jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 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

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

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "6006:80"
@@ -59,7 +59,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped
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
ports:
- "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
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "6006:80"
@@ -66,7 +66,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped
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
ports:
- "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
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "6006:80"
@@ -59,7 +59,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped
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
ports:
- "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
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "6006:80"
@@ -59,7 +59,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped
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
ports:
- "8808:80"

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

@@ -108,7 +108,7 @@ services:
restart: unless-stopped
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
ports:
- "6006:80"
@@ -122,7 +122,7 @@ services:
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
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
ports:
- "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}
DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_PINECONE"
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
ports:
- "6006:80"
@@ -54,7 +54,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_PINECONE"
restart: unless-stopped
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
ports:
- "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
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "6006:80"
@@ -59,7 +59,7 @@ services:
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped
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
ports:
- "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
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "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
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
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
@@ -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 |
| 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 |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card |
| 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 |
| 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 |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card |
| **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 |
| 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 |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card |
| 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 |
| 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 |
| vllm-service | opea/vllm-gaudi:latest | Configurable |
| 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 |
| _tgi-guardrails-service_ | ghcr.io/huggingface/tgi-gaudi:2.0.6 | 1 card | Yes |
| _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 |
| tei-reranking-service | ghcr.io/huggingface/tei-gaudi:1.5.0 | 1 card | No |
| 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. |
| 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. |
| 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. |
@@ -284,7 +284,7 @@ ChatQnA now supports running the latest DeepSeek models, including [deepseek-ai/
### 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

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

@@ -33,7 +33,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "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}
LOGFLAG: ${LOGFLAG}
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
ports:
- "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}
LOGFLAG: ${LOGFLAG}
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
ports:
- "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}
restart: unless-stopped
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
ports:
- "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
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "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
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "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
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
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.

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

@@ -26,7 +26,7 @@ services:
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
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
ports:
- "8090:80"