ubuntu24.0离线安装Ollama和纯cpu版本以及对接Spring AI

一.官网下载 0.3.13版本

ollama离线安装包下载地址

二.将文件包上传至ubuntu服务器

三.下载安装脚本

curl -fsSL https://ollama.com/install.sh

修改远程拉取ollama代码为本地解压
源需要修改的脚本代码如下

if curl -I --silent --fail --location "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" >/dev/null ; then
    status "Downloading Linux ${ARCH} bundle"
    curl --fail --show-error --location --progress-bar \
        "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
        $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
    BUNDLE=1
    if [ "$OLLAMA_INSTALL_DIR/bin/ollama" != "$BINDIR/ollama" ] ; then
        status "Making ollama accessible in the PATH in $BINDIR"
        $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
    fi
else
    status "Downloading Linux ${ARCH} CLI"
    curl --fail --show-error --location --progress-bar -o "$TEMP_DIR/ollama"\
    "https://ollama.com/download/ollama-linux-${ARCH}${VER_PARAM}"
    $SUDO install -o0 -g0 -m755 $TEMP_DIR/ollama $OLLAMA_INSTALL_DIR/ollama
    BUNDLE=0
    if [ "$OLLAMA_INSTALL_DIR/ollama" != "$BINDIR/ollama" ] ; then
        status "Making ollama accessible in the PATH in $BINDIR"
        $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
    fi
fi

新改后代码

status "Downloading Linux ${ARCH} bundle"
#    curl --fail --show-error --location --progress-bar \
#        "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
$SUDO tar -xzf ./ollama-linux-amd64.tgz -C "$OLLAMA_INSTALL_DIR"
BUNDLE=1
if [ "$OLLAMA_INSTALL_DIR/bin/ollama" != "$BINDIR/ollama" ] ; then
    status "Making ollama accessible in the PATH in $BINDIR"
    $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
fi

四.剔除GPU相关下载ROCM等，纯CPU运行脚本

在题目3的基础上，又剔除了GPU部分，即从wls2注释将下面全部删除

完整版 离线基于CPU的运行脚本

#!/bin/sh
# This script installs Ollama on Linux.
# It detects the current operating system architecture and installs the appropriate version of Ollama.

set -eu

status() { echo ">>> $*" >&2; }
error() { echo "ERROR $*"; exit 1; }
warning() { echo "WARNING: $*"; }

TEMP_DIR=$(mktemp -d)
cleanup() { rm -rf $TEMP_DIR; }
trap cleanup EXIT

available() { command -v $1 >/dev/null; }
require() {
    local MISSING=''
    for TOOL in $*; do
        if ! available $TOOL; then
            MISSING="$MISSING $TOOL"
        fi
    done

    echo $MISSING
}

[ "$(uname -s)" = "Linux" ] || error 'This script is intended to run on Linux only.'

ARCH=$(uname -m)
case "$ARCH" in
    x86_64) ARCH="amd64" ;;
    aarch64|arm64) ARCH="arm64" ;;
    *) error "Unsupported architecture: $ARCH" ;;
esac

IS_WSL2=false

KERN=$(uname -r)
case "$KERN" in
    *icrosoft*WSL2 | *icrosoft*wsl2) IS_WSL2=true;;
    *icrosoft) error "Microsoft WSL1 is not currently supported. Please use WSL2 with 'wsl --set-version <distro> 2'" ;;
    *) ;;
esac

VER_PARAM="${OLLAMA_VERSION:+?version=$OLLAMA_VERSION}"

SUDO=
if [ "$(id -u)" -ne 0 ]; then
    # Running as root, no need for sudo
    if ! available sudo; then
        error "This script requires superuser permissions. Please re-run as root."
    fi

    SUDO="sudo"
fi

NEEDS=$(require curl awk grep sed tee xargs)
if [ -n "$NEEDS" ]; then
    status "ERROR: The following tools are required but missing:"
    for NEED in $NEEDS; do
        echo "  - $NEED"
    done
    exit 1
fi

for BINDIR in /usr/local/bin /usr/bin /bin; do
    echo $PATH | grep -q $BINDIR && break || continue
done
OLLAMA_INSTALL_DIR=$(dirname ${BINDIR})

status "Installing ollama to $OLLAMA_INSTALL_DIR"
$SUDO install -o0 -g0 -m755 -d $BINDIR
$SUDO install -o0 -g0 -m755 -d "$OLLAMA_INSTALL_DIR"
status "Downloading Linux ${ARCH} bundle"
#    curl --fail --show-error --location --progress-bar \
#        "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
$SUDO tar -xzf ./ollama-linux-amd64.tgz -C "$OLLAMA_INSTALL_DIR"
BUNDLE=1
if [ "$OLLAMA_INSTALL_DIR/bin/ollama" != "$BINDIR/ollama" ] ; then
    status "Making ollama accessible in the PATH in $BINDIR"
    $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
fi



install_success() {
    status 'The Ollama API is now available at 127.0.0.1:11434.'
    status 'Install complete. Run "ollama" from the command line.'
}
trap install_success EXIT

# Everything from this point onwards is optional.

configure_systemd() {
    if ! id ollama >/dev/null 2>&1; then
        status "Creating ollama user..."
        $SUDO useradd -r -s /bin/false -U -m -d /usr/share/ollama ollama
    fi
    if getent group render >/dev/null 2>&1; then
        status "Adding ollama user to render group..."
        $SUDO usermod -a -G render ollama
    fi
    if getent group video >/dev/null 2>&1; then
        status "Adding ollama user to video group..."
        $SUDO usermod -a -G video ollama
    fi

    status "Adding current user to ollama group..."
    $SUDO usermod -a -G ollama $(whoami)

    status "Creating ollama systemd service..."
    cat <<EOF | $SUDO tee /etc/systemd/system/ollama.service >/dev/null
[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=$BINDIR/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=$PATH"

[Install]
WantedBy=default.target
EOF
    SYSTEMCTL_RUNNING="$(systemctl is-system-running || true)"
    case $SYSTEMCTL_RUNNING in
        running|degraded)
            status "Enabling and starting ollama service..."
            $SUDO systemctl daemon-reload
            $SUDO systemctl enable ollama

            start_service() { $SUDO systemctl restart ollama; }
            trap start_service EXIT
            ;;
    esac
}

if available systemctl; then
    configure_systemd
fi

install_success

五.ollama常用命令

# 关闭ollama服务
service ollama stop

ollama serve # 启动ollama
ollama create # 从模型文件创建模型
ollama show  # 显示模型信息
ollama run qwen2.5:3b-instruct-q4_K_M  # 运行模型，会先自动下载模型
ollama pull  # 从注册仓库中拉取模型
ollama push  # 将模型推送到注册仓库
ollama list  # 列出已下载模型
ollama ps  # 列出正在运行的模型
ollama cp  # 复制模型
ollama rm  # 删除模型

六. 远程测试

建议生产不开启，因为没有token等限制，必须注意接口调用安全
1.首先停止ollama服务：

systemctl stop ollama

2.修改ollama的service文件：

vim /etc/systemd/system/ollama.service

3.新增Environment="OLLAMA_HOST=0.0.0.0:11434"

[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=/usr/local/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin"
Environment="OLLAMA_HOST=0.0.0.0:11434"

[Install]
WantedBy=default.target

4. 启动ollama

systemctl daemon-reload
systemctl start ollama
# 若启动失败可以使用 ollama serve测试

七.对接spring AI

    <dependencyManagement>
        <dependencies>
            <!--spring boot依赖-->
            <dependency>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-dependencies</artifactId>
                <version>${spring.boot.version}</version>
                <type>pom</type>
                <scope>runtime</scope>
            </dependency>
            <dependency>
                <groupId>org.springframework.ai</groupId>
                <artifactId>spring-ai-bom</artifactId>
                <version>1.0.0-SNAPSHOT</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>
    
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.springframework.ai/spring-ai-ollama-spring-boot-starter -->
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
        </dependency>

    </dependencies>

    <repositories>
        <repository>
            <id>spring-milestones</id>
            <name>Spring Milestones</name>
            <url>https://repo.spring.io/milestone</url>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </repository>
        <repository>
            <id>spring-snapshots</id>
            <name>Spring Snapshots</name>
            <url>https://repo.spring.io/snapshot</url>
            <releases>
                <enabled>false</enabled>
            </releases>
        </repository>
    </repositories>

若以上代码无法拉取，可能被setting.xml全局拦截到镜像站。 以上spring ai还未发布到maven中央仓库请参考maven多仓库私库模板配置

spring:
  application:
    name: spring-ai-ollama
  ai:
    ollama:
      base-url: http://192.168.200.94:11434
      chat:
        # 为了使模型输入内容拥有更多的多样性或随机性，应当增加temperature。
        #在 temperature 非零的情况下，从 0.95 左右的 top-p（或 250 左右的 top-k ）开始，根据需要降低 temperature。
        # 如果有太多无意义的内容、垃圾内容或产生幻觉，应当降低 temperature 和 降低top-p/top-k。
        # 如果 temperature 很高而模型输出内容的多样性却很低，应当增加top-p/top-k。
        # 为了获得更多样化的主题，应当增加存在惩罚值。
        # 为了获得更多样化且更少重复内容的模型输出，应当增加频率惩罚。
        options:
          # 配置文件指定时，现在程序中指定的模型，程序没有指定模型在对应查找配置中的模型
          #          model: qwen:0.5b-chat
          model: qwen2.5:3b-instruct-q4_K_M
          # 支持的最大字符数
          max_tokens: 2048
          # 温度值越高，准确率下降，温度值越低，准确率上升
          # 对于每个提示语只需要单个答案：零。
          #对于每个提示语需要多个答案：非零。
          temperature: 0.4
          # 随机采样 值越大，随机性越高
          # 在 temperature 为零的情况下：输出不受影响。
          # 在 temperature 不为零的情况下：非零。
          top_p: 0.2
          # 贪心解码 值越大，随机性越高
          top-k: 40
          # 频率惩罚 让token每次在文本中出现都受到惩罚。这可以阻止重复使用相同的token/单词/短语，同时也会使模型讨论的主题更加多样化，更频繁地更换主题
          # 当问题仅存在一个正确答案时：零。
          # 当问题存在多个正确答案时：可自由选择。
          frequency-penalty: 0
          # 存在惩罚 如果一个token已经在文本中出现过，就会受到惩罚 使其讨论的主题更加多样化，话题变化更加频繁，而不会明显抑制常用词的重复
          presence-penalty: 0

@RestController
public class QianWenController {

    @Resource
    private OllamaChatModel ollamaChatModel;

    @RequestMapping(value = "/ai/ollama")
    public Object ollama(@RequestParam(value = "msg") String msg) {
        String called = ollamaChatModel.call(msg);
        System.out.println(called);
        return called;
    }

    @RequestMapping(value = "/ai/ollama2")
    public Map<String, Object> ollama2(@RequestParam(value = "msg") String msg) {
        Map<String, Object> map = new HashMap<String, Object>();
        long start = System.currentTimeMillis();
        ChatResponse chatResponse = ollamaChatModel.call(new Prompt(msg, OllamaOptions.create().
                withModel("qwen2.5:3b-instruct-q4_K_M")//使用哪个大模型
                .withTemperature(0.4D)));//温度，温度值越高，准确率下降，温度值越低，准确率上升
        String content = chatResponse.getResult().getOutput().getContent();
        long end = System.currentTimeMillis();
        map.put("content", content);
        map.put("time", (end - start) / 1000);
        return map;
    }

    @RequestMapping(value = "/ai/stream",produces = MediaType.TEXT_EVENT_STREAM_VALUE)
    public Flux<String>  stream(@RequestParam(value = "msg") String msg) {
        return ollamaChatModel
                .stream(new Prompt(msg))
                .flatMapSequential(chunk -> Flux.just(chunk.getResult().getOutput().getContent()));
    }
}