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

Update TEI docker image to 1.6 (#1650)

Browse Source 
Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
This commit is contained in:
xiguiw
2025-03-27 09:40:22 +08:00
committed by GitHub
parent 03179296b4
commit 87baeb833d
43 changed files with 60 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AgentQnA/tests/step1_build_images.sh
View File

@@ -22,7 +22,7 @@ function build_docker_images_for_retrieval_tool(){
echo "Build all the images with --no-cache..." echo "Build all the images with --no-cache..."
service_list="doc-index-retriever dataprep embedding retriever reranking" service_list="doc-index-retriever dataprep embedding retriever reranking"
docker compose -f build.yaml build ${service_list} --no-cache docker compose -f build.yaml build ${service_list} --no-cache
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

4
ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml
View File

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "6006:80" - "6006:80"
@@ -59,7 +59,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-reranking-server container_name: tei-reranking-server
ports: ports:
- "8808:80" - "8808:80"

4
ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -33,7 +33,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "6006:80" - "6006:80"
@@ -66,7 +66,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-reranking-server container_name: tei-reranking-server
ports: ports:
- "8808:80" - "8808:80"

4
ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml
View File

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "6006:80" - "6006:80"
@@ -59,7 +59,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-reranking-server container_name: tei-reranking-server
ports: ports:
- "8808:80" - "8808:80"

4
ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen_tgi.yaml
View File

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "6006:80" - "6006:80"
@@ -59,7 +59,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-reranking-server container_name: tei-reranking-server
ports: ports:
- "8808:80" - "8808:80"

4
ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml
View File

@@ -108,7 +108,7 @@ services:
restart: unless-stopped restart: unless-stopped
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "6006:80" - "6006:80"
@@ -122,7 +122,7 @@ services:
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-reranking-server container_name: tei-reranking-server
ports: ports:
- "8808:80" - "8808:80"

4
ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml
View File

@@ -23,7 +23,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_PINECONE" DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_PINECONE"
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "6006:80" - "6006:80"
@@ -54,7 +54,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_PINECONE" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_PINECONE"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-reranking-server container_name: tei-reranking-server
ports: ports:
- "8808:80" - "8808:80"

4
ChatQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml
View File

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "6006:80" - "6006:80"
@@ -59,7 +59,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-reranking-server container_name: tei-reranking-server
ports: ports:
- "8808:80" - "8808:80"

2
ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml
View File

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "6006:80" - "6006:80"

