diff --git a/ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml b/ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml index 2dc105708..078464bb9 100644 --- a/ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml +++ b/ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${CHATQNA_INDEX_NAME} TEI_ENDPOINT: ${CHATQNA_TEI_EMBEDDING_ENDPOINT} HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped chatqna-tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 @@ -109,11 +115,18 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-backend-server depends_on: - - chatqna-redis-vector-db - - chatqna-tei-embedding-service - - chatqna-retriever - - chatqna-tei-reranking-service - - chatqna-tgi-service + chatqna-redis-vector-db: + condition: service_started + chatqna-tei-embedding-service: + condition: service_started + chatqna-retriever: + condition: service_started + chatqna-tei-reranking-service: + condition: service_started + chatqna-tgi-service: + condition: service_started + chatqna-dataprep-service: + condition: service_healthy ports: - "${CHATQNA_BACKEND_SERVICE_PORT:-8888}:8888" environment: diff --git a/ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen.yaml b/ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen.yaml index 415a61ea0..aec398775 100644 --- a/ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen.yaml +++ b/ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${CHATQNA_INDEX_NAME} TEI_ENDPOINT: ${CHATQNA_TEI_EMBEDDING_ENDPOINT} HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped chatqna-tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 @@ -128,12 +134,20 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-backend-server depends_on: - - chatqna-redis-vector-db - - chatqna-tei-embedding-service - - chatqna-retriever - - chatqna-tei-reranking-service - - chatqna-tgi-service - - chatqna-llm-faqgen + chatqna-redis-vector-db: + condition: service_started + chatqna-tei-embedding-service: + condition: service_started + chatqna-retriever: + condition: service_started + chatqna-tei-reranking-service: + condition: service_started + chatqna-tgi-service: + condition: service_started + chatqna-llm-faqgen: + condition: service_started + chatqna-dataprep-service: + condition: service_healthy ports: - "${CHATQNA_BACKEND_SERVICE_PORT}:8888" environment: diff --git a/ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen_vllm.yaml b/ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen_vllm.yaml index 6d7d0cd02..1c193f718 100644 --- a/ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen_vllm.yaml +++ b/ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen_vllm.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${CHATQNA_INDEX_NAME} TEI_ENDPOINT: ${CHATQNA_TEI_EMBEDDING_ENDPOINT} HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped chatqna-tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 @@ -133,12 +139,20 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-backend-server depends_on: - - chatqna-redis-vector-db - - chatqna-tei-embedding-service - - chatqna-retriever - - chatqna-tei-reranking-service - - chatqna-vllm-service - - chatqna-llm-faqgen + chatqna-redis-vector-db: + condition: service_started + chatqna-tei-embedding-service: + condition: service_started + chatqna-retriever: + condition: service_started + chatqna-tei-reranking-service: + condition: service_started + chatqna-vllm-service: + condition: service_started + chatqna-llm-faqgen: + condition: service_started + chatqna-dataprep-redis-service: + condition: service_healthy ports: - "${CHATQNA_BACKEND_SERVICE_PORT}:8888" environment: diff --git a/ChatQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml b/ChatQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml index 51cb00229..d95ec39e9 100644 --- a/ChatQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml +++ b/ChatQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${CHATQNA_INDEX_NAME} TEI_ENDPOINT: ${CHATQNA_TEI_EMBEDDING_ENDPOINT} HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped chatqna-tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 @@ -111,11 +117,18 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-backend-server depends_on: - - chatqna-redis-vector-db - - chatqna-tei-embedding-service - - chatqna-retriever - - chatqna-tei-reranking-service - - chatqna-vllm-service + chatqna-redis-vector-db: + condition: service_started + chatqna-tei-embedding-service: + condition: service_started + chatqna-retriever: + condition: service_started + chatqna-tei-reranking-service: + condition: service_started + chatqna-vllm-service: + condition: service_started + chatqna-dataprep-service: + condition: service_healthy ports: - "${CHATQNA_BACKEND_SERVICE_PORT}:8888" environment: diff --git a/ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml b/ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml index f6ee6ecef..6e3578e97 100644 --- a/ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml +++ b/ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-server @@ -92,11 +98,16 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-aipc-backend-server depends_on: - - redis-vector-db - - dataprep-redis-service - - tei-embedding-service - - retriever - - tei-reranking-service + redis-vector-db: + condition: service_started + dataprep-redis-service: + condition: service_healthy + tei-embedding-service: + condition: service_started + retriever: + condition: service_started + tei-reranking-service: + condition: service_started ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml index b5703ab94..12b179996 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml @@ -32,6 +32,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-server @@ -107,11 +113,18 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-xeon-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - vllm-service + redis-vector-db: + condition: service_started + dataprep-redis-service: + condition: service_healthy + tei-embedding-service: + condition: service_started + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + vllm-service: + condition: service_healthy ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml index a3525f86c..06232276f 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-server @@ -121,12 +127,20 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-xeon-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - vllm-service - - llm-faqgen + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + vllm-service: + condition: service_started + llm-faqgen: + condition: service_started + dataprep-redis-service: + condition: service_healthy ports: - ${CHATQNA_BACKEND_PORT:-8888}:8888 environment: diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen_tgi.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen_tgi.yaml index 7e34ff041..1cd3f4fe7 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen_tgi.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen_tgi.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-server @@ -121,12 +127,20 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-xeon-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - tgi-service - - llm-faqgen + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + tgi-service: + condition: service_started + llm-faqgen: + condition: service_started + dataprep-redis-service: + condition: service_healthy ports: - ${CHATQNA_BACKEND_PORT:-8888}:8888 environment: diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml index 05ce63e77..d7a5b687d 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml @@ -78,6 +78,11 @@ services: HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} EMBEDDING_MODEL_ID: ${EMBEDDING_MODEL_ID} LOGFLAG: ${LOGFLAG} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 restart: unless-stopped depends_on: milvus-standalone: @@ -154,7 +159,7 @@ services: LLM_MODEL_ID: ${LLM_MODEL_ID} VLLM_TORCH_PROFILER_DIR: "/mnt" healthcheck: - test: ["CMD-SHELL", "curl -f http://$host_ip:9009/health || exit 1"] + test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"] interval: 10s timeout: 10s retries: 100 @@ -164,12 +169,16 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-xeon-backend-server depends_on: - - milvus-standalone - - tei-embedding-service - - dataprep-milvus-service - - retriever - - tei-reranking-service - - vllm-service + tei-embedding-service: + condition: service_started + dataprep-milvus-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + vllm-service: + condition: service_healthy ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml index 1c6774510..ffd397209 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml @@ -22,6 +22,12 @@ services: LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY} HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_PINECONE" + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-server @@ -89,11 +95,16 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-xeon-backend-server depends_on: - - tei-embedding-service - - dataprep-pinecone-service - - retriever - - tei-reranking-service - - vllm-service + tei-embedding-service: + condition: service_started + dataprep-pinecone-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + vllm-service: + condition: service_started ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml index a08e37342..38cad037a 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml @@ -26,6 +26,12 @@ services: TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_QDRANT" + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 container_name: tei-embedding-server @@ -94,11 +100,18 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-xeon-backend-server depends_on: - - qdrant-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - vllm-service + qdrant-vector-db: + condition: service_started + dataprep-qdrant-service: + condition: service_healthy + tei-embedding-service: + condition: service_started + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + vllm-service: + condition: service_started ports: - "8912:8888" environment: diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml index 62452a9fd..7e138435c 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-server @@ -94,12 +100,18 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-xeon-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - dataprep-redis-service - - retriever - - tei-reranking-service - - tgi-service + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + tgi-service: + condition: service_started ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml b/ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml index d0d25428f..dea682626 100644 --- a/ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml +++ b/ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-server @@ -78,11 +84,16 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-xeon-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - dataprep-redis-service - - retriever - - vllm-service + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + vllm-service: + condition: service_started ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml index 37576e06b..b8b96ad04 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml @@ -32,6 +32,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-gaudi-server @@ -102,7 +108,7 @@ services: NUM_CARDS: ${NUM_CARDS} VLLM_TORCH_PROFILER_DIR: "/mnt" healthcheck: - test: ["CMD-SHELL", "curl -f http://$host_ip:8007/health || exit 1"] + test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"] interval: 10s timeout: 10s retries: 100 @@ -115,11 +121,18 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-gaudi-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - vllm-service + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + vllm-service: + condition: service_healthy ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen.yaml index 6bbbec3e1..f84c955b3 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen.yaml @@ -26,6 +26,12 @@ services: TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} LOGFLAG: ${LOGFLAG} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-gaudi-server @@ -100,7 +106,7 @@ services: LLM_ENDPOINT_PORT: ${LLM_ENDPOINT_PORT} VLLM_SKIP_WARMUP: ${VLLM_SKIP_WARMUP:-false} healthcheck: - test: ["CMD-SHELL", "curl -f http://${host_ip}:${LLM_ENDPOINT_PORT}/health || exit 1"] + test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"] interval: 10s timeout: 10s retries: 100 @@ -132,12 +138,20 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-gaudi-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - vllm-service - - llm-faqgen + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + vllm-service: + condition: service_healthy + llm-faqgen: + condition: service_started ports: - ${CHATQNA_BACKEND_PORT:-8888}:8888 environment: diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen_tgi.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen_tgi.yaml index 670caccea..e54e616c4 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen_tgi.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen_tgi.yaml @@ -26,6 +26,12 @@ services: TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} LOGFLAG: ${LOGFLAG} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-gaudi-server @@ -109,7 +115,7 @@ services: - SYS_NICE ipc: host healthcheck: - test: ["CMD-SHELL", "curl -f http://${host_ip}:${LLM_ENDPOINT_PORT}/health || exit 1"] + test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"] interval: 10s timeout: 10s retries: 100 @@ -137,12 +143,20 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-gaudi-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - tgi-service - - llm-faqgen + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + tgi-service: + condition: service_healthy + llm-faqgen: + condition: service_started ports: - ${CHATQNA_BACKEND_PORT:-8888}:8888 environment: diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml index 32368748c..cc0ea6f5b 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped vllm-guardrails-service: image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest} container_name: vllm-guardrails-server @@ -154,13 +160,22 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-gaudi-guardrails-server depends_on: - - redis-vector-db - - vllm-guardrails-service - - guardrails - - tei-embedding-service - - retriever - - tei-reranking-service - - vllm-service + redis-vector-db: + condition: service_started + vllm-guardrails-service: + condition: service_started + guardrails: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + vllm-service: + condition: service_started ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml index f10a34e6a..5be2c4387 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-gaudi-server @@ -109,11 +115,18 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-gaudi-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - tgi-service + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + tgi-service: + condition: service_started ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml index 4d4413dd1..a59138bbd 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-gaudi-server @@ -84,10 +90,16 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-gaudi-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - vllm-service + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + vllm-service: + condition: service_started ports: - "8888:8888" environment: diff --git a/ChatQnA/docker_compose/nvidia/gpu/compose.yaml b/ChatQnA/docker_compose/nvidia/gpu/compose.yaml index a655a3712..7a30c37c6 100644 --- a/ChatQnA/docker_compose/nvidia/gpu/compose.yaml +++ b/ChatQnA/docker_compose/nvidia/gpu/compose.yaml @@ -25,6 +25,12 @@ services: INDEX_NAME: ${INDEX_NAME} TEI_ENDPOINT: http://tei-embedding-service:80 HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} + healthcheck: + test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"] + interval: 10s + timeout: 5s + retries: 50 + restart: unless-stopped tei-embedding-service: image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 container_name: tei-embedding-server @@ -108,11 +114,18 @@ services: image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} container_name: chatqna-backend-server depends_on: - - redis-vector-db - - tei-embedding-service - - retriever - - tei-reranking-service - - tgi-service + redis-vector-db: + condition: service_started + tei-embedding-service: + condition: service_started + dataprep-redis-service: + condition: service_healthy + retriever: + condition: service_started + tei-reranking-service: + condition: service_started + tgi-service: + condition: service_started ports: - "8888:8888" environment: