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

Enhance CI/CD infrastructure (#593)

Browse Source 
Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: Sun, Xuehao <xuehao.sun@intel.com>
This commit is contained in:
chen, suyue
2024-08-15 22:39:21 +08:00
committed by GitHub
parent e71aba0080
commit c26d0f62b8
61 changed files with 989 additions and 956 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
ChatQnA/docker/aipc/compose.yaml
View File

@@ -1,8 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
@@ -11,7 +9,7 @@ services:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: opea/dataprep-redis:latest
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
@@ -39,7 +37,7 @@ services:
https_proxy: ${https_proxy}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -53,7 +51,7 @@ services:
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: opea/retriever-redis:latest
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
@@ -85,7 +83,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-aipc-server
depends_on:
- tei-reranking-service
@@ -102,7 +100,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
llm:
image: opea/llm-ollama
image: ${REGISTRY:-opea}/llm-ollama
container_name: llm-ollama
ports:
- "9000:9000"
@@ -118,7 +116,7 @@ services:
OLLAMA_ENDPOINT: ${OLLAMA_ENDPOINT}
OLLAMA_MODEL: ${OLLAMA_MODEL}
chaqna-aipc-backend-server:
image: opea/chatqna:latest
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-aipc-backend-server
depends_on:
- redis-vector-db
@@ -142,7 +140,7 @@ services:
ipc: host
restart: always
chaqna-aipc-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-aipc-ui-server
depends_on:
- chaqna-aipc-backend-server

108
ChatQnA/docker/docker_build_compose.yaml Normal file
View File

@@ -0,0 +1,108 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
services:
chatqna:
build:
args:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
no_proxy: ${no_proxy}
dockerfile: ./Dockerfile
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
chatqna-ui:
build:
context: ui
dockerfile: ./docker/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
chatqna-conversation-ui:
build:
context: ui
dockerfile: ./docker/Dockerfile.react
extends: chatqna
image: ${REGISTRY:-opea}/chatqna-conversation-ui:${TAG:-latest}
embedding-tei:
build:
context: GenAIComps
dockerfile: comps/embeddings/langchain/docker/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
retriever-redis:
build:
context: GenAIComps
dockerfile: comps/retrievers/langchain/redis/docker/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
retriever-qdrant:
build:
context: GenAIComps
dockerfile: comps/retrievers/haystack/qdrant/docker/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/retriever-qdrant:${TAG:-latest}
reranking-tei:
build:
context: GenAIComps
dockerfile: comps/reranks/tei/docker/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
llm-tgi:
build:
context: GenAIComps
dockerfile: comps/llms/text-generation/tgi/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
llm-ollama:
build:
context: GenAIComps
dockerfile: comps/llms/text-generation/ollama/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/llm-ollama:${TAG:-latest}
llm-vllm:
build:
context: GenAIComps
dockerfile: comps/llms/text-generation/vllm/docker/Dockerfile.microservice
extends: chatqna
image: ${REGISTRY:-opea}/llm-vllm:${TAG:-latest}
llm-vllm-hpu:
build:
context: GenAIComps
dockerfile: comps/llms/text-generation/vllm/docker/Dockerfile.hpu
extends: chatqna
image: ${REGISTRY:-opea}/llm-vllm-hpu:${TAG:-latest}
llm-vllm-ray:
build:
context: GenAIComps
dockerfile: comps/llms/text-generation/vllm-ray/docker/Dockerfile.microservice
extends: chatqna
image: ${REGISTRY:-opea}/llm-vllm-ray:${TAG:-latest}
llm-vllm-ray-hpu:
build:
context: GenAIComps
dockerfile: comps/llms/text-generation/vllm-ray/docker/Dockerfile.vllmray
extends: chatqna
image: ${REGISTRY:-opea}/llm-vllm-ray-hpu:${TAG:-latest}
dataprep-redis:
build:
context: GenAIComps
dockerfile: comps/dataprep/redis/langchain/docker/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
dataprep-qdrant:
build:
context: GenAIComps
dockerfile: comps/dataprep/qdrant/docker/Dockerfile
extends: chatqna
image: ${REGISTRY:-opea}/dataprep-qdrant:${TAG:-latest}
tei-gaudi:
build:
context: tei-gaudi
dockerfile: Dockerfile-hpu
extends: chatqna
image: ${REGISTRY:-opea}/tei-gaudi:${TAG:-latest}
vllm:
build:
context: vllm
dockerfile: Dockerfile.cpu
extends: chatqna
image: ${REGISTRY:-opea}/vllm:${TAG:-latest}

19
ChatQnA/docker/gaudi/compose.yaml
View File

@@ -1,9 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
@@ -12,7 +9,7 @@ services:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: opea/dataprep-redis:latest
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
@@ -28,7 +25,7 @@ services:
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: opea/tei-gaudi:latest
image: ${REGISTRY:-opea}/tei-gaudi:${TAG:-latest}
container_name: tei-embedding-gaudi-server
ports:
- "8090:80"
@@ -49,7 +46,7 @@ services:
ENABLE_EXPERIMENTAL_FLAGS: true
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -63,7 +60,7 @@ services:
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: opea/retriever-redis:latest
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
@@ -94,7 +91,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-gaudi-server
depends_on:
- tei-reranking-service
@@ -132,7 +129,7 @@ services:
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
llm:
image: opea/llm-tgi:latest
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-gaudi-server
depends_on:
- tgi-service
@@ -149,7 +146,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
chaqna-gaudi-backend-server:
image: opea/chatqna:latest
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
depends_on:
- redis-vector-db
@@ -174,7 +171,7 @@ services:
ipc: host
restart: always
chaqna-gaudi-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server

21
ChatQnA/docker/gaudi/compose_guardrails.yaml
View File

@@ -1,9 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
@@ -12,7 +9,7 @@ services:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: opea/dataprep-redis:latest
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
@@ -49,7 +46,7 @@ services:
ipc: host
command: --model-id ${GURADRAILS_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
guardrails:
image: opea/guardrails-tgi:latest
image: ${REGISTRY:-opea}/guardrails-tgi:${TAG:-latest}
container_name: guardrails-tgi-gaudi-server
ports:
- "9090:9090"
@@ -63,7 +60,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-embedding-service:
image: opea/tei-gaudi:latest
image: ${REGISTRY:-opea}/tei-gaudi:${TAG:-latest}
container_name: tei-embedding-gaudi-server
ports:
- "8090:80"
@@ -82,7 +79,7 @@ services:
MAX_WARMUP_SEQUENCE_LENGTH: 512
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -96,7 +93,7 @@ services:
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: opea/retriever-redis:latest
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
@@ -127,7 +124,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-gaudi-server
depends_on:
- tei-reranking-service
@@ -165,7 +162,7 @@ services:
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
llm:
image: opea/llm-tgi:latest
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-gaudi-server
depends_on:
- tgi-service
@@ -182,7 +179,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
chaqna-gaudi-backend-server:
image: opea/chatqna-guardrails:latest
image: ${REGISTRY:-opea}/chatqna-guardrails:${TAG:-latest}
container_name: chatqna-gaudi-guardrails-server
depends_on:
- redis-vector-db
@@ -210,7 +207,7 @@ services:
ipc: host
restart: always
chaqna-gaudi-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server

21
ChatQnA/docker/gaudi/compose_vllm.yaml
View File

@@ -1,9 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
@@ -12,7 +9,7 @@ services:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: opea/dataprep-redis:latest
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
@@ -28,7 +25,7 @@ services:
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: opea/tei-gaudi:latest
image: ${REGISTRY:-opea}/tei-gaudi:${TAG:-latest}
container_name: tei-embedding-gaudi-server
ports:
- "8090:80"
@@ -47,7 +44,7 @@ services:
MAX_WARMUP_SEQUENCE_LENGTH: 512
command: --model-id ${EMBEDDING_MODEL_ID}
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -61,7 +58,7 @@ services:
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: opea/retriever-redis:latest
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
@@ -92,7 +89,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-gaudi-server
depends_on:
- tei-reranking-service
@@ -109,7 +106,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
vllm-service:
image: opea/llm-vllm-hpu:latest
image: ${REGISTRY:-opea}/llm-vllm-hpu:${TAG:-latest}
container_name: vllm-gaudi-server
ports:
- "8007:80"
@@ -129,7 +126,7 @@ services:
ipc: host
command: /bin/bash -c "export VLLM_CPU_KVCACHE_SPACE=40 && python3 -m vllm.entrypoints.openai.api_server --enforce-eager --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048"
llm:
image: opea/llm-vllm:latest
image: ${REGISTRY:-opea}/llm-vllm:${TAG:-latest}
container_name: llm-vllm-gaudi-server
depends_on:
- vllm-service
@@ -145,7 +142,7 @@ services:
LLM_MODEL: ${LLM_MODEL_ID}
restart: unless-stopped
chaqna-gaudi-backend-server:
image: opea/chatqna:latest
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
depends_on:
- redis-vector-db
@@ -171,7 +168,7 @@ services:
ipc: host
restart: always
chaqna-gaudi-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server