16
ChatQnA/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -95,7 +95,7 @@ d560c232b120 opea/retriever:latest
a1d7ca2d3787 ghcr.io/huggingface/tei-gaudi:1.5.0 "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8808->80/tcp, [::]:8808->80/tcp tei-reranking-gaudi-server a1d7ca2d3787 ghcr.io/huggingface/tei-gaudi:1.5.0 "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8808->80/tcp, [::]:8808->80/tcp tei-reranking-gaudi-server
9a9f3fd4fd4c opea/vllm-gaudi:latest "python3 -m vllm.ent…" 2 minutes ago Exited (1) 2 minutes ago vllm-gaudi-server 9a9f3fd4fd4c opea/vllm-gaudi:latest "python3 -m vllm.ent…" 2 minutes ago Exited (1) 2 minutes ago vllm-gaudi-server
1ab9bbdf5182 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 1ab9bbdf5182 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
9ee0789d819e ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8090->80/tcp, [::]:8090->80/tcp tei-embedding-gaudi-server 9ee0789d819e ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8090->80/tcp, [::]:8090->80/tcp tei-embedding-gaudi-server
``` ```
### Test the Pipeline ### Test the Pipeline
@@ -148,7 +148,7 @@ The default deployment utilizes Gaudi devices primarily for the `vllm-service`,
| ---------------------------- | ----------------------------------------------------- | ------------ | | ---------------------------- | ----------------------------------------------------- | ------------ |
| redis-vector-db | redis/redis-stack:7.2.0-v9 | No | | redis-vector-db | redis/redis-stack:7.2.0-v9 | No |
| dataprep-redis-service | opea/dataprep:latest | No | | dataprep-redis-service | opea/dataprep:latest | No |
| tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No | | tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No |
| retriever | opea/retriever:latest | No | | retriever | opea/retriever:latest | No |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card | | tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card |
| vllm-service | opea/vllm-gaudi:latest | Configurable | | vllm-service | opea/vllm-gaudi:latest | Configurable |
@@ -164,7 +164,7 @@ The TGI (Text Generation Inference) deployment and the default deployment differ
| ---------------------------- | ----------------------------------------------------- | -------------- | | ---------------------------- | ----------------------------------------------------- | -------------- |
| redis-vector-db | redis/redis-stack:7.2.0-v9 | No | | redis-vector-db | redis/redis-stack:7.2.0-v9 | No |
| dataprep-redis-service | opea/dataprep:latest | No | | dataprep-redis-service | opea/dataprep:latest | No |
| tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No | | tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No |
| retriever | opea/retriever:latest | No | | retriever | opea/retriever:latest | No |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card | | tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card |
| **tgi-service** | ghcr.io/huggingface/tgi-gaudi:2.0.6 | Configurable | | **tgi-service** | ghcr.io/huggingface/tgi-gaudi:2.0.6 | Configurable |
@@ -184,7 +184,7 @@ The TGI (Text Generation Inference) deployment and the default deployment differ
| ---------------------------- | ----------------------------------------------------- | ------------ | | ---------------------------- | ----------------------------------------------------- | ------------ |
| redis-vector-db | redis/redis-stack:7.2.0-v9 | No | | redis-vector-db | redis/redis-stack:7.2.0-v9 | No |
| dataprep-redis-service | opea/dataprep:latest | No | | dataprep-redis-service | opea/dataprep:latest | No |
| tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No | | tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No |
| retriever | opea/retriever:latest | No | | retriever | opea/retriever:latest | No |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card | | tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card |
| vllm-service | opea/vllm-gaudi:latest | Configurable | | vllm-service | opea/vllm-gaudi:latest | Configurable |
@@ -203,7 +203,7 @@ The _compose_without_rerank.yaml_ Docker Compose file is distinct from the defau
| ---------------------------- | ----------------------------------------------------- | -------------- | | ---------------------------- | ----------------------------------------------------- | -------------- |
| redis-vector-db | redis/redis-stack:7.2.0-v9 | No | | redis-vector-db | redis/redis-stack:7.2.0-v9 | No |
| dataprep-redis-service | opea/dataprep:latest | No | | dataprep-redis-service | opea/dataprep:latest | No |
| tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No | | tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No |
| retriever | opea/retriever:latest | No | | retriever | opea/retriever:latest | No |
| vllm-service | opea/vllm-gaudi:latest | Configurable | | vllm-service | opea/vllm-gaudi:latest | Configurable |
| chatqna-gaudi-backend-server | opea/chatqna:latest | No | | chatqna-gaudi-backend-server | opea/chatqna:latest | No |
@@ -222,7 +222,7 @@ The _compose_guardrails.yaml_ Docker Compose file introduces enhancements over t
| dataprep-redis-service | opea/dataprep:latest | No | No | | dataprep-redis-service | opea/dataprep:latest | No | No |
| _tgi-guardrails-service_ | ghcr.io/huggingface/tgi-gaudi:2.0.6 | 1 card | Yes | | _tgi-guardrails-service_ | ghcr.io/huggingface/tgi-gaudi:2.0.6 | 1 card | Yes |
| _guardrails_ | opea/guardrails:latest | No | No | | _guardrails_ | opea/guardrails:latest | No | No |
| tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No | No | | tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No | No |
| retriever | opea/retriever:latest | No | No | | retriever | opea/retriever:latest | No | No |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card | No | | tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card | No |
| vllm-service | opea/vllm-gaudi:latest | Configurable | Yes | | vllm-service | opea/vllm-gaudi:latest | Configurable | Yes |
@@ -258,7 +258,7 @@ The table provides a comprehensive overview of the ChatQnA services utilized acr
