add other format for vector

rag-service/pom.xml

@@ -137,6 +137,10 @@
 			<groupId>org.springframework.kafka</groupId>
 			<artifactId>spring-kafka</artifactId>
 		</dependency>
+		<dependency>
+			<groupId>org.springframework.ai</groupId>
+			<artifactId>spring-ai-tika-document-reader</artifactId>
+		</dependency>
 	</dependencies>
 	<dependencyManagement>
 		<dependencies>

rag-service/src/main/java/com/balex/rag/service/impl/UserDocumentServiceImpl.java

@@ -20,6 +20,7 @@ import org.springframework.retry.annotation.Retryable;
 import org.springframework.stereotype.Service;
 import org.springframework.web.multipart.MultipartFile;
 import org.springframework.web.servlet.mvc.method.annotation.SseEmitter;
+import org.springframework.ai.reader.tika.TikaDocumentReader;
 
 import java.io.IOException;
 import java.security.MessageDigest;
@@ -177,7 +178,13 @@ public class UserDocumentServiceImpl implements UserDocumentService {
             }
         };
 
-        List<Document> docs = new TextReader(resource).get();
+        List<Document> docs;
+        String ext = getExtensionOrTxt(filename);
+        if (ext.equals("txt")) {
+            docs = new TextReader(resource).get();
+        } else {
+            docs = new TikaDocumentReader(resource).get();
+        }
 
         TokenTextSplitter splitter = TokenTextSplitter.builder()
                 .withChunkSize(chunkSize)

rag-service/src/main/resources/application.properties

@@ -24,6 +24,9 @@ spring.cloud.consul.discovery.deregister-critical-service-after=1m
 management.endpoints.web.exposure.include=health,info
 management.endpoint.health.show-details=always
 
+spring.servlet.multipart.max-file-size=5MB
+spring.servlet.multipart.max-request-size=10MB
+
 spring.datasource.url=${SPRING_DATASOURCE_URL:jdbc:postgresql://localhost:5432/ragdb}
 spring.datasource.username=${SPRING_DATASOURCE_USERNAME:postgres}
 spring.datasource.password=${SPRING_DATASOURCE_PASSWORD:postgres}

rag-view/src/features/constants.js

@@ -29,12 +29,9 @@ export const PREFIX_UPLOAD_STREAM = "/upload-stream";
 export const FORM_DATA_FILES = "files";
 export const TYPE_WINDOW_UNDEFINED = "undefined";
 export const TOKEN_UNDEFINED = "undefined";
-export const MAX_FILE_SIZE_KB = 10;
+export const MAX_FILE_SIZE_KB = 2048;
 export const MAX_FILES_TO_UPLOAD = 3;
 export const DEFAULT_ERROR_STATUS = 500;
-export const FULFILLED_BUT_NOT_SUCCESS_ERROR_STATUS = 999;
-export const UNKNOWN_ERROR_AFTER_FULFILLED_QUERY =
-  "Unknown error after fulfilled query";
 export const UNKNOWN_ERROR = "Unknown error";
 export const STATUS_UNAUTHORIZED = "unauthorized";
 export const HTTP_STATUS_UNAUTHORIZED_CODE = 401;

rag-view/src/pages/UploadPage/components/FileSelector.jsx

@@ -28,7 +28,7 @@ const FileSelector = ({ disabled, onFilesChange }) => {
       <input
         ref={fileInputRef}
         type="file"
-        accept=".txt"
+        accept=".txt,.pdf,.docx,.doc,.md,.rtf,.html"
         multiple
         style={{ display: "none" }}
         onChange={onFilesChange}