21
ChatQnA/docker/gaudi/compose_vllm_ray.yaml
View File

@@ -1,9 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
@@ -12,7 +9,7 @@ services:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: opea/dataprep-redis:latest
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
@@ -28,7 +25,7 @@ services:
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: opea/tei-gaudi:latest
image: ${REGISTRY:-opea}/tei-gaudi:${TAG:-latest}
container_name: tei-embedding-gaudi-server
ports:
- "8090:80"
@@ -47,7 +44,7 @@ services:
MAX_WARMUP_SEQUENCE_LENGTH: 512
command: --model-id ${EMBEDDING_MODEL_ID}
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -61,7 +58,7 @@ services:
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: opea/retriever-redis:latest
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
@@ -92,7 +89,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-gaudi-server
depends_on:
- tei-reranking-service
@@ -109,7 +106,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
vllm-ray-service:
image: opea/llm-vllm-ray-hpu:latest
image: ${REGISTRY:-opea}/llm-vllm-ray-hpu:${TAG:-latest}
container_name: vllm-ray-gaudi-server
ports:
- "8006:8000"
@@ -129,7 +126,7 @@ services:
ipc: host
command: /bin/bash -c "ray start --head && python vllm_ray_openai.py --port_number 8000 --model_id_or_path $LLM_MODEL_ID --tensor_parallel_size 2 --enforce_eager True"
llm:
image: opea/llm-vllm-ray:latest
image: ${REGISTRY:-opea}/llm-vllm-ray:${TAG:-latest}
container_name: llm-vllm-ray-gaudi-server
depends_on:
- vllm-ray-service
@@ -145,7 +142,7 @@ services:
LLM_MODEL: ${LLM_MODEL_ID}
restart: unless-stopped
chaqna-gaudi-backend-server:
image: opea/chatqna:latest
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
depends_on:
- redis-vector-db
@@ -171,7 +168,7 @@ services:
ipc: host
restart: always
chaqna-gaudi-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server

17
ChatQnA/docker/gpu/compose.yaml
View File

@@ -1,9 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
@@ -12,7 +9,7 @@ services:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: opea/dataprep-redis:latest
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
@@ -50,7 +47,7 @@ services:
count: 1
capabilities: [gpu]
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -64,7 +61,7 @@ services:
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: opea/retriever-redis:latest
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
@@ -102,7 +99,7 @@ services:
count: 1
capabilities: [gpu]
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-server
depends_on:
- tei-reranking-service
@@ -142,7 +139,7 @@ services:
count: 1
capabilities: [gpu]
llm:
image: opea/llm-tgi:latest
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-server
depends_on:
- tgi-service
@@ -159,7 +156,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
chaqna-backend-server:
image: opea/chatqna:latest
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-backend-server
depends_on:
- redis-vector-db
@@ -184,7 +181,7 @@ services:
ipc: host
restart: always
chaqna-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-ui-server
depends_on:
- chaqna-backend-server

17
ChatQnA/docker/xeon/compose.yaml
View File

@@ -1,9 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
@@ -12,7 +9,7 @@ services:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: opea/dataprep-redis:latest
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
@@ -42,7 +39,7 @@ services:
https_proxy: ${https_proxy}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -56,7 +53,7 @@ services:
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: opea/retriever-redis:latest
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
@@ -88,7 +85,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-xeon-server
depends_on:
- tei-reranking-service
@@ -121,7 +118,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${LLM_MODEL_ID}
llm:
image: opea/llm-tgi:latest
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-server
depends_on:
- tgi-service
@@ -138,7 +135,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
chaqna-xeon-backend-server:
image: opea/chatqna:latest
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
- redis-vector-db
@@ -164,7 +161,7 @@ services:
ipc: host
restart: always
chaqna-xeon-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chaqna-xeon-backend-server

17
ChatQnA/docker/xeon/compose_qdrant.yaml
View File

@@ -1,9 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
qdrant-vector-db:
image: qdrant/qdrant
@@ -12,7 +9,7 @@ services:
- "6333:6333"
- "6334:6334"
dataprep-qdrant-service:
image: opea/dataprep-qdrant:latest
image: ${REGISTRY:-opea}/dataprep-qdrant:${TAG:-latest}
container_name: dataprep-qdrant-server
depends_on:
- qdrant-vector-db
@@ -42,7 +39,7 @@ services:
https_proxy: ${https_proxy}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -56,7 +53,7 @@ services:
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
restart: unless-stopped
retriever:
image: opea/retriever-qdrant:latest
image: ${REGISTRY:-opea}/retriever-qdrant:${TAG:-latest}
container_name: retriever-qdrant-server
depends_on:
- qdrant-vector-db
@@ -88,7 +85,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-xeon-server
depends_on:
- tei-reranking-service
@@ -121,7 +118,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${LLM_MODEL_ID}
llm:
image: opea/llm-tgi:latest
image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
container_name: llm-tgi-server
depends_on:
- tgi-service
@@ -138,7 +135,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped
chaqna-xeon-backend-server:
image: opea/chatqna:latest
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
- qdrant-vector-db
@@ -167,7 +164,7 @@ services:
ipc: host
restart: always
chaqna-xeon-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chaqna-xeon-backend-server

