From 939502dba1f039e0ee40205685c6f2094c6f5441 Mon Sep 17 00:00:00 2001 From: "chen, suyue" Date: Mon, 12 Aug 2024 00:26:01 +0800 Subject: [PATCH] support multiple test cases for ChatQnA (#553) Signed-off-by: chensuyue --- .github/workflows/_image-build.yml | 5 + .github/workflows/_run-docker-compose.yml | 111 ++++++++++++++++++ .github/workflows/pr-docker-compose-e2e.yml | 59 ++-------- ChatQnA/docker/gaudi/README.md | 4 +- ChatQnA/docker/gaudi/compose_vllm.yaml | 2 +- ChatQnA/docker/gaudi/compose_vllm_ray.yaml | 2 +- ChatQnA/docker/xeon/README.md | 2 +- ...ompose_qdrant.yaml => compose_qdrant.yaml} | 13 -- ...er_compose_vllm.yaml => compose_vllm.yaml} | 15 +-- ...h => _test_chatqna_guardrails_on_gaudi.sh} | 2 +- ...eon.sh => _test_chatqna_qdrant_on_xeon.sh} | 13 +- ...audi.sh => _test_chatqna_vllm_on_gaudi.sh} | 4 +- ..._xeon.sh => _test_chatqna_vllm_on_xeon.sh} | 14 ++- ....sh => _test_chatqna_vllm_ray_on_gaudi.sh} | 4 +- ChatQnA/tests/test_chatqna_on_gaudi.sh | 2 +- 15 files changed, 153 insertions(+), 99 deletions(-) create mode 100644 .github/workflows/_run-docker-compose.yml rename ChatQnA/docker/xeon/{docker_compose_qdrant.yaml => compose_qdrant.yaml} (93%) rename ChatQnA/docker/xeon/{docker_compose_vllm.yaml => compose_vllm.yaml} (93%) rename ChatQnA/tests/{test_chatqna_guardrails_on_gaudi.sh => _test_chatqna_guardrails_on_gaudi.sh} (99%) rename ChatQnA/tests/{test_chatqna_qdrant_on_xeon.sh => _test_chatqna_qdrant_on_xeon.sh} (95%) rename ChatQnA/tests/{test_chatqna_vllm_on_gaudi.sh => _test_chatqna_vllm_on_gaudi.sh} (97%) rename ChatQnA/tests/{test_chatqna_vllm_on_xeon.sh => _test_chatqna_vllm_on_xeon.sh} (96%) rename ChatQnA/tests/{test_chatqna_vllm_ray_on_gaudi.sh => _test_chatqna_vllm_ray_on_gaudi.sh} (97%) diff --git a/.github/workflows/_image-build.yml b/.github/workflows/_image-build.yml index bca7616a1..7e5f29df2 100644 --- a/.github/workflows/_image-build.yml +++ b/.github/workflows/_image-build.yml @@ -34,6 +34,10 @@ jobs: image_repo: ${{ steps.build-megaservice-image.outputs.image_repo }} image_tag: ${{ steps.build-megaservice-image.outputs.image_tag }} steps: + - name: Clean up Working Directory + run: | + sudo rm -rf ${{github.workspace}}/* || true + - name: Get checkout ref run: | if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then @@ -62,3 +66,4 @@ jobs: fi echo "IMAGE_TAG=${IMAGE_TAG}" echo "image_tag=$IMAGE_TAG" >> $GITHUB_OUTPUT + echo "image_repo=${IMAGE_REPO}" >> $GITHUB_OUTPUT diff --git a/.github/workflows/_run-docker-compose.yml b/.github/workflows/_run-docker-compose.yml new file mode 100644 index 000000000..4e4644b34 --- /dev/null +++ b/.github/workflows/_run-docker-compose.yml @@ -0,0 +1,111 @@ +# Copyright (C) 2024 Intel Corporation +# SPDX-License-Identifier: Apache-2.0 + +name: Image Build +permissions: read-all +on: + workflow_call: + inputs: + registry: + description: Container Registry URL + required: false + default: "" + type: string + tag: + description: Container Tag + required: false + default: "latest" + type: string + example: + description: Example to test + required: true + type: string + hardware: + description: Hardware to run the test on + required: true + type: string +jobs: + get-test-case: + runs-on: ubuntu-latest + outputs: + test_cases: ${{ steps.test-case-matrix.outputs.test_cases }} + CHECKOUT_REF: ${{ steps.get-checkout-ref.outputs.CHECKOUT_REF }} + steps: + - name: Get checkout ref + id: get-checkout-ref + run: | + if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then + CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge + else + CHECKOUT_REF=${{ github.ref }} + fi + echo "CHECHOUT_REF=${CHECKOUT_REF}" >> $GITHUB_OUTPUT + echo "checkout ref ${CHECKOUT_REF}" + + - name: Checkout out Repo + uses: actions/checkout@v4 + with: + ref: ${{ steps.get-checkout-ref.outputs.CHECKOUT_REF }} + fetch-depth: 0 + + - name: Get test matrix + shell: bash + id: test-case-matrix + run: | + set -x + example_l=$(echo ${{ inputs.example }} | tr '[:upper:]' '[:lower:]') + cd ${{ github.workspace }}/${{ inputs.example }}/tests + test_cases=$(find . -type f -name "test_${example_l}*on_${{ inputs.hardware }}.sh" -print | cut -d/ -f2 | jq -R '.' | jq -sc '.') + echo "test_cases=$test_cases" >> $GITHUB_OUTPUT + + run-test: + needs: [get-test-case] + strategy: + matrix: + test_case: ${{ fromJSON(needs.get-test-case.outputs.test_cases) }} + runs-on: ${{ inputs.hardware }} + continue-on-error: true + steps: + - name: Clean up Working Directory + run: | + sudo rm -rf ${{github.workspace}}/* || true + docker system prune -f + docker rmi $(docker images --filter reference="*/*/*:latest" -q) || true + + - name: Checkout out Repo + uses: actions/checkout@v4 + with: + ref: ${{ needs.get-test-case.outputs.CHECKOUT_REF }} + fetch-depth: 0 + + - name: Run test + shell: bash + env: + HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }} + GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }} + GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }} + IMAGE_REPO: ${{ inputs.registry }} + IMAGE_TAG: ${{ inputs.tag }} + example: ${{ inputs.example }} + hardware: ${{ inputs.hardware }} + test_case: ${{ matrix.test_case }} + run: | + cd ${{ github.workspace }}/$example/tests + export IMAGE_REPO=${OPEA_IMAGE_REPO} + if [ -f ${test_case} ]; then timeout 30m bash ${test_case}; else echo "Test script {${test_case}} not found, skip test!"; fi + + - name: Clean up container + shell: bash + if: cancelled() || failure() + run: | + cd ${{ github.workspace }}/${{ inputs.example }}/docker/${{ inputs.hardware }} + docker compose stop && docker compose rm -f + docker system prune -f + docker rmi $(docker images --filter reference="*:5000/*/*" -q) || true + + - name: Publish pipeline artifact + if: ${{ !cancelled() }} + uses: actions/upload-artifact@v4 + with: + name: ${{ matrix.test_case }} + path: ${{ github.workspace }}/${{ inputs.example }}/tests/*.log diff --git a/.github/workflows/pr-docker-compose-e2e.yml b/.github/workflows/pr-docker-compose-e2e.yml index 2ba04e027..856b25c6a 100644 --- a/.github/workflows/pr-docker-compose-e2e.yml +++ b/.github/workflows/pr-docker-compose-e2e.yml @@ -13,8 +13,7 @@ on: - "**/ui/**" - "!**.md" - "!**.txt" - - .github/workflows/docker-compose-e2e.yml - workflow_dispatch: + - .github/workflows/pr-docker-compose-e2e.yml # If there is a new commit, the previous jobs will be canceled concurrency: @@ -37,55 +36,13 @@ jobs: mega_service: "${{ matrix.example }}" runner_label: "docker-build-${{ matrix.hardware }}" - Example-test: + example-test: needs: [job1, mega-image-build] strategy: matrix: ${{ fromJSON(needs.job1.outputs.run_matrix) }} - runs-on: ${{ matrix.hardware }} - continue-on-error: true - steps: - - name: Test example - run: | - echo "Matrix - example ${{ matrix.example }}, hardware ${{ matrix.hardware }}" - - - name: Clean Up Working Directory - run: sudo rm -rf ${{github.workspace}}/* - - - name: Checkout out Repo - uses: actions/checkout@v4 - with: - ref: "refs/pull/${{ github.event.number }}/merge" - - - name: Run test - env: - HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }} - GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }} - GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }} - example: ${{ matrix.example }} - hardware: ${{ matrix.hardware }} - IMAGE_TAG: ${{ needs.mega-image-build.outputs.image_tag }} - IMAGE_REPO_GAUDI: ${{ vars.IMAGE_REPO_GAUDI }} - IMAGE_REPO_XEON: ${{ vars.IMAGE_REPO_XEON }} - run: | - cd ${{ github.workspace }}/$example/tests - if [ "$hardware" == "gaudi" ]; then IMAGE_REPO=$IMAGE_REPO_GAUDI; else IMAGE_REPO=$IMAGE_REPO_XEON; fi - export IMAGE_REPO=${IMAGE_REPO} - example_l=$(echo $example | tr '[:upper:]' '[:lower:]') - if [ -f test_${example_l}_on_${hardware}.sh ]; then timeout 30m bash test_${example_l}_on_${hardware}.sh; else echo "Test script not found, skip test!"; fi - - - name: Clean up container - env: - example: ${{ matrix.example }} - hardware: ${{ matrix.hardware }} - if: cancelled() || failure() - run: | - cd ${{ github.workspace }}/$example/docker/$hardware - docker compose stop && docker compose rm -f - echo y | docker system prune - - - name: Publish pipeline artifact - if: ${{ !cancelled() }} - uses: actions/upload-artifact@v4 - with: - name: ${{ matrix.example }}-${{ matrix.hardware }} - path: ${{ github.workspace }}/${{ matrix.example }}/tests/*.log + uses: ./.github/workflows/_run-docker-compose.yml + with: + tag: ${{ needs.mega-image-build.outputs.image_tag }} + example: ${{ matrix.example }} + hardware: ${{ matrix.hardware }} + secrets: inherit diff --git a/ChatQnA/docker/gaudi/README.md b/ChatQnA/docker/gaudi/README.md index 2f70c0f14..03cc79bad 100644 --- a/ChatQnA/docker/gaudi/README.md +++ b/ChatQnA/docker/gaudi/README.md @@ -46,7 +46,7 @@ docker build --no-cache -t opea/llm-tgi:latest --build-arg https_proxy=$https_pr Build vllm docker. ```bash -docker build --no-cache -t vllm:hpu --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/vllm/docker/Dockerfile.hpu . +docker build --no-cache -t opea/llm-vllm-hpu:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/vllm/docker/Dockerfile.hpu . ``` Build microservice docker. @@ -60,7 +60,7 @@ docker build --no-cache -t opea/llm-vllm:latest --build-arg https_proxy=$https_p Build vllm-on-ray docker. ```bash -docker build --no-cache -t vllm_ray:habana --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/vllm-ray/docker/Dockerfile.vllmray . +docker build --no-cache -t opea/llm-vllm-ray-hpu:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/vllm-ray/docker/Dockerfile.vllmray . ``` Build microservice docker. diff --git a/ChatQnA/docker/gaudi/compose_vllm.yaml b/ChatQnA/docker/gaudi/compose_vllm.yaml index 69be293f3..9082bff46 100644 --- a/ChatQnA/docker/gaudi/compose_vllm.yaml +++ b/ChatQnA/docker/gaudi/compose_vllm.yaml @@ -109,7 +109,7 @@ services: HF_HUB_ENABLE_HF_TRANSFER: 0 restart: unless-stopped vllm-service: - image: vllm:hpu + image: opea/llm-vllm-hpu:latest container_name: vllm-gaudi-server ports: - "8008:80" diff --git a/ChatQnA/docker/gaudi/compose_vllm_ray.yaml b/ChatQnA/docker/gaudi/compose_vllm_ray.yaml index 7bce9463a..d7fa0ca6e 100644 --- a/ChatQnA/docker/gaudi/compose_vllm_ray.yaml +++ b/ChatQnA/docker/gaudi/compose_vllm_ray.yaml @@ -109,7 +109,7 @@ services: HF_HUB_ENABLE_HF_TRANSFER: 0 restart: unless-stopped vllm-ray-service: - image: vllm_ray:habana + image: opea/llm-vllm-ray-hpu:latest container_name: vllm-ray-gaudi-server ports: - "8008:8000" diff --git a/ChatQnA/docker/xeon/README.md b/ChatQnA/docker/xeon/README.md index a8a815d4f..2c71feff8 100644 --- a/ChatQnA/docker/xeon/README.md +++ b/ChatQnA/docker/xeon/README.md @@ -99,7 +99,7 @@ Build vLLM docker. ```bash git clone https://github.com/vllm-project/vllm.git cd ./vllm/ -docker build --no-cache -t vllm:cpu --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile.cpu . +docker build --no-cache -t