| ---------------------------- | ----------------------------------------------------- | -------- | -------------------------------------------------------------------------------------------------- | | ---------------------------- | ----------------------------------------------------- | -------- | -------------------------------------------------------------------------------------------------- |
| redis-vector-db | redis/redis-stack:7.2.0-v9 | No | Acts as a Redis database for storing and managing data. | | redis-vector-db | redis/redis-stack:7.2.0-v9 | No | Acts as a Redis database for storing and managing data. |
| dataprep-redis-service | opea/dataprep:latest | No | Prepares data and interacts with the Redis database. | | dataprep-redis-service | opea/dataprep:latest | No | Prepares data and interacts with the Redis database. |
| tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 | No | Provides text embedding services, often using Hugging Face models. | | tei-embedding-service | ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 | No | Provides text embedding services, often using Hugging Face models. |
| retriever | opea/retriever:latest | No | Retrieves data from the Redis database and interacts with embedding services. | | retriever | opea/retriever:latest | No | Retrieves data from the Redis database and interacts with embedding services. |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | Yes | Reranks text embeddings, typically using Gaudi hardware for enhanced performance. | | tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | Yes | Reranks text embeddings, typically using Gaudi hardware for enhanced performance. |
| vllm-service | opea/vllm-gaudi:latest | No | Handles large language model (LLM) tasks, utilizing Gaudi hardware. | | vllm-service | opea/vllm-gaudi:latest | No | Handles large language model (LLM) tasks, utilizing Gaudi hardware. |
@@ -284,7 +284,7 @@ ChatQnA now supports running the latest DeepSeek models, including [deepseek-ai/
### tei-embedding-service & tei-reranking-service ### tei-embedding-service & tei-reranking-service
The `ghcr.io/huggingface/text-embeddings-inference:cpu-1.5` image supporting `tei-embedding-service` and `tei-reranking-service` depends on the `EMBEDDING_MODEL_ID` or `RERANK_MODEL_ID` environment variables respectively to specify the embedding model and reranking model used for converting text into vector representations and rankings. This choice impacts the quality and relevance of the embeddings rerankings for various applications. Unlike the `vllm-service`, the `tei-embedding-service` and `tei-reranking-service` each typically acquires only one Gaudi device and does not use the `NUM_CARDS` parameter; embedding and reranking tasks generally do not require extensive parallel processing and one Gaudi per service is appropriate. The list of [supported embedding and reranking models](https://github.com/huggingface/tei-gaudi?tab=readme-ov-file#supported-models) can be found at the the [huggingface/tei-gaudi](https://github.com/huggingface/tei-gaudi?tab=readme-ov-file#supported-models) website. The `ghcr.io/huggingface/text-embeddings-inference:cpu-1.6` image supporting `tei-embedding-service` and `tei-reranking-service` depends on the `EMBEDDING_MODEL_ID` or `RERANK_MODEL_ID` environment variables respectively to specify the embedding model and reranking model used for converting text into vector representations and rankings. This choice impacts the quality and relevance of the embeddings rerankings for various applications. Unlike the `vllm-service`, the `tei-embedding-service` and `tei-reranking-service` each typically acquires only one Gaudi device and does not use the `NUM_CARDS` parameter; embedding and reranking tasks generally do not require extensive parallel processing and one Gaudi per service is appropriate. The list of [supported embedding and reranking models](https://github.com/huggingface/tei-gaudi?tab=readme-ov-file#supported-models) can be found at the the [huggingface/tei-gaudi](https://github.com/huggingface/tei-gaudi?tab=readme-ov-file#supported-models) website.
### tgi-gaurdrails-service ### tgi-gaurdrails-service

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

@@ -33,7 +33,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-gaudi-server container_name: tei-embedding-gaudi-server
ports: ports:
- "8090:80" - "8090:80"

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

@@ -27,7 +27,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG} LOGFLAG: ${LOGFLAG}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-gaudi-server container_name: tei-embedding-gaudi-server
ports: ports:
- "8090:80" - "8090:80"

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

@@ -27,7 +27,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG} LOGFLAG: ${LOGFLAG}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-gaudi-server container_name: tei-embedding-gaudi-server
ports: ports:
- "8090:80" - "8090:80"

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

@@ -65,7 +65,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped restart: unless-stopped
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-gaudi-server container_name: tei-embedding-gaudi-server
ports: ports:
- "8090:80" - "8090:80"

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

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-gaudi-server container_name: tei-embedding-gaudi-server
ports: ports:
- "8090:80" - "8090:80"

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

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-gaudi-server container_name: tei-embedding-gaudi-server
ports: ports:
- "8090:80" - "8090:80"

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

@@ -51,7 +51,7 @@ f810f3b4d329 opea/embedding:latest "python embed
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 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 05c40b636239 ghcr.io/huggingface/tgi-gaudi:2.0.6 "text-generation-lau…" 2 minutes ago Exited (1) About a minute ago tgi-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 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 88399dbc9e43 ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 "text-embeddings-rou…" 2 minutes ago Up 2 minutes 0.0.0.0:8808->80/tcp, :::8808->80/tcp tei-reranking-gaudi-server
``` ```
In this case, `ghcr.io/huggingface/tgi-gaudi:2.0.6` Existed. In this case, `ghcr.io/huggingface/tgi-gaudi:2.0.6` Existed.