19
ChatQnA/docker/xeon/compose_vllm.yaml
View File

@@ -1,9 +1,6 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
version: "3.8"
services:
redis-vector-db:
image: redis/redis-stack:7.2.0-v9
@@ -12,7 +9,7 @@ services:
- "6379:6379"
- "8001:8001"
dataprep-redis-service:
image: opea/dataprep-redis:latest
image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
@@ -41,7 +38,7 @@ services:
https_proxy: ${https_proxy}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
embedding:
image: opea/embedding-tei:latest
image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
container_name: embedding-tei-server
depends_on:
- tei-embedding-service
@@ -58,7 +55,7 @@ services:
LANGCHAIN_PROJECT: "opea-embedding-service"
restart: unless-stopped
retriever:
image: opea/retriever-redis:latest
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
depends_on:
- redis-vector-db
@@ -93,7 +90,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
reranking:
image: opea/reranking-tei:latest
image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
container_name: reranking-tei-xeon-server
depends_on:
- tei-reranking-service
@@ -113,7 +110,7 @@ services:
LANGCHAIN_PROJECT: "opea-reranking-service"
restart: unless-stopped
vllm_service:
image: opea/vllm:latest
image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
container_name: vllm-service
ports:
- "9009:80"
@@ -128,7 +125,7 @@ services:
LLM_MODEL_ID: ${LLM_MODEL_ID}
command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
llm:
image: opea/llm-vllm:latest
image: ${REGISTRY:-opea}/llm-vllm:${TAG:-latest}
container_name: llm-vllm-server
depends_on:
- vllm_service
@@ -149,7 +146,7 @@ services:
LANGCHAIN_PROJECT: "opea-llm-service"
restart: unless-stopped
chaqna-xeon-backend-server:
image: opea/chatqna:latest
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
- redis-vector-db
@@ -174,7 +171,7 @@ services:
ipc: host
restart: always
chaqna-xeon-ui-server:
image: opea/chatqna-ui:latest
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chaqna-xeon-backend-server

64
ChatQnA/tests/test_chatqna_on_gaudi.sh
View File

@@ -3,47 +3,33 @@
# SPDX-License-Identifier: Apache-2.0
set -e
echo "IMAGE_REPO=${IMAGE_REPO}"
IMAGE_REPO=${IMAGE_REPO:-"opea"}
IMAGE_TAG=${IMAGE_TAG:-"latest"}
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
export REGISTRY=${IMAGE_REPO}
export TAG=${IMAGE_TAG}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
cd $WORKPATH
cd $WORKPATH/docker
git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps
git clone https://github.com/huggingface/tei-gaudi
docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile .
docker build -t opea/retriever-redis:latest -f comps/retrievers/langchain/redis/docker/Dockerfile .
docker build -t opea/reranking-tei:latest -f comps/reranks/tei/docker/Dockerfile .
docker build -t opea/llm-tgi:latest -f comps/llms/text-generation/tgi/Dockerfile .
docker build -t opea/dataprep-redis:latest -f comps/dataprep/redis/langchain/docker/Dockerfile .
# cd ..
# git clone https://github.com/huggingface/tei-gaudi
# cd tei-gaudi/
# docker build --no-cache -f Dockerfile-hpu -t opea/tei-gaudi:latest .
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="chatqna chatqna-ui dataprep-redis embedding-tei retriever-redis reranking-tei llm-tgi tei-gaudi"
docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
cd $WORKPATH/docker
docker build --no-cache -t opea/chatqna:latest -f Dockerfile .
cd $WORKPATH/docker/ui
docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile .
docker images
}
function start_services() {
# build tei-gaudi for each test instead of pull from local registry
cd $WORKPATH
git clone https://github.com/huggingface/tei-gaudi
cd tei-gaudi/
docker build --no-cache -q -f Dockerfile-hpu -t opea/tei-gaudi:latest .
cd $WORKPATH/docker/gaudi
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
@@ -67,24 +53,9 @@ function start_services() {
sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
if [[ "$IMAGE_REPO" != "" ]]; then
# Replace the container name with a test-specific name
echo "using image repository $IMAGE_REPO and image tag $IMAGE_TAG"
if [ "${mode}" == "perf" ]; then
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose.yaml
else
sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${IMAGE_TAG}#g" compose.yaml
sed -i "s#image: opea/chatqna-ui:latest#image: opea/chatqna-ui:${IMAGE_TAG}#g" compose.yaml
sed -i "s#image: opea/chatqna-conversation-ui:latest#image: opea/chatqna-conversation-ui:${IMAGE_TAG}#g" compose.yaml
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose.yaml
sed -i "s#image: ${IMAGE_REPO}opea/tei-gaudi:latest#image: opea/tei-gaudi:latest#g" compose.yaml
fi
echo "cat compose.yaml"
cat compose.yaml
fi
# Start Docker Containers
docker compose up -d
n=0
until [[ "$n" -ge 400 ]]; do
docker logs tgi-gaudi-server > ${LOG_PATH}/tgi_service_start.log
@@ -246,13 +217,16 @@ function validate_frontend() {
cd $WORKPATH/docker/ui/svelte
local conda_env_name="OPEA_e2e"
export PATH=${HOME}/miniforge3/bin/:$PATH
# conda remove -n ${conda_env_name} --all -y
# conda create -n ${conda_env_name} python=3.12 -y
if conda info --envs | grep -q "$conda_env_name"; then
echo "$conda_env_name exist!"
else
conda create -n ${conda_env_name} python=3.12 -y
fi
source activate ${conda_env_name}
sed -i "s/localhost/$ip_address/g" playwright.config.ts
# conda install -c conda-forge nodejs -y
conda install -c conda-forge nodejs -y
npm install && npm ci && npx playwright install --with-deps
node -v && npm -v && pip list
@@ -275,7 +249,7 @@ function stop_docker() {
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "" ]]; then build_docker_images; fi
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_time=$(date +%s)
start_services
end_time=$(date +%s)

