1.5B

ollama run https://www.modelscope.cn/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF

pom

注意不能用阿里云的MAVEN

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <parent>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-parent</artifactId>
    <version>3.4.4</version>
    <relativePath/> <!-- lookup parent from repository -->
  </parent>
  <groupId>com.fan</groupId>
  <artifactId>ollamaV2</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <name>ollamaV2</name>
  <description>ollamaV2</description>
  <url/>
  <licenses>
    <license/>
  </licenses>
  <developers>
    <developer/>
  </developers>
  <scm>
    <connection/>
    <developerConnection/>
    <tag/>
    <url/>
  </scm>
  <properties>
    <java.version>17</java.version>
    <spring-ai.version>1.0.0-M6</spring-ai.version>
  </properties>
  <dependencies>
    <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter-web</artifactId>
    </dependency>
    <dependency>
      <groupId>org.springframework.ai</groupId>
      <artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
    </dependency>

    <dependency>
      <groupId>org.projectlombok</groupId>
      <artifactId>lombok</artifactId>
      <optional>true</optional>
    </dependency>
    <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter-test</artifactId>
      <scope>test</scope>
    </dependency>
  </dependencies>
  <dependencyManagement>
    <dependencies>
      <dependency>
        <groupId>org.springframework.ai</groupId>
        <artifactId>spring-ai-bom</artifactId>
        <version>${spring-ai.version}</version>
        <type>pom</type>
        <scope>import</scope>
      </dependency>
    </dependencies>
  </dependencyManagement>

  <build>
    <plugins>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-compiler-plugin</artifactId>
        <configuration>
          <annotationProcessorPaths>
            <path>
              <groupId>org.projectlombok</groupId>
              <artifactId>lombok</artifactId>
            </path>
          </annotationProcessorPaths>
        </configuration>
      </plugin>
      <plugin>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-maven-plugin</artifactId>
        <configuration>
          <excludes>
            <exclude>
              <groupId>org.projectlombok</groupId>
              <artifactId>lombok</artifactId>
            </exclude>
          </excludes>
        </configuration>
      </plugin>
    </plugins>
  </build>

</project>

配置

spring:
  ai:
    ollama:
      base-url: http://localhost:11434
      chat:
        options:
          model: www.modelscope.cn/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:latest

config

package com.fan.config;

import lombok.RequiredArgsConstructor;
import org.springframework.ai.chat.client.ChatClient;
import org.springframework.ai.chat.memory.ChatMemory;
import org.springframework.ai.chat.memory.InMemoryChatMemory;
import org.springframework.ai.ollama.OllamaChatModel;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;

@Configuration
@RequiredArgsConstructor
public class AiConfig {

    final OllamaChatModel model;

    @Bean
    public ChatClient chatClient() {
        return ChatClient.builder(model)
//                .defaultSystem("You are a helpful assistant.")
                .build();
    }

    @Bean
    public ChatMemory chatMemory() {
        return new InMemoryChatMemory();
    }

}

接口

package com.fan.controller;

import lombok.RequiredArgsConstructor;
import org.springframework.ai.chat.client.ChatClient;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.bind.annotation.RestController;

@RequiredArgsConstructor
@RestController
public class ChatController {

    final ChatClient chatClient;

    @RequestMapping("/chat")
    public String chat(@RequestParam(value = "msg") String msg) {
        try {
            return chatClient.prompt().user(msg).call().content();
        } catch (Exception e) {
            e.printStackTrace();
            return e.getMessage();
        }
    }

}

模型向量化

ollama run https://www.modelscope.cn/Embedding-GGUF/all-MiniLM-L12-v2-GGUF

数据库

https://www.postgresql.org/download/linux/ubuntu/

安装教程：https://blog.csdn.net/weixin_44594317/article/details/144029200

加pgvector

sudo apt install postgresql-server-dev-16 build-essential
git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
cd pgvector
# 编译
make

# 安装到 PostgreSQL 扩展目录
sudo make install

# 连接到目标数据库（以 postgres 用户为例）
sudo -u postgres psql -d your_database_name

# 创建扩展
CREATE EXTENSION vector;

# 验证安装
\dx

启用 uuid-ossp 扩展
sudo -u postgres psql -d mydb
CREATE EXTENSION IF NOT EXISTS "uuid-ossp";
\df uuid_generate_v4

sql

create table vector_store (
    id uuid default uuid_generate_v4() not null primary key,
    content text,
    metadata jsonb,
    embedding vector(384)
);