2
ChatQnA/docker_compose/nvidia/gpu/compose.yaml
View File

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80 TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-server container_name: tei-embedding-server
ports: ports:
- "8090:80" - "8090:80"

4
ChatQnA/kubernetes/gmc/README.md
View File

@@ -15,9 +15,9 @@ The ChatQnA application is defined as a Custom Resource (CR) file that the above
The ChatQnA uses the below prebuilt images if you choose a Xeon deployment The ChatQnA uses the below prebuilt images if you choose a Xeon deployment
- redis-vector-db: redis/redis-stack:7.2.0-v9 - redis-vector-db: redis/redis-stack:7.2.0-v9
- tei_embedding_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 - tei_embedding_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
- retriever: opea/retriever:latest - retriever: opea/retriever:latest
- tei_xeon_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 - tei_xeon_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
- tgi-service: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu - tgi-service: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
- chaqna-xeon-backend-server: opea/chatqna:latest - chaqna-xeon-backend-server: opea/chatqna:latest

2
ChatQnA/tests/test_compose_faqgen_on_gaudi.sh
View File

@@ -37,7 +37,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm-gaudi nginx" service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm-gaudi nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0 docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_faqgen_on_xeon.sh
View File

@@ -38,7 +38,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm nginx" service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_faqgen_tgi_on_gaudi.sh
View File

@@ -35,7 +35,7 @@ function build_docker_images() {
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 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/text-embeddings-inference:cpu-1.6
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0 docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_faqgen_tgi_on_xeon.sh
View File

@@ -39,7 +39,7 @@ function build_docker_images() {
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_guardrails_on_gaudi.sh
View File

@@ -38,7 +38,7 @@ function build_docker_images() {
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 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/text-embeddings-inference:cpu-1.6
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0 docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s docker images && sleep 1s

2
ChatQnA/tests/test_compose_milvus_on_xeon.sh
View File

@@ -42,7 +42,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui dataprep retriever vllm nginx" service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_on_gaudi.sh
View File

@@ -37,7 +37,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi nginx" service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0 docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_on_xeon.sh
View File

@@ -41,7 +41,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui dataprep retriever vllm nginx" service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_pinecone_on_xeon.sh
View File

@@ -41,7 +41,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui dataprep retriever vllm nginx" service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_tgi_on_gaudi.sh
View File

@@ -36,7 +36,7 @@ function build_docker_images() {
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6 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/text-embeddings-inference:cpu-1.6
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0 docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s docker images && sleep 1s

2
ChatQnA/tests/test_compose_tgi_on_xeon.sh
View File

@@ -36,7 +36,7 @@ function build_docker_images() {
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

2
ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh
View File

@@ -37,7 +37,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi nginx" service_list="chatqna chatqna-ui dataprep retriever vllm-gaudi nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0 docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
docker images && sleep 1s docker images && sleep 1s

