【新增】AI 知识库:支持读取 PDF、DOC/DOCX、PPT/PPTX 和 HTML等格式

This commit is contained in:
xiaoxin 2024-08-05 14:00:35 +08:00
parent 2a984504d9
commit d698ef70b5
3 changed files with 44 additions and 2 deletions

View File

@ -3,7 +3,7 @@ package cn.iocoder.yudao.module.ai.service.knowledge;
import jakarta.annotation.Resource;
import lombok.extern.slf4j.Slf4j;
import org.springframework.ai.document.Document;
import org.springframework.ai.reader.TextReader;
import org.springframework.ai.reader.tika.TikaDocumentReader;
import org.springframework.ai.transformer.splitter.TokenTextSplitter;
import org.springframework.ai.vectorstore.RedisVectorStore;
import org.springframework.beans.factory.annotation.Value;
@ -34,7 +34,7 @@ public class DocServiceImpl implements DocService {
public void embeddingDoc() {
// 读取文件
org.springframework.core.io.Resource file = data;
TextReader loader = new TextReader(file);
TikaDocumentReader loader = new TikaDocumentReader(file);
List<Document> documents = loader.get();
// 文档分段
List<Document> segments = tokenTextSplitter.apply(documents);

View File

@ -39,11 +39,17 @@
<artifactId>spring-ai-stability-ai-spring-boot-starter</artifactId>
<version>${spring-ai.version}</version>
</dependency>
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-transformers-spring-boot-starter</artifactId>
<version>${spring-ai.version}</version>
</dependency>
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-tika-document-reader</artifactId>
<version>${spring-ai.version}</version>
</dependency>
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-redis-store</artifactId>

View File

@ -10,11 +10,18 @@ import cn.iocoder.yudao.framework.ai.core.model.xinghuo.XingHuoChatModel;
import cn.iocoder.yudao.framework.ai.core.model.xinghuo.XingHuoChatOptions;
import com.alibaba.cloud.ai.tongyi.TongYiAutoConfiguration;
import lombok.extern.slf4j.Slf4j;
import org.springframework.ai.autoconfigure.vectorstore.redis.RedisVectorStoreProperties;
import org.springframework.ai.document.MetadataMode;
import org.springframework.ai.transformer.splitter.TokenTextSplitter;
import org.springframework.ai.transformers.TransformersEmbeddingModel;
import org.springframework.ai.vectorstore.RedisVectorStore;
import org.springframework.boot.autoconfigure.AutoConfiguration;
import org.springframework.boot.autoconfigure.condition.ConditionalOnProperty;
import org.springframework.boot.autoconfigure.data.redis.RedisProperties;
import org.springframework.boot.context.properties.EnableConfigurationProperties;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Import;
import redis.clients.jedis.JedisPooled;
/**
* 芋道 AI 自动配置
@ -73,4 +80,33 @@ public class YudaoAiAutoConfiguration {
return new SunoApi(yudaoAiProperties.getSuno().getBaseUrl());
}
// ========== rag 相关 ==========
@Bean
public TransformersEmbeddingModel transformersEmbeddingClient() {
return new TransformersEmbeddingModel(MetadataMode.EMBED);
}
/**
* 我们启动有加载很多 Embedding 模型不晓得取哪个好 new TransformersEmbeddingModel
*/
@Bean
public RedisVectorStore vectorStore(TransformersEmbeddingModel transformersEmbeddingModel, RedisVectorStoreProperties properties,
RedisProperties redisProperties) {
var config = RedisVectorStore.RedisVectorStoreConfig.builder()
.withIndexName(properties.getIndex())
.withPrefix(properties.getPrefix())
.build();
RedisVectorStore redisVectorStore = new RedisVectorStore(config, transformersEmbeddingModel,
new JedisPooled(redisProperties.getHost(), redisProperties.getPort()),
properties.isInitializeSchema());
redisVectorStore.afterPropertiesSet();
return redisVectorStore;
}
@Bean
public TokenTextSplitter tokenTextSplitter() {
return new TokenTextSplitter(500, 100, 5, 10000, true);
}
}