feat: 流式应答ui

ai-rag-app/pom.xml

@@ -29,16 +29,16 @@
 <!--            <artifactId>spring-ai-openai-spring-boot-starter</artifactId>-->
 <!--        </dependency>-->
 
-        <dependency>
+<!--        <dependency>-->
-            <groupId>org.springframework.ai</groupId>
+<!--            <groupId>org.springframework.ai</groupId>-->
-            <artifactId>spring-ai-tika-document-reader</artifactId>
+<!--            <artifactId>spring-ai-tika-document-reader</artifactId>-->
-        </dependency>
+<!--        </dependency>-->
 
-        <!-- 处理知识库：向量库 -->
+<!--        &lt;!&ndash; 处理知识库：向量库 &ndash;&gt;-->
-        <dependency>
+<!--        <dependency>-->
-            <groupId>org.springframework.ai</groupId>
+<!--            <groupId>org.springframework.ai</groupId>-->
-            <artifactId>spring-ai-pgvector-store-spring-boot-starter</artifactId>
+<!--            <artifactId>spring-ai-pgvector-store-spring-boot-starter</artifactId>-->
-        </dependency>
+<!--        </dependency>-->
 
         <!-- 使用ollama的api -->
         <dependency>

ai-rag-app/src/main/java/com/storm/dev/config/OllamaConfig.java

@@ -1,16 +1,10 @@
 package com.storm.dev.config;
 
 import org.springframework.ai.ollama.OllamaChatClient;
-import org.springframework.ai.ollama.OllamaEmbeddingClient;
 import org.springframework.ai.ollama.api.OllamaApi;
-import org.springframework.ai.ollama.api.OllamaOptions;
-import org.springframework.ai.transformer.splitter.TokenTextSplitter;
-import org.springframework.ai.vectorstore.PgVectorStore;
-import org.springframework.ai.vectorstore.SimpleVectorStore;
 import org.springframework.beans.factory.annotation.Value;
 import org.springframework.context.annotation.Bean;
 import org.springframework.context.annotation.Configuration;
-import org.springframework.jdbc.core.JdbcTemplate;
 
 /**
  * 注入OllamaApi、OllamaChatClient对象
@@ -30,24 +24,4 @@ public class OllamaConfig {
         return new OllamaChatClient(ollamaApi);
     }
 
-    @Bean
-    public TokenTextSplitter tokenTextSplitter() {
-        return new TokenTextSplitter();
-    }
-
-    @Bean
-    public SimpleVectorStore simpleVectorStore(OllamaApi ollamaApi) {
-        OllamaEmbeddingClient embeddingClient = new OllamaEmbeddingClient(ollamaApi);
-        embeddingClient.withDefaultOptions(OllamaOptions.create().withModel("nomic-embed-text"));
-        return new SimpleVectorStore(embeddingClient);
-    }
-
-    @Bean
-    public PgVectorStore pgVectorStore(OllamaApi ollamaApi, JdbcTemplate jdbcTemplate) {
-        OllamaEmbeddingClient embeddingClient = new OllamaEmbeddingClient(ollamaApi);
-        embeddingClient.withDefaultOptions(OllamaOptions.create().withModel("nomic-embed-text"));
-        return new PgVectorStore(jdbcTemplate, embeddingClient);
-    }
-
-
 }

ai-rag-app/src/main/resources/application-dev.yml

@@ -2,25 +2,16 @@ server:
   port: 8090
 
 spring:
-  datasource:
-    driver-class-name: org.postgresql.Driver
-    username: postgres
-    password: postgres
-    url: jdbc:postgresql://192.168.109.134:15432/ai-rag-knowledge
-    type: com.zaxxer.hikari.HikariDataSource
   ai:
     ollama:
-      base-url: http://192.168.109.134:11434
+      base-url: http://117.72.202.142:11434
-      embedding:
+
-        options:
-          num-batch: 512
-        model: nomic-embed-text
 # Redis
 redis:
   sdk:
     config:
-      host: 127.0.0.1
+      host: 117.72.202.142
-      port: 6379
+      port: 16379
       pool-size: 10
       min-idle-size: 5
       idle-timeout: 30000

ai-rag-app/src/test/java/com/storm/dev/text/RAGApiTest.java

@@ -1,90 +0,0 @@
-package com.storm.dev.text;
-
-import com.alibaba.fastjson.JSON;
-import jakarta.annotation.Resource;
-import lombok.extern.slf4j.Slf4j;
-import org.junit.Test;
-import org.junit.runner.RunWith;
-import org.springframework.ai.chat.ChatResponse;
-import org.springframework.ai.chat.messages.Message;
-import org.springframework.ai.chat.messages.UserMessage;
-import org.springframework.ai.chat.prompt.Prompt;
-import org.springframework.ai.chat.prompt.SystemPromptTemplate;
-import org.springframework.ai.document.Document;
-import org.springframework.ai.ollama.OllamaChatClient;
-import org.springframework.ai.ollama.api.OllamaApi;
-import org.springframework.ai.ollama.api.OllamaOptions;
-import org.springframework.ai.reader.tika.TikaDocumentReader;
-import org.springframework.ai.transformer.splitter.TokenTextSplitter;
-import org.springframework.ai.vectorstore.PgVectorStore;
-import org.springframework.ai.vectorstore.SearchRequest;
-import org.springframework.ai.vectorstore.SimpleVectorStore;
-import org.springframework.boot.test.context.SpringBootTest;
-import org.springframework.test.context.junit4.SpringRunner;
-
-import java.util.ArrayList;
-import java.util.List;
-import java.util.Map;
-import java.util.stream.Collectors;
-
-/**
- * @author: lyd
- * @date: 2026/1/14 21:47
- */
-@Slf4j
-@RunWith(SpringRunner.class)
-@SpringBootTest
-public class RAGApiTest {
-    @Resource
-    private OllamaChatClient ollamaChatClient;
-    @Resource
-    private TokenTextSplitter tokenTextSplitter;
-    @Resource
-    private SimpleVectorStore simpleVectorStore;
-    @Resource
-    private PgVectorStore pgVectorStore;
-
-    @Test
-    public void upload() {
-        // 上传
-        TikaDocumentReader reader = new TikaDocumentReader("./data/file.text");
-        List<Document> documents = reader.get();
-        List<Document> documentSplitterList = tokenTextSplitter.apply(documents);
-        // 打标
-        documents.forEach(document -> document.getMetadata().put("knowledge", "德德"));
-        documentSplitterList.forEach(document -> document.getMetadata().put("knowledge", "德德"));
-
-        pgVectorStore.accept(documentSplitterList);
-        log.info("上传完成!");
-    }
-
-    @Test
-    public void chat() {
-        // 构建提问
-        String message = "李永德，哪年出生的";
-
-        // 构建推理模板
-        String SYSTEM_PROMPT = """
-                Use the information from the DOCUMENTS section to provide accurate answers but act as if you knew this information innately.
-                If unsure, simply state that you don't know.
-                Another thing you need to note is that your reply must be in Chinese!
-                DOCUMENTS:
-                    {documents}
-                """;
-        // 读取向量库信息
-        SearchRequest request = SearchRequest.query(message).withTopK(5).withFilterExpression("knowledge == '德德'");
-        // 相似性搜索
-        List<Document> documents = pgVectorStore.similaritySearch(request);
-        String documentsCollectors = documents.stream().map(Document::getContent).collect(Collectors.joining());
-
-        // 推理：RAG
-        Message ragMessage = new SystemPromptTemplate(SYSTEM_PROMPT).createMessage(Map.of("documents", documentsCollectors));
-        ArrayList<Message> messages = new ArrayList<>();
-        messages.add(new UserMessage(message));
-        messages.add(ragMessage);
-
-        // 提问
-        ChatResponse chatResponse = ollamaChatClient.call(new Prompt(messages, OllamaOptions.create().withModel("deepseek-r1:7b")));
-        log.info("测试结果:{}", JSON.toJSONString(chatResponse));
-    }
-}

ai-rag-app/src/test/resources/data/file.text

@@ -1 +0,0 @@
-李永德，1999年12月31日出生，福建泉州人。

ai-rag-trigger/src/main/java/com/storm/dev/trigger/http/OllamaController.java

@@ -22,7 +22,7 @@ public class OllamaController implements IAiService {
     private OllamaChatClient chatClient;
 
     /**
-     * http://localhost:8090/api/v1/ollama/generate?model=deepseek-r1:7b&message=1+1
+     * http://localhost:8090/api/v1/ollama/generate?model=deepseek-r1:1.5b&message=1+1
      */
     @GetMapping("generate")
     @Override
@@ -31,7 +31,7 @@ public class OllamaController implements IAiService {
     }
 
     /**
-     * http://localhost:8090/api/v1/ollama/generate_stream?model=deepseek-r1:7b&message=hi
+     * http://localhost:8090/api/v1/ollama/generate_stream?model=deepseek-r1:1.5b&message=hi
      */
     @GetMapping("generate_stream")
     @Override

docs/docker-compose-environment-aliyun2.yml

@@ -1,43 +0,0 @@
-# docker-compose -f docker-compose-environment-aliyun.yml up -d
-version: '3'
-services:
-  # 对话模型
-  # ollama pull deepseek-r1:1.5b
-  # 运行模型
-  # ollama run deepseek-r1:1.5b
-  # 联网模型
-  # ollama pull nomic-embed-text
-  ollama:
-    image: registry.cn-hangzhou.aliyuncs.com/xfg-studio/ollama:0.5.10
-    container_name: ollama
-    restart: unless-stopped
-    ports:
-      - "11434:11434"
-  vector_db:
-    image: registry.cn-hangzhou.aliyuncs.com/xfg-studio/pgvector:v0.5.0
-    container_name: vector_db
-    restart: always
-    environment:
-      - POSTGRES_USER=postgres
-      - POSTGRES_PASSWORD=postgres
-      - POSTGRES_DB=ai-rag-knowledge
-      - PGPASSWORD=postgres
-    volumes:
-      - ./pgvector/sql/init.sql:/docker-entrypoint-initdb.d/init.sql
-    logging:
-      options:
-        max-size: 10m
-        max-file: "3"
-    ports:
-      - '15432:5432'
-    healthcheck:
-      test: "pg_isready -U postgres -d ai-rag-knowledge"
-      interval: 2s
-      timeout: 20s
-      retries: 10
-    networks:
-      - my-network
-
-networks:
-  my-network:
-    driver: bridge

docs/nginx/html/ai-case-04.html

@@ -69,7 +69,7 @@
             addMessage('<span class="animate-pulse">▍</span>');
 
             // 构建API URL
-            const apiUrl = `http://localhost:8090/api/v1/ollama/generate_stream?model=deepseek-r1:7b&message=${encodeURIComponent(message)}`;
+            const apiUrl = `http://localhost:8090/api/v1/ollama/generate_stream?model=deepseek-r1:1.5b&message=${encodeURIComponent(message)}`;
 
             // 使用EventSource接收流式响应
             const eventSource = new EventSource(apiUrl);

docs/nginx/html/index.html

@@ -56,7 +56,7 @@
 
 <script>
   const API_BASE = 'http://localhost:8090/api/v1/ollama/generate_stream';
-  const MODEL = 'deepseek-r1:7b';
+  const MODEL = 'deepseek-r1:1.5b';
   const chatContainer = document.getElementById('chatContainer');
   const messageInput = document.getElementById('messageInput');
   const sendButton = document.getElementById('sendButton');