2
ChatQnA/tests/test_compose_without_rerank_on_xeon.sh
View File

@@ -42,7 +42,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui dataprep retriever vllm nginx" service_list="chatqna chatqna-ui dataprep retriever vllm nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

4
DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -32,7 +32,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG} LOGFLAG: ${LOGFLAG}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate" 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-server container_name: tei-embedding-server
ports: ports:
@@ -90,7 +90,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${RERANK_MODEL_ID} --auto-truncate" 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 container_name: tei-reranking-server
ports: ports:

2
DocIndexRetriever/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml
View File

@@ -30,7 +30,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG} LOGFLAG: ${LOGFLAG}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate" 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-server container_name: tei-embedding-server
ports: ports:

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

@@ -89,7 +89,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${RERANK_MODEL_ID} --auto-truncate" 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-gaudi-server container_name: tei-reranking-gaudi-server
ports: ports:

2
DocIndexRetriever/tests/test_compose_on_xeon.sh
View File

@@ -24,7 +24,7 @@ function build_docker_images() {
service_list="dataprep embedding retriever reranking doc-index-retriever" service_list="dataprep embedding retriever reranking doc-index-retriever"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker pull redis/redis-stack:7.2.0-v9 docker pull redis/redis-stack:7.2.0-v9
docker images && sleep 1s docker images && sleep 1s

2
DocIndexRetriever/tests/test_compose_without_rerank_on_xeon.sh
View File

@@ -24,7 +24,7 @@ function build_docker_images() {
service_list="dataprep embedding retriever doc-index-retriever" service_list="dataprep embedding retriever doc-index-retriever"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker pull redis/redis-stack:7.2.0-v9 docker pull redis/redis-stack:7.2.0-v9
docker images && sleep 1s docker images && sleep 1s

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

@@ -33,7 +33,7 @@ services:
retries: 20 retries: 20
start_period: 3s start_period: 3s
tei-embedding-serving: tei-embedding-serving:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
container_name: tei-embedding-serving container_name: tei-embedding-serving
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate" entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
ports: ports:

2
GraphRAG/tests/test_compose_on_gaudi.sh
View File

@@ -35,7 +35,7 @@ function build_docker_images() {
docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/tgi-gaudi:2.3.1 docker pull ghcr.io/huggingface/tgi-gaudi:2.3.1
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
docker images && sleep 1s docker images && sleep 1s
} }

4
ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -33,7 +33,7 @@ services:
DATAPREP_TYPE: ${DATAPREP_TYPE} DATAPREP_TYPE: ${DATAPREP_TYPE}
LOGFLAG: ${LOGFLAG} LOGFLAG: ${LOGFLAG}
tei-embedding-service: tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate" 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-server container_name: tei-embedding-server
ports: ports:
@@ -89,7 +89,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS" RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${RERANK_MODEL_ID} --auto-truncate" 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 container_name: tei-reranking-server
ports: ports:

2
ProductivitySuite/tests/test_compose_on_xeon.sh
View File

@@ -22,7 +22,7 @@ function build_docker_images() {
echo "Build all the images with --no-cache, check docker_image_build.log for details..." echo "Build all the images with --no-cache, check docker_image_build.log for details..."
docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker images && sleep 1s docker images && sleep 1s
} }

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

@@ -61,7 +61,7 @@ services:
GOOGLE_CSE_ID: ${GOOGLE_CSE_ID} GOOGLE_CSE_ID: ${GOOGLE_CSE_ID}
restart: unless-stopped restart: unless-stopped
tei-reranking-service: tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${RERANK_MODEL_ID} --auto-truncate" 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 container_name: tei-reranking-server
ports: ports:

2
SearchQnA/tests/test_compose_on_gaudi.sh
View File

@@ -35,7 +35,7 @@ function build_docker_images() {
service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen" service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log 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/text-embeddings-inference:cpu-1.6
docker pull ghcr.io/huggingface/tei-gaudi:1.5.0 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/tgi-gaudi:2.0.6
docker images && sleep 1s docker images && sleep 1s