opea/vllm:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile.cpu . ``` Build microservice. diff --git a/ChatQnA/docker/xeon/docker_compose_qdrant.yaml b/ChatQnA/docker/xeon/compose_qdrant.yaml similarity index 93% rename from ChatQnA/docker/xeon/docker_compose_qdrant.yaml rename to ChatQnA/docker/xeon/compose_qdrant.yaml index e3ed77f4e..d3573d248 100644 --- a/ChatQnA/docker/xeon/docker_compose_qdrant.yaml +++ b/ChatQnA/docker/xeon/compose_qdrant.yaml @@ -189,19 +189,6 @@ services: - DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT} ipc: host restart: always - chaqna-xeon-conversation-ui-server: - image: opea/chatqna-conversation-ui:latest - container_name: chatqna-xeon-conversation-ui-server - environment: - - no_proxy=${no_proxy} - - https_proxy=${https_proxy} - - http_proxy=${http_proxy} - ports: - - 5174:80 - depends_on: - - chaqna-xeon-backend-server - ipc: host - restart: always networks: default: diff --git a/ChatQnA/docker/xeon/docker_compose_vllm.yaml b/ChatQnA/docker/xeon/compose_vllm.yaml similarity index 93% rename from ChatQnA/docker/xeon/docker_compose_vllm.yaml rename to ChatQnA/docker/xeon/compose_vllm.yaml index 2ff0faa1a..b66218c9a 100644 --- a/ChatQnA/docker/xeon/docker_compose_vllm.yaml +++ b/ChatQnA/docker/xeon/compose_vllm.yaml @@ -113,7 +113,7 @@ services: LANGCHAIN_PROJECT: "opea-reranking-service" restart: unless-stopped vllm_service: - image: vllm:cpu + image: opea/vllm:latest container_name: vllm-service ports: - "9009:80" @@ -190,19 +190,6 @@ services: - DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT} ipc: host restart: always - chaqna-xeon-conversation-ui-server: - image: opea/chatqna-conversation-ui:latest - container_name: chatqna-xeon-conversation-ui-server - environment: - - no_proxy=${no_proxy} - - https_proxy=${https_proxy} - - http_proxy=${http_proxy} - ports: - - 5174:80 - depends_on: - - chaqna-xeon-backend-server - ipc: host - restart: always networks: default: diff --git a/ChatQnA/tests/test_chatqna_guardrails_on_gaudi.sh b/ChatQnA/tests/_test_chatqna_guardrails_on_gaudi.sh similarity index 99% rename from ChatQnA/tests/test_chatqna_guardrails_on_gaudi.sh rename to ChatQnA/tests/_test_chatqna_guardrails_on_gaudi.sh index 742d933d1..6248dcff8 100644 --- a/ChatQnA/tests/test_chatqna_guardrails_on_gaudi.sh +++ b/ChatQnA/tests/_test_chatqna_guardrails_on_gaudi.sh @@ -43,7 +43,7 @@ function start_services() { cd $WORKPATH git clone https://github.com/huggingface/tei-gaudi cd tei-gaudi/ - docker build --no-cache -f Dockerfile-hpu -t opea/tei-gaudi:latest . + docker build --no-cache -q -f Dockerfile-hpu -t opea/tei-gaudi:latest . cd $WORKPATH/docker/gaudi export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" diff --git a/ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh b/ChatQnA/tests/_test_chatqna_qdrant_on_xeon.sh similarity index 95% rename from ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh rename to ChatQnA/tests/_test_chatqna_qdrant_on_xeon.sh index 977e28749..f2d0f0e37 100644 --- a/ChatQnA/tests/test_chatqna_qdrant_on_xeon.sh +++ b/ChatQnA/tests/_test_chatqna_qdrant_on_xeon.sh @@ -16,7 +16,7 @@ function build_docker_images() { docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile . docker build -t opea/retriever-qdrant:latest -f comps/retrievers/haystack/qdrant/docker/Dockerfile . - docker build -t opea/reranking-tei:latest -f comps/reranks/langchain/docker/Dockerfile . + docker build -t opea/reranking-tei:latest -f comps/reranks/tei/docker/Dockerfile . docker build -t opea/llm-tgi:latest -f comps/llms/text-generation/tgi/Dockerfile . docker build -t opea/dataprep-qdrant:latest -f comps/dataprep/qdrant/docker/Dockerfile . @@ -55,14 +55,15 @@ function start_services() { if [[ "$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.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: ${IMAGE_REPO}opea/#g" compose.yaml + sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${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: ${IMAGE_REPO}opea/#g" compose_qdrant.yaml + cat compose_qdrant.yaml fi # Start Docker Containers - docker compose up -d + docker compose -f compose_qdrant.yaml up -d n=0 until [[ "$n" -ge 200 ]]; do docker logs tgi-service > tgi_service_start.log diff --git a/ChatQnA/tests/test_chatqna_vllm_on_gaudi.sh b/ChatQnA/tests/_test_chatqna_vllm_on_gaudi.sh similarity index 97% rename from ChatQnA/tests/test_chatqna_vllm_on_gaudi.sh rename to ChatQnA/tests/_test_chatqna_vllm_on_gaudi.sh index 87953dfde..716a20678 100644 --- a/ChatQnA/tests/test_chatqna_vllm_on_gaudi.sh +++ b/ChatQnA/tests/_test_chatqna_vllm_on_gaudi.sh @@ -17,7 +17,7 @@ function build_docker_images() { 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 vllm:hpu -f comps/llms/text-generation/vllm/docker/Dockerfile.hpu . + 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 . @@ -42,7 +42,7 @@ function start_services() { cd $WORKPATH git clone https://github.com/huggingface/tei-gaudi cd tei-gaudi/ - docker build --no-cache -f Dockerfile-hpu -t opea/tei-gaudi:latest . + 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" diff --git a/ChatQnA/tests/test_chatqna_vllm_on_xeon.sh b/ChatQnA/tests/_test_chatqna_vllm_on_xeon.sh similarity index 96% rename from ChatQnA/tests/test_chatqna_vllm_on_xeon.sh rename to ChatQnA/tests/_test_chatqna_vllm_on_xeon.sh index 6ea823f72..e92954313 100644 --- a/ChatQnA/tests/test_chatqna_vllm_on_xeon.sh +++ b/ChatQnA/tests/_test_chatqna_vllm_on_xeon.sh @@ -26,15 +26,21 @@ function build_docker_images() { cd $WORKPATH/docker/ui docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile . - cd $WORKPATH - git clone https://github.com/vllm-project/vllm.git - cd vllm - docker build --no-cache -t vllm:cpu -f Dockerfile.cpu . +# 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 images } function start_services() { + # build vllm for each test instead of pull from local registry + 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" diff --git a/ChatQnA/tests/test_chatqna_vllm_ray_on_gaudi.sh b/ChatQnA/tests/_test_chatqna_vllm_ray_on_gaudi.sh similarity index 97% rename from ChatQnA/tests/test_chatqna_vllm_ray_on_gaudi.sh rename to ChatQnA/tests/_test_chatqna_vllm_ray_on_gaudi.sh index 6d94252e5..ab41c3bb8 100644 --- a/ChatQnA/tests/test_chatqna_vllm_ray_on_gaudi.sh +++ b/ChatQnA/tests/_test_chatqna_vllm_ray_on_gaudi.sh @@ -17,7 +17,7 @@ function build_docker_images() { 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 vllm_ray:habana -f comps/llms/text-generation/vllm-ray/docker/Dockerfile.vllmray . + 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 . @@ -42,7 +42,7 @@ function start_services() { cd $WORKPATH git clone https://github.com/huggingface/tei-gaudi cd tei-gaudi/ - docker build --no-cache -f Dockerfile-hpu -t opea/tei-gaudi:latest . + 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" diff --git a/ChatQnA/tests/test_chatqna_on_gaudi.sh b/ChatQnA/tests/test_chatqna_on_gaudi.sh index 957a02685..3a5e7537b 100644 --- a/ChatQnA/tests/test_chatqna_on_gaudi.sh +++ b/ChatQnA/tests/test_chatqna_on_gaudi.sh @@ -42,7 +42,7 @@ function start_services() { cd $WORKPATH git clone https://github.com/huggingface/tei-gaudi cd tei-gaudi/ - docker build --no-cache -f Dockerfile-hpu -t opea/tei-gaudi:latest . + 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"