You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
285 lines
10 KiB
XML
285 lines
10 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!--
|
|
Document Intelligence Platform
|
|
Author: Martin.Schweitzer@procon.co.at and claude.ai
|
|
|
|
Spring Boot application for processing EU eForms public procurement notices.
|
|
Features:
|
|
- Apache Camel directory watching and processing
|
|
- PostgreSQL storage with XML and vector columns
|
|
- Async vectorization using sentence-transformers
|
|
- REST API for structured and semantic search
|
|
-->
|
|
<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>3.3.5</version>
|
|
<relativePath/>
|
|
</parent>
|
|
|
|
<groupId>at.procon.dip</groupId>
|
|
<artifactId>document-intelligence-platform</artifactId>
|
|
<version>1.0.0-SNAPSHOT</version>
|
|
<name>Document Intelligence Platform</name>
|
|
<description>Generic document ingestion, normalization, and semantic search platform with TED support</description>
|
|
|
|
<properties>
|
|
<java.version>21</java.version>
|
|
<camel.version>4.8.1</camel.version>
|
|
<eforms-sdk.version>1.13.1</eforms-sdk.version>
|
|
<pgvector.version>0.1.6</pgvector.version>
|
|
<djl.version>0.30.0</djl.version>
|
|
</properties>
|
|
|
|
<dependencies>
|
|
<!-- Spring Boot Core -->
|
|
<dependency>
|
|
<groupId>org.springframework.boot</groupId>
|
|
<artifactId>spring-boot-starter-web</artifactId>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.springframework.boot</groupId>
|
|
<artifactId>spring-boot-starter-data-jpa</artifactId>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.springframework.boot</groupId>
|
|
<artifactId>spring-boot-starter-validation</artifactId>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.springframework.boot</groupId>
|
|
<artifactId>spring-boot-starter-actuator</artifactId>
|
|
</dependency>
|
|
|
|
<!-- Apache Camel -->
|
|
<dependency>
|
|
<groupId>org.apache.camel.springboot</groupId>
|
|
<artifactId>camel-spring-boot-starter</artifactId>
|
|
<version>${camel.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.camel</groupId>
|
|
<artifactId>camel-file</artifactId>
|
|
<version>${camel.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.camel</groupId>
|
|
<artifactId>camel-jaxb</artifactId>
|
|
<version>${camel.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.camel</groupId>
|
|
<artifactId>camel-validator</artifactId>
|
|
<version>${camel.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.camel</groupId>
|
|
<artifactId>camel-http</artifactId>
|
|
<version>${camel.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.camel</groupId>
|
|
<artifactId>camel-bean</artifactId>
|
|
<version>${camel.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.camel</groupId>
|
|
<artifactId>camel-jackson</artifactId>
|
|
<version>${camel.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.camel</groupId>
|
|
<artifactId>camel-mail</artifactId>
|
|
<version>${camel.version}</version>
|
|
</dependency>
|
|
|
|
<!-- JSoup for HTML to Text conversion -->
|
|
<dependency>
|
|
<groupId>org.jsoup</groupId>
|
|
<artifactId>jsoup</artifactId>
|
|
<version>1.18.1</version>
|
|
</dependency>
|
|
|
|
<!-- Apache PDFBox for PDF text extraction -->
|
|
<dependency>
|
|
<groupId>org.apache.pdfbox</groupId>
|
|
<artifactId>pdfbox</artifactId>
|
|
<version>3.0.3</version>
|
|
</dependency>
|
|
|
|
<!-- PostgreSQL -->
|
|
<dependency>
|
|
<groupId>org.postgresql</groupId>
|
|
<artifactId>postgresql</artifactId>
|
|
<scope>runtime</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>com.pgvector</groupId>
|
|
<artifactId>pgvector</artifactId>
|
|
<version>${pgvector.version}</version>
|
|
</dependency>
|
|
|
|
<!-- EU eForms SDK for schema validation -->
|
|
<dependency>
|
|
<groupId>eu.europa.ted.eforms</groupId>
|
|
<artifactId>eforms-sdk</artifactId>
|
|
<version>${eforms-sdk.version}</version>
|
|
</dependency>
|
|
|
|
<!-- XML Processing -->
|
|
<dependency>
|
|
<groupId>jakarta.xml.bind</groupId>
|
|
<artifactId>jakarta.xml.bind-api</artifactId>
|
|
<version>4.0.2</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.glassfish.jaxb</groupId>
|
|
<artifactId>jaxb-runtime</artifactId>
|
|
<version>4.0.5</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>com.sun.xml.bind</groupId>
|
|
<artifactId>jaxb-impl</artifactId>
|
|
<version>4.0.5</version>
|
|
<scope>runtime</scope>
|
|
</dependency>
|
|
|
|
<!-- DJL (Deep Java Library) for sentence-transformers integration -->
|
|
<dependency>
|
|
<groupId>ai.djl</groupId>
|
|
<artifactId>api</artifactId>
|
|
<version>${djl.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>ai.djl.huggingface</groupId>
|
|
<artifactId>tokenizers</artifactId>
|
|
<version>${djl.version}</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>ai.djl.pytorch</groupId>
|
|
<artifactId>pytorch-engine</artifactId>
|
|
<version>${djl.version}</version>
|
|
<scope>runtime</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>ai.djl.pytorch</groupId>
|
|
<artifactId>pytorch-model-zoo</artifactId>
|
|
<version>${djl.version}</version>
|
|
</dependency>
|
|
|
|
<!-- Utilities -->
|
|
<dependency>
|
|
<groupId>org.projectlombok</groupId>
|
|
<artifactId>lombok</artifactId>
|
|
<optional>true</optional>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.mapstruct</groupId>
|
|
<artifactId>mapstruct</artifactId>
|
|
<version>1.6.2</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>com.google.guava</groupId>
|
|
<artifactId>guava</artifactId>
|
|
<version>33.3.1-jre</version>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.commons</groupId>
|
|
<artifactId>commons-compress</artifactId>
|
|
<version>1.27.1</version>
|
|
</dependency>
|
|
|
|
<!-- Apache POI for Excel generation -->
|
|
<dependency>
|
|
<groupId>org.apache.poi</groupId>
|
|
<artifactId>poi-ooxml</artifactId>
|
|
<version>5.3.0</version>
|
|
</dependency>
|
|
|
|
<!-- OpenAPI Documentation -->
|
|
<dependency>
|
|
<groupId>org.springdoc</groupId>
|
|
<artifactId>springdoc-openapi-starter-webmvc-ui</artifactId>
|
|
<version>2.6.0</version>
|
|
</dependency>
|
|
|
|
<!-- Testing -->
|
|
<dependency>
|
|
<groupId>org.springframework.boot</groupId>
|
|
<artifactId>spring-boot-starter-test</artifactId>
|
|
<scope>test</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.apache.camel</groupId>
|
|
<artifactId>camel-test-spring-junit5</artifactId>
|
|
<version>${camel.version}</version>
|
|
<scope>test</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.testcontainers</groupId>
|
|
<artifactId>postgresql</artifactId>
|
|
<scope>test</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.flywaydb</groupId>
|
|
<artifactId>flyway-core</artifactId>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.flywaydb</groupId>
|
|
<artifactId>flyway-database-postgresql</artifactId>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>org.testcontainers</groupId>
|
|
<artifactId>junit-jupiter</artifactId>
|
|
<version>1.21.4</version>
|
|
<scope>test</scope>
|
|
</dependency>
|
|
<dependency>
|
|
<groupId>com.fasterxml.jackson.datatype</groupId>
|
|
<artifactId>jackson-datatype-jsr310</artifactId>
|
|
</dependency>
|
|
</dependencies>
|
|
|
|
<build>
|
|
<plugins>
|
|
<plugin>
|
|
<groupId>org.springframework.boot</groupId>
|
|
<artifactId>spring-boot-maven-plugin</artifactId>
|
|
<configuration>
|
|
<mainClass>at.procon.dip.DocumentIntelligencePlatformApplication</mainClass>
|
|
<excludes>
|
|
<exclude>
|
|
<groupId>org.projectlombok</groupId>
|
|
<artifactId>lombok</artifactId>
|
|
</exclude>
|
|
</excludes>
|
|
</configuration>
|
|
</plugin>
|
|
<plugin>
|
|
<groupId>org.apache.maven.plugins</groupId>
|
|
<artifactId>maven-compiler-plugin</artifactId>
|
|
<configuration>
|
|
<source>${java.version}</source>
|
|
<target>${java.version}</target>
|
|
<annotationProcessorPaths>
|
|
<path>
|
|
<groupId>org.projectlombok</groupId>
|
|
<artifactId>lombok</artifactId>
|
|
<version>${lombok.version}</version>
|
|
</path>
|
|
<path>
|
|
<groupId>org.mapstruct</groupId>
|
|
<artifactId>mapstruct-processor</artifactId>
|
|
<version>1.6.2</version>
|
|
</path>
|
|
</annotationProcessorPaths>
|
|
</configuration>
|
|
</plugin>
|
|
</plugins>
|
|
</build>
|
|
</project>
|