55
ChatQnA/tests/test_chatqna_on_xeon.sh
View File

@@ -2,29 +2,28 @@
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
set -xe
echo "IMAGE_REPO=${IMAGE_REPO}"
set -e
IMAGE_REPO=${IMAGE_REPO:-"opea"}
IMAGE_TAG=${IMAGE_TAG:-"latest"}
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
export REGISTRY=${IMAGE_REPO}
export TAG=${IMAGE_TAG}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
cd $WORKPATH
git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps
docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile .
docker build -t opea/retriever-redis:latest -f comps/retrievers/langchain/redis/docker/Dockerfile .
docker build -t opea/reranking-tei:latest -f comps/reranks/tei/docker/Dockerfile .
docker build -t opea/llm-tgi:latest -f comps/llms/text-generation/tgi/Dockerfile .
docker build -t opea/dataprep-redis:latest -f comps/dataprep/redis/langchain/docker/Dockerfile .
cd $WORKPATH/docker
docker build --no-cache -t opea/chatqna:latest -f Dockerfile .
git clone https://github.com/opea-project/GenAIComps.git
cd $WORKPATH/docker/ui
docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile .
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="chatqna chatqna-ui chatqna-conversation-ui dataprep-redis embedding-tei retriever-redis reranking-tei llm-tgi"
docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker images
}
@@ -54,21 +53,6 @@ function start_services() {
sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
if [[ "$IMAGE_REPO" != "" ]]; then
# Replace the container name with a test-specific name
echo "using image repository $IMAGE_REPO and image tag $IMAGE_TAG"
if [ "${mode}" == "perf" ]; then
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose.yaml
else
sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${IMAGE_TAG}#g" compose.yaml
sed -i "s#image: opea/chatqna-ui:latest#image: opea/chatqna-ui:${IMAGE_TAG}#g" compose.yaml
sed -i "s#image: opea/chatqna-conversation-ui:latest#image: opea/chatqna-conversation-ui:${IMAGE_TAG}#g" compose.yaml
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose.yaml
fi
echo "cat compose.yaml"
cat compose.yaml
fi
# Start Docker Containers
docker compose up -d
n=0
@@ -233,14 +217,17 @@ function validate_frontend() {
cd $WORKPATH/docker/ui/svelte
local conda_env_name="OPEA_e2e"
export PATH=${HOME}/miniforge3/bin/:$PATH
# conda remove -n ${conda_env_name} --all -y
# conda create -n ${conda_env_name} python=3.12 -y
if conda info --envs | grep -q "$conda_env_name"; then
echo "$conda_env_name exist!"
else
conda create -n ${conda_env_name} python=3.12 -y
fi
source activate ${conda_env_name}
echo "[ TEST INFO ]: --------- conda env activated ---------"
sed -i "s/localhost/$ip_address/g" playwright.config.ts
# conda install -c conda-forge nodejs -y
conda install -c conda-forge nodejs -y
npm install && npm ci && npx playwright install --with-deps
node -v && npm -v && pip list
@@ -263,7 +250,7 @@ function stop_docker() {
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "" ]]; then build_docker_images; fi
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_time=$(date +%s)
start_services
end_time=$(date +%s)

36
ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh
View File

@@ -3,28 +3,24 @@
# SPDX-License-Identifier: Apache-2.0
set -e
echo "IMAGE_REPO=${IMAGE_REPO}"
IMAGE_REPO=${IMAGE_REPO:-"opea"}
IMAGE_TAG=${IMAGE_TAG:-"latest"}
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
export REGISTRY=${IMAGE_REPO}
export TAG=${IMAGE_TAG}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
cd $WORKPATH
git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps
docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile .
docker build -t opea/retriever-qdrant:latest -f comps/retrievers/haystack/qdrant/docker/Dockerfile .
docker build -t opea/reranking-tei:latest -f comps/reranks/tei/docker/Dockerfile .
docker build -t opea/llm-tgi:latest -f comps/llms/text-generation/tgi/Dockerfile .
docker build -t opea/dataprep-qdrant:latest -f comps/dataprep/qdrant/docker/Dockerfile .
cd $WORKPATH/docker
docker build --no-cache -t opea/chatqna:latest -f Dockerfile .
git clone https://github.com/opea-project/GenAIComps.git
cd $WORKPATH/docker/ui
docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile .
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="chatqna chatqna-ui dataprep-qdrant embedding-tei retriever-qdrant reranking-tei llm-tgi"
docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker images
}
@@ -56,16 +52,6 @@ function start_services() {
sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
if [[ "$IMAGE_REPO" != "" ]]; then
# Replace the container name with a test-specific name
echo "using image repository $IMAGE_REPO and image tag $IMAGE_TAG"
sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${IMAGE_TAG}#g" compose_qdrant.yaml
sed -i "s#image: opea/chatqna-ui:latest#image: opea/chatqna-ui:${IMAGE_TAG}#g" compose_qdrant.yaml
sed -i "s#image: opea/chatqna-conversation-ui:latest#image: opea/chatqna-conversation-ui:${IMAGE_TAG}#g" compose_qdrant.yaml
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose_qdrant.yaml
cat compose_qdrant.yaml
fi
# Start Docker Containers
docker compose -f compose_qdrant.yaml up -d
n=0
@@ -235,7 +221,7 @@ function stop_docker() {
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "" ]]; then build_docker_images; fi
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_time=$(date +%s)
start_services
end_time=$(date +%s)

61
ChatQnA/tests/test_chatqna_vllm_on_gaudi.sh
View File

@@ -3,47 +3,31 @@
# SPDX-License-Identifier: Apache-2.0
set -e
echo "IMAGE_REPO=${IMAGE_REPO}"
IMAGE_REPO=${IMAGE_REPO:-"opea"}
IMAGE_TAG=${IMAGE_TAG:-"latest"}
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
export REGISTRY=${IMAGE_REPO}
export TAG=${IMAGE_TAG}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
cd $WORKPATH
cd $WORKPATH/docker
git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps
git clone https://github.com/huggingface/tei-gaudi
docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile .
docker build -t opea/retriever-redis:latest -f comps/retrievers/langchain/redis/docker/Dockerfile .
docker build -t opea/reranking-tei:latest -f comps/reranks/tei/docker/Dockerfile .
docker build -t opea/llm-vllm-hpu:latest -f comps/llms/text-generation/vllm/docker/Dockerfile.hpu .
docker build -t opea/llm-vllm:latest -f comps/llms/text-generation/vllm/docker/Dockerfile.microservice .
docker build -t opea/dataprep-redis:latest -f comps/dataprep/redis/langchain/docker/Dockerfile .
# cd ..
# git clone https://github.com/huggingface/tei-gaudi
# cd tei-gaudi/
# docker build --no-cache -f Dockerfile-hpu -t opea/tei-gaudi:latest .
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="chatqna chatqna-ui dataprep-redis embedding-tei retriever-redis reranking-tei tei-gaudi llm-vllm-hpu llm-vllm"
docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
cd $WORKPATH/docker
docker build --no-cache -t opea/chatqna:latest -f Dockerfile .
cd $WORKPATH/docker/ui
docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile .
docker images
}
function start_services() {
# build tei-gaudi for each test instead of pull from local registry
cd $WORKPATH
git clone https://github.com/huggingface/tei-gaudi
cd tei-gaudi/
docker build --no-cache -q -f Dockerfile-hpu -t opea/tei-gaudi:latest .
cd $WORKPATH/docker/gaudi
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
@@ -65,18 +49,6 @@ function start_services() {
sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
if [[ "$IMAGE_REPO" != "" ]]; then
# Replace the container name with a test-specific name
echo "using image repository $IMAGE_REPO and image tag $IMAGE_TAG"
sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${IMAGE_TAG}#g" compose_vllm.yaml
sed -i "s#image: opea/chatqna-ui:latest#image: opea/chatqna-ui:${IMAGE_TAG}#g" compose_vllm.yaml
sed -i "s#image: opea/chatqna-conversation-ui:latest#image: opea/chatqna-conversation-ui:${IMAGE_TAG}#g" compose_vllm.yaml
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose_vllm.yaml
sed -i "s#image: ${IMAGE_REPO}opea/tei-gaudi:latest#image: opea/tei-gaudi:latest#g" compose_vllm.yaml
echo "cat compose_vllm.yaml"
cat compose_vllm.yaml
fi
# Start Docker Containers
docker compose -f compose_vllm.yaml up -d
n=0
@@ -198,13 +170,16 @@ function validate_frontend() {
cd $WORKPATH/docker/ui/svelte
local conda_env_name="OPEA_e2e"
export PATH=${HOME}/miniforge3/bin/:$PATH
# conda remove -n ${conda_env_name} --all -y
# conda create -n ${conda_env_name} python=3.12 -y
if conda info --envs | grep -q "$conda_env_name"; then
echo "$conda_env_name exist!"
else
conda create -n ${conda_env_name} python=3.12 -y
fi
source activate ${conda_env_name}
sed -i "s/localhost/$ip_address/g" playwright.config.ts
# conda install -c conda-forge nodejs -y
conda install -c conda-forge nodejs -y
npm install && npm ci && npx playwright install --with-deps
node -v && npm -v && pip list
@@ -227,7 +202,7 @@ function stop_docker() {
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "" ]]; then build_docker_images; fi
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_time=$(date +%s)
start_services
end_time=$(date +%s)

66
ChatQnA/tests/test_chatqna_vllm_on_xeon.sh
View File

@@ -3,43 +3,33 @@
# SPDX-License-Identifier: Apache-2.0
set -e
echo "IMAGE_REPO=${IMAGE_REPO}"
IMAGE_REPO=${IMAGE_REPO:-"opea"}
IMAGE_TAG=${IMAGE_TAG:-"latest"}
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
export REGISTRY=${IMAGE_REPO}
export TAG=${IMAGE_TAG}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
cd $WORKPATH
git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps
docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile .
docker build -t opea/retriever-redis:latest -f comps/retrievers/langchain/redis/docker/Dockerfile .
docker build -t opea/reranking-tei:latest -f comps/reranks/tei/docker/Dockerfile .
docker build -t opea/llm-vllm:latest -f comps/llms/text-generation/vllm/docker/Dockerfile.microservice .
docker build -t opea/dataprep-redis:latest -f comps/dataprep/redis/langchain/docker/Dockerfile .
cd $WORKPATH/docker
docker build --no-cache -t opea/chatqna:latest -f Dockerfile .
git clone https://github.com/opea-project/GenAIComps.git
git clone https://github.com/vllm-project/vllm.git
cd $WORKPATH/docker/ui
docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile .
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="chatqna chatqna-ui dataprep-redis embedding-tei retriever-redis reranking-tei llm-vllm vllm"
docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
# cd $WORKPATH
# git clone https://github.com/vllm-project/vllm.git
# cd vllm
# docker build --no-cache -t opea/vllm:latest -f Dockerfile.cpu .
docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker images
}
function start_services() {
cd $WORKPATH
git clone https://github.com/vllm-project/vllm.git
cd vllm
docker build --no-cache -t opea/vllm:latest -f Dockerfile.cpu .
cd $WORKPATH/docker/xeon
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
@@ -62,29 +52,15 @@ function start_services() {
sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
if [[ "$IMAGE_REPO" != "" ]]; then
# Replace the container name with a test-specific name
echo "using image repository $IMAGE_REPO and image tag $IMAGE_TAG"
if [ "${mode}" == "perf" ]; then
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose_vllm.yaml
else
sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${IMAGE_TAG}#g" compose_vllm.yaml
sed -i "s#image: opea/chatqna-ui:latest#image: opea/chatqna-ui:${IMAGE_TAG}#g" compose_vllm.yaml
sed -i "s#image: opea/chatqna-conversation-ui:latest#image: opea/chatqna-conversation-ui:${IMAGE_TAG}#g" compose_vllm.yaml
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose_vllm.yaml
sed -i "s#image: ${IMAGE_REPO}opea/vllm:latest#image: opea/vllm:latest#g" compose_vllm.yaml
fi
fi
# Start Docker Containers
docker compose -f compose_vllm.yaml up -d
n=0
until [[ "$n" -ge 10 ]]; do
until [[ "$n" -ge 100 ]]; do
docker logs vllm-service > ${LOG_PATH}/vllm_service_start.log
if grep -q Connected ${LOG_PATH}/vllm_service_start.log; then
break
fi
sleep 10s
sleep 5s
n=$((n+1))
done
}
@@ -196,13 +172,17 @@ function validate_frontend() {
cd $WORKPATH/docker/ui/svelte
local conda_env_name="OPEA_e2e"
export PATH=${HOME}/miniforge3/bin/:$PATH
# conda remove -n ${conda_env_name} --all -y
# conda create -n ${conda_env_name} python=3.12 -y
if conda info --envs | grep -q "$conda_env_name"; then
echo "$conda_env_name exist!"
else
conda create -n ${conda_env_name} python=3.12 -y
fi
source activate ${conda_env_name}
sed -i "s/localhost/$ip_address/g" playwright.config.ts
# conda install -c conda-forge nodejs -y
conda install -c conda-forge nodejs -y
npm install && npm ci && npx playwright install --with-deps
node -v && npm -v && pip list
@@ -225,7 +205,7 @@ function stop_docker() {
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "" ]]; then build_docker_images; fi
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_time=$(date +%s)
start_services
end_time=$(date +%s)

60
ChatQnA/tests/test_chatqna_vllm_ray_on_gaudi.sh
View File

@@ -3,46 +3,31 @@
# SPDX-License-Identifier: Apache-2.0
set -e
echo "IMAGE_REPO=${IMAGE_REPO}"
IMAGE_REPO=${IMAGE_REPO:-"opea"}
IMAGE_TAG=${IMAGE_TAG:-"latest"}
echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
export REGISTRY=${IMAGE_REPO}
export TAG=${IMAGE_TAG}
WORKPATH=$(dirname "$PWD")
LOG_PATH="$WORKPATH/tests"
ip_address=$(hostname -I | awk '{print $1}')
function build_docker_images() {
cd $WORKPATH
cd $WORKPATH/docker
git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps
git clone https://github.com/huggingface/tei-gaudi
docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile .
docker build -t opea/retriever-redis:latest -f comps/retrievers/langchain/redis/docker/Dockerfile .
docker build -t opea/reranking-tei:latest -f comps/reranks/tei/docker/Dockerfile .
docker build -t opea/llm-vllm-ray-hpu:latest -f comps/llms/text-generation/vllm-ray/docker/Dockerfile.vllmray .
docker build -t opea/llm-vllm-ray:latest -f comps/llms/text-generation/vllm-ray/docker/Dockerfile.microservice .
docker build -t opea/dataprep-redis:latest -f comps/dataprep/redis/langchain/docker/Dockerfile .
# cd ..
# git clone https://github.com/huggingface/tei-gaudi
# cd tei-gaudi/
# docker build --no-cache -f Dockerfile-hpu -t opea/tei-gaudi:latest .
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
service_list="chatqna chatqna-ui dataprep-redis embedding-tei retriever-redis reranking-tei tei-gaudi llm-vllm-ray-hpu llm-vllm-ray"
docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
cd $WORKPATH/docker
docker build --no-cache -t opea/chatqna:latest -f Dockerfile .
cd $WORKPATH/docker/ui
docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile .
docker images
}
function start_services() {
# build tei-gaudi for each test instead of pull from local registry
cd $WORKPATH
git clone https://github.com/huggingface/tei-gaudi
cd tei-gaudi/
docker build --no-cache -q -f Dockerfile-hpu -t opea/tei-gaudi:latest .
cd $WORKPATH/docker/gaudi
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
@@ -65,18 +50,6 @@ function start_services() {
sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
if [[ "$IMAGE_REPO" != "" ]]; then
# Replace the container name with a test-specific name
echo "using image repository $IMAGE_REPO and image tag $IMAGE_TAG"
sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${IMAGE_TAG}#g" compose_vllm_ray.yaml
sed -i "s#image: opea/chatqna-ui:latest#image: opea/chatqna-ui:${IMAGE_TAG}#g" compose_vllm_ray.yaml
sed -i "s#image: opea/chatqna-conversation-ui:latest#image: opea/chatqna-conversation-ui:${IMAGE_TAG}#g" compose_vllm_ray.yaml
sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose_vllm_ray.yaml
sed -i "s#image: ${IMAGE_REPO}opea/tei-gaudi:latest#image: opea/tei-gaudi:latest#g" compose_vllm_ray.yaml
echo "cat compose_vllm_ray.yaml"
cat compose_vllm_ray.yaml
fi
# Start Docker Containers
docker compose -f compose_vllm_ray.yaml up -d
n=0
@@ -198,13 +171,16 @@ function validate_frontend() {
cd $WORKPATH/docker/ui/svelte
local conda_env_name="OPEA_e2e"
export PATH=${HOME}/miniforge3/bin/:$PATH
# conda remove -n ${conda_env_name} --all -y
# conda create -n ${conda_env_name} python=3.12 -y
if conda info --envs | grep -q "$conda_env_name"; then
echo "$conda_env_name exist!"
else
conda create -n ${conda_env_name} python=3.12 -y
fi
source activate ${conda_env_name}
sed -i "s/localhost/$ip_address/g" playwright.config.ts
# conda install -c conda-forge nodejs -y
conda install -c conda-forge nodejs -y
npm install && npm ci && npx playwright install --with-deps
node -v && npm -v && pip list
@@ -227,7 +203,7 @@ function stop_docker() {
function main() {
stop_docker
if [[ "$IMAGE_REPO" == "" ]]; then build_docker_images; fi
if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
start_time=$(date +%s)
start_services
end_time=$(date +%s)