Sie können eine Deep Learning-VM mit einer NVIDIA RAG-Arbeitslast unter Verwendung einer PostgreSQL-Datenbank vom Typ „pgvector“ bereitstellen, die von VMware Data Services Manager verwaltet wird.
Voraussetzungen
- Stellen Sie sicher, dass VMware Private AI Foundation with NVIDIA konfiguriert ist. Weitere Informationen finden Sie unter Vorbereiten von VMware Cloud Foundation für die Bereitstellung von Private AI-Arbeitslasten.
- Bereitstellen einer Vektordatenbank in VMware Private AI Foundation with NVIDIA.
Prozedur
- Wenn Sie als Datenwissenschaftler die Deep Learning-VM mithilfe eines Katalogelements in VMware Aria Automation bereitstellen, geben Sie die Details der PostgreSQL-Datenbank „pgvector“ an, nachdem Sie die virtuelle Maschine bereitgestellt haben.
- Bereitstellen einer RAG-Workstation in VMware Aria Automation.
- Navigieren Sie zu und suchen Sie die Bereitstellung der Deep Learning-VM.
- Speichern Sie im Abschnitt Workstation-VM die Details für die SSH-Anmeldung bei der virtuellen Maschine.
- Melden Sie sich bei der Deep Learning-VM über SSH mit den in Automation Service Broker verfügbaren Anmeldedaten an.
- Fügen Sie die folgenden pgvector-Variablen zur Datei /opt/data/compose.env hinzu:
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
- Starten Sie die NVIDIA RAG-Multi-Container-Anwendung neu, indem Sie die folgenden Befehle ausführen.
Beispielsweise für 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
- Wenn Sie als DevOps-Ingenieur die Deep Learning-VM für einen Datenwissenschaftler direkt auf dem vSphere-Cluster oder mithilfe des Befehls kubectl bereitstellen, erstellen Sie ein cloud-init-Skript und stellen Sie die Deep Learning-VM bereit.
- Erstellen Sie ein cloud-init-Skript für NVIDIA RAG und die von Ihnen erstellte pgvector PostgreSQL-Datenbank.
Sie können die anfängliche Version des cloud-init-Skripts für NVIDIA RAG ändern. Beispielsweise für NVIDIA RAG 24.03 und eine pgvector-PostgreSQL-Datenbank mit Verbindungsdetails
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 set -eu source /opt/dlvm/utils.sh trap 'error_exit "Unexpected error occurs at dl workload"' ERR set_proxy "http" "https" 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}:${RAG_VERSION}" EMBED_MODEL_URI="${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 LLM_MODEL_URI="${LLM_REPO_NAME}/${LLM_NAME}:${LLM_VERSION}" 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 - path: /opt/dlvm/utils.sh permissions: '0755' content: | #!/bin/bash error_exit() { echo "Error: $1" >&2 vmtoolsd --cmd "info-set guestinfo.vmservice.bootstrap.condition false, DLWorkloadFailure, $1" exit 1 } check_protocol() { local proxy_url=$1 shift local supported_protocols=("$@") if [[ -n "${proxy_url}" ]]; then local protocol=$(echo "${proxy_url}" | awk -F '://' '{if (NF > 1) print $1; else print ""}') if [ -z "$protocol" ]; then echo "No specific protocol provided. Skipping protocol check." return 0 fi local protocol_included=false for var in "${supported_protocols[@]}"; do if [[ "${protocol}" == "${var}" ]]; then protocol_included=true break fi done if [[ "${protocol_included}" == false ]]; then error_exit "Unsupported protocol: ${protocol}. Supported protocols are: ${supported_protocols[*]}" fi fi } # $@: list of supported protocols set_proxy() { local supported_protocols=("$@") CONFIG_JSON_BASE64=$(grep 'config-json' /opt/dlvm/ovf-env.xml | sed -n 's/.*oe:value="\([^"]*\).*/\1/p') CONFIG_JSON=$(echo ${CONFIG_JSON_BASE64} | base64 --decode) HTTP_PROXY_URL=$(echo "${CONFIG_JSON}" | jq -r '.http_proxy // empty') HTTPS_PROXY_URL=$(echo "${CONFIG_JSON}" | jq -r '.https_proxy // empty') if [[ $? -ne 0 || (-z "${HTTP_PROXY_URL}" && -z "${HTTPS_PROXY_URL}") ]]; then echo "Info: The config-json was parsed, but no proxy settings were found." return 0 fi check_protocol "${HTTP_PROXY_URL}" "${supported_protocols[@]}" check_protocol "${HTTPS_PROXY_URL}" "${supported_protocols[@]}" if ! grep -q 'http_proxy' /etc/environment; then echo "export http_proxy=${HTTP_PROXY_URL} export https_proxy=${HTTPS_PROXY_URL} export HTTP_PROXY=${HTTP_PROXY_URL} export HTTPS_PROXY=${HTTPS_PROXY_URL} export no_proxy=localhost,127.0.0.1" >> /etc/environment source /etc/environment fi # Configure Docker to use a proxy mkdir -p /etc/systemd/system/docker.service.d echo "[Service] Environment=\"HTTP_PROXY=${HTTP_PROXY_URL}\" Environment=\"HTTPS_PROXY=${HTTPS_PROXY_URL}\" Environment=\"NO_PROXY=localhost,127.0.0.1\"" > /etc/systemd/system/docker.service.d/proxy.conf systemctl daemon-reload systemctl restart docker echo "Info: docker and system environment are now configured to use the proxy settings" }
- Codieren Sie das cloud-init-Skript in das base64-Format.
Sie verwenden ein base64-Codierungstool, z. B. https://decode64base.com/, um die codierte Version Ihres cloud-init-Skripts zu generieren.
- Stellen Sie die Deep Learning-VM bereit und übergeben Sie den base64-Wert des cloud-init-Skripts an den Eingabeparameter
user-data
.
- Erstellen Sie ein cloud-init-Skript für NVIDIA RAG und die von Ihnen erstellte pgvector PostgreSQL-Datenbank.