Vous pouvez déployer une VM à apprentissage profond avec une charge de travail NVIDIA RAG à l'aide d'une base de données PostgreSQL pgvector gérée par VMware Data Services Manager.

Conditions préalables

Procédure

  1. Si vous déployez la VM à apprentissage profond directement sur le cluster vSphere ou à l'aide de la commande kubectl, créez un script cloud-init et déployez la VM à apprentissage profond.
    1. Créez un script cloud-init pour NVIDIA RAG et la base de données PostgreSQL pgvector que vous avez créée.
      Vous pouvez modifier la version initiale du script cloud-init pour NVIDIA RAG. Par exemple, pour NVIDIA RAG 24.03 et une base de données PostgreSQL pgvector avec les détails de connexion postgres://pgvector_db_admin:encoded_pgvector_db_admin_password@pgvector_db_ip_address:5432/pgvector_db_name.
      #cloud-config
      write_files:
      - path: /opt/dlvm/dl_app.sh
        permissions: '0755'
        content: |
          #!/bin/bash
          error_exit() {
            echo "Error: $1" >&2
            exit 1
          }
      
          cat <<EOF > /opt/dlvm/config.json
          {
            "_comment": "This provides default support for RAG: TensorRT inference, llama2-13b model, and H100x2 GPU",
            "rag": {
              "org_name": "cocfwga8jq2c",
              "org_team_name": "no-team",
              "rag_repo_name": "nvidia/paif",
              "llm_repo_name": "nvidia/nim",
              "embed_repo_name": "nvidia/nemo-retriever",
              "rag_name": "rag-docker-compose",
              "rag_version": "24.03",
              "embed_name": "nv-embed-qa",
              "embed_type": "NV-Embed-QA",
              "embed_version": "4",
              "inference_type": "trt",
              "llm_name": "llama2-13b-chat",
              "llm_version": "h100x2_fp16_24.02",
              "num_gpu": "2",
              "hf_token": "huggingface token to pull llm model, update when using vllm inference",
              "hf_repo": "huggingface llm model repository, update when using vllm inference"
            }
          }
          EOF
          CONFIG_JSON=$(cat "/opt/dlvm/config.json")
          INFERENCE_TYPE=$(echo "${CONFIG_JSON}" | jq -r '.rag.inference_type')
          if [ "${INFERENCE_TYPE}" = "trt" ]; then
            required_vars=("ORG_NAME" "ORG_TEAM_NAME" "RAG_REPO_NAME" "LLM_REPO_NAME" "EMBED_REPO_NAME" "RAG_NAME" "RAG_VERSION" "EMBED_NAME" "EMBED_TYPE" "EMBED_VERSION" "LLM_NAME" "LLM_VERSION" "NUM_GPU")
          elif [ "${INFERENCE_TYPE}" = "vllm" ]; then
            required_vars=("ORG_NAME" "ORG_TEAM_NAME" "RAG_REPO_NAME" "LLM_REPO_NAME" "EMBED_REPO_NAME" "RAG_NAME" "RAG_VERSION" "EMBED_NAME" "EMBED_TYPE" "EMBED_VERSION" "LLM_NAME" "NUM_GPU" "HF_TOKEN" "HF_REPO")
          else
            error_exit "Inference type '${INFERENCE_TYPE}' is not recognized. No action will be taken."
          fi
          for index in "${!required_vars[@]}"; do
            key="${required_vars[$index]}"
            jq_query=".rag.${key,,} | select (.!=null)"
            value=$(echo "${CONFIG_JSON}" | jq -r "${jq_query}")
            if [[ -z "${value}" ]]; then 
              error_exit "${key} is required but not set."
            else
              eval ${key}=\""${value}"\"
            fi
          done
      
          RAG_URI="${RAG_REPO_NAME}/${RAG_NAME}:${RAG_VERSION}"
          LLM_MODEL_URI="${LLM_REPO_NAME}/${LLM_NAME}:${LLM_VERSION}"
          EMBED_MODEL_URI="${EMBED_REPO_NAME}/${EMBED_NAME}:${EMBED_VERSION}"
      
          NGC_CLI_VERSION="3.41.2"
          NGC_CLI_URL="https://api.ngc.nvidia.com/v2/resources/nvidia/ngc-apps/ngc_cli/versions/${NGC_CLI_VERSION}/files/ngccli_linux.zip"
      
          mkdir -p /opt/data
          cd /opt/data
      
          if [ ! -f .file_downloaded ]; then
            # clean up
            rm -rf compose.env ${RAG_NAME}* ${LLM_NAME}* ngc* ${EMBED_NAME}* *.json .file_downloaded
      
            # install ngc-cli
            wget --content-disposition ${NGC_CLI_URL} -O ngccli_linux.zip && unzip ngccli_linux.zip
            export PATH=`pwd`/ngc-cli:${PATH}
      
            APIKEY=""
            REG_URI="nvcr.io"
      
            if [[ "$(grep registry-uri /opt/dlvm/ovf-env.xml | sed -n 's/.*oe:value="\([^"]*\).*/\1/p')" == *"${REG_URI}"* ]]; then
              APIKEY=$(grep registry-passwd /opt/dlvm/ovf-env.xml | sed -n 's/.*oe:value="\([^"]*\).*/\1/p')
            fi
      
            if [ -z "${APIKEY}" ]; then
                error_exit "No APIKEY found"
            fi
      
            # config ngc-cli
            mkdir -p ~/.ngc
      
            cat << EOF > ~/.ngc/config
            [CURRENT]
            apikey = ${APIKEY}
            format_type = ascii
            org = ${ORG_NAME}
            team = ${ORG_TEAM_NAME}
            ace = no-ace
          EOF
      
            # ngc docker login
            docker login nvcr.io -u \$oauthtoken -p ${APIKEY}
      
            # dockerhub login for general components, e.g. minio
            DOCKERHUB_URI=$(grep registry-2-uri /opt/dlvm/ovf-env.xml | sed -n 's/.*oe:value="\([^"]*\).*/\1/p')
            DOCKERHUB_USERNAME=$(grep registry-2-user /opt/dlvm/ovf-env.xml | sed -n 's/.*oe:value="\([^"]*\).*/\1/p')
            DOCKERHUB_PASSWORD=$(grep registry-2-passwd /opt/dlvm/ovf-env.xml | sed -n 's/.*oe:value="\([^"]*\).*/\1/p')
      
            if [[ -n "${DOCKERHUB_USERNAME}" && -n "${DOCKERHUB_PASSWORD}" ]]; then
              docker login -u ${DOCKERHUB_USERNAME} -p ${DOCKERHUB_PASSWORD}
            else
              echo "Warning: DockerHub not login"
            fi
      
            # get RAG files
            ngc registry resource download-version ${RAG_URI}
      
            # get llm model
            if [ "${INFERENCE_TYPE}" = "trt" ]; then
              ngc registry model download-version ${LLM_MODEL_URI}
              chmod -R o+rX ${LLM_NAME}_v${LLM_VERSION}
              LLM_MODEL_FOLDER="/opt/data/${LLM_NAME}_v${LLM_VERSION}"
            elif [ "${INFERENCE_TYPE}" = "vllm" ]; then
              pip install huggingface_hub
              huggingface-cli login --token ${HF_TOKEN}
              huggingface-cli download --resume-download ${HF_REPO}/${LLM_NAME} --local-dir ${LLM_NAME} --local-dir-use-symlinks False
              LLM_MODEL_FOLDER="/opt/data/${LLM_NAME}"
              cat << EOF > ${LLM_MODEL_FOLDER}/model_config.yaml 
              engine:
                model: /model-store
                enforce_eager: false
                max_context_len_to_capture: 8192
                max_num_seqs: 256
                dtype: float16
                tensor_parallel_size: ${NUM_GPU}
                gpu_memory_utilization: 0.8
          EOF
              chmod -R o+rX ${LLM_MODEL_FOLDER}
              python3 -c "import yaml, json, sys; print(json.dumps(yaml.safe_load(sys.stdin.read())))" < "${RAG_NAME}_v${RAG_VERSION}/rag-app-text-chatbot.yaml"> rag-app-text-chatbot.json
              jq '.services."nemollm-inference".image = "nvcr.io/nvidia/nim/nim_llm:24.02-day0" |
                  .services."nemollm-inference".command = "nim_vllm --model_name ${MODEL_NAME} --model_config /model-store/model_config.yaml" |
                  .services."nemollm-inference".ports += ["8000:8000"] |
                  .services."nemollm-inference".expose += ["8000"]' rag-app-text-chatbot.json > temp.json && mv temp.json rag-app-text-chatbot.json
              python3 -c "import yaml, json, sys; print(yaml.safe_dump(json.load(sys.stdin), default_flow_style=False, sort_keys=False))" < rag-app-text-chatbot.json > "${RAG_NAME}_v${RAG_VERSION}/rag-app-text-chatbot.yaml"
            fi
      
            # get embedding models
            ngc registry model download-version ${EMBED_MODEL_URI}
            chmod -R o+rX ${EMBED_NAME}_v${EMBED_VERSION}
      
            # config compose.env
            cat << EOF > compose.env
            export MODEL_DIRECTORY="${LLM_MODEL_FOLDER}"
            export MODEL_NAME=${LLM_NAME}
            export NUM_GPU=${NUM_GPU}
            export APP_CONFIG_FILE=/dev/null
            export EMBEDDING_MODEL_DIRECTORY="/opt/data/${EMBED_NAME}_v${EMBED_VERSION}"
            export EMBEDDING_MODEL_NAME=${EMBED_TYPE}
            export EMBEDDING_MODEL_CKPT_NAME="${EMBED_TYPE}-${EMBED_VERSION}.nemo"
            export POSTGRES_HOST_IP=pgvector_db_ip_address
            export POSTGRES_PORT_NUMBER=5432
            export POSTGRES_DB=pgvector_db_name
            export POSTGRES_USER=pgvector_db_admin
            export POSTGRES_PASSWORD=encoded_pgvector_db_admin_password
          EOF
      
            touch .file_downloaded
          fi
      
          # start NGC RAG
          docker compose -f ${RAG_NAME}_v${RAG_VERSION}/docker-compose-vectordb.yaml up -d pgvector
          source compose.env; docker compose -f ${RAG_NAME}_v${RAG_VERSION}/rag-app-text-chatbot.yaml up -d
    2. Codez le script cloud-init au format base64.
      Utilisez un outil de codage au format base64, tel que https://decode64base.com/ pour générer la version codée de votre script cloud-init.
    3. Déployez la VM à apprentissage profond, en transmettant la valeur base64 du script cloud-init au paramètre d'entrée user-data.
  2. Si vous déployez la VM à apprentissage profond à l'aide d'un élément de catalogue dans VMware Aria Automation, fournissez les détails de la base de données PostgreSQL pgvector après avoir déployé la machine virtuelle.
    1. Déployez la VM à apprentissage profond à partir d'Automation Service Broker.
    2. Accédez à Consommer > Déploiements > Déploiements et recherchez le déploiement de VM à apprentissage profond.
    3. Dans la section VM Workstation, enregistrez les détails de la connexion par SSH à la machine virtuelle.
    4. Connectez-vous à la VM à apprentissage profond via SSH à l'aide des informations d'identification disponibles dans Automation Service Broker.
    5. Ajoutez les variables pgvector suivantes au fichier /opt/data/compose.env :
      POSTGRES_HOST_IP=pgvector_db_ip_address
      POSTGRES_PORT_NUMBER=5432
      POSTGRES_DB=pgvector_db_name
      POSTGRES_USER=pgvector_db_admin
      POSTGRES_PASSWORD=encoded_pgvector_db_admin_password
    6. Redémarrez l'application à conteneurs multiples NVIDIA RAG en exécutant les commandes suivantes.
      Par exemple, pour NVIDIA RAG 24.03 :
      cd /opt/data
      docker compose -f rag-docker-compose_v24.03/rag-app-text-chatbot.yaml down
      docker compose -f rag-docker-compose_v24.03/docker-compose-vectordb.yaml down
      docker compose -f rag-docker-compose_v24.03/docker-compose-vectordb.yaml up -d