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:

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:

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: