ETL Pipeline

@Component
class MyJsonReader {

	private final Resource resource;

    MyJsonReader(@Value("classpath:bikes.json") Resource resource) {
        this.resource = resource;
    }

	List<Document> loadJsonAsDocuments() {
        JsonReader jsonReader = new JsonReader(this.resource, "description", "content");
        return jsonReader.get();
	}
}

[
  {
    "id": 1,
    "brand": "Trek",
    "description": "A high-performance mountain bike for trail riding."
  },
  {
    "id": 2,
    "brand": "Cannondale",
    "description": "An aerodynamic road bike for racing enthusiasts."
  }
]

@Component
class MyTextReader {

    private final Resource resource;

    MyTextReader(@Value("classpath:text-source.txt") Resource resource) {
        this.resource = resource;
    }

	List<Document> loadText() {
		TextReader textReader = new TextReader(this.resource);
		textReader.getCustomMetadata().put("filename", "text-source.txt");

		return textReader.read();
    }
}

List<Document> documents = textReader.get();
List<Document> splitDocuments = new TokenTextSplitter().apply(this.documents);

@Component
class MyMarkdownReader {

    private final Resource resource;

    MyMarkdownReader(@Value("classpath:code.md") Resource resource) {
        this.resource = resource;
    }

    List<Document> loadMarkdown() {
        MarkdownDocumentReaderConfig config = MarkdownDocumentReaderConfig.builder()
            .withHorizontalRuleCreateDocument(true)
            .withIncludeCodeBlock(false)
            .withIncludeBlockquote(false)
            .withAdditionalMetadata("filename", "code.md")
            .build();

        MarkdownDocumentReader reader = new MarkdownDocumentReader(this.resource, config);
        return reader.get();
    }
}

This is a Java sample application:

```java
package com.example.demo;

import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;

@SpringBootApplication
public class DemoApplication {
    public static void main(String[] args) {
        SpringApplication.run(DemoApplication.class, args);
    }
}
```

Markdown also provides the possibility to `use inline code formatting throughout` the entire sentence.

---

Another possibility is to set block code without specific highlighting:

```
./mvnw spring-javaformat:apply
```

@Component
public class MyPagePdfDocumentReader {

	List<Document> getDocsFromPdf() {

		PagePdfDocumentReader pdfReader = new PagePdfDocumentReader("classpath:/sample1.pdf",
				PdfDocumentReaderConfig.builder()
					.withPageTopMargin(0)
					.withPageExtractedTextFormatter(ExtractedTextFormatter.builder()
						.withNumberOfTopTextLinesToDelete(0)
						.build())
					.withPagesPerDocument(1)
					.build());

		return pdfReader.read();
    }

}

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-pdf-document-reader</artifactId>
</dependency>

dependencies {
    implementation 'org.springframework.ai:spring-ai-pdf-document-reader'
}

@Component
public class MyPagePdfDocumentReader {

	List<Document> getDocsFromPdfWithCatalog() {

        ParagraphPdfDocumentReader pdfReader = new ParagraphPdfDocumentReader("classpath:/sample1.pdf",
                PdfDocumentReaderConfig.builder()
                    .withPageTopMargin(0)
                    .withPageExtractedTextFormatter(ExtractedTextFormatter.builder()
                        .withNumberOfTopTextLinesToDelete(0)
                        .build())
                    .withPagesPerDocument(1)
                    .build());

	    return pdfReader.read();
    }
}

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-tika-document-reader</artifactId>
</dependency>

dependencies {
    implementation 'org.springframework.ai:spring-ai-tika-document-reader'
}

@Component
class MyTikaDocumentReader {

    private final Resource resource;

    MyTikaDocumentReader(@Value("classpath:/word-sample.docx")
                            Resource resource) {
        this.resource = resource;
    }

    List<Document> loadText() {
        TikaDocumentReader tikaDocumentReader = new TikaDocumentReader(this.resource);
        return tikaDocumentReader.read();
    }
}

@Component
class MyTokenTextSplitter {

    public List<Document> splitDocuments(List<Document> documents) {
        TokenTextSplitter splitter = new TokenTextSplitter();
        return splitter.apply(documents);
    }

    public List<Document> splitCustomized(List<Document> documents) {
        TokenTextSplitter splitter = new TokenTextSplitter(1000, 400, 10, 5000, true);
        return splitter.apply(documents);
    }
}

Document doc1 = new Document("This is a long piece of text that needs to be split into smaller chunks for processing.",
        Map.of("source", "example.txt"));
Document doc2 = new Document("Another document with content that will be split based on token count.",
        Map.of("source", "example2.txt"));

TokenTextSplitter splitter = new TokenTextSplitter();
List<Document> splitDocuments = this.splitter.apply(List.of(this.doc1, this.doc2));

for (Document doc : splitDocuments) {
    System.out.println("Chunk: " + doc.getContent());
    System.out.println("Metadata: " + doc.getMetadata());
}

@Component
class MyKeywordEnricher {

    private final ChatModel chatModel;

    MyKeywordEnricher(ChatModel chatModel) {
        this.chatModel = chatModel;
    }

    List<Document> enrichDocuments(List<Document> documents) {
        KeywordMetadataEnricher enricher = new KeywordMetadataEnricher(this.chatModel, 5);
        return enricher.apply(documents);
    }
}

\{context_str}. Give %s unique keywords for this document. Format as comma separated. Keywords:

ChatModel chatModel = // initialize your chat model
KeywordMetadataEnricher enricher = new KeywordMetadataEnricher(chatModel, 5);

Document doc = new Document("This is a document about artificial intelligence and its applications in modern technology.");

List<Document> enrichedDocs = enricher.apply(List.of(this.doc));

Document enrichedDoc = this.enrichedDocs.get(0);
String keywords = (String) this.enrichedDoc.getMetadata().get("excerpt_keywords");
System.out.println("Extracted keywords: " + keywords);

@Configuration
class EnricherConfig {

    @Bean
    public SummaryMetadataEnricher summaryMetadata(OpenAiChatModel aiClient) {
        return new SummaryMetadataEnricher(aiClient,
            List.of(SummaryType.PREVIOUS, SummaryType.CURRENT, SummaryType.NEXT));
    }
}

@Component
class MySummaryEnricher {

    private final SummaryMetadataEnricher enricher;

    MySummaryEnricher(SummaryMetadataEnricher enricher) {
        this.enricher = enricher;
    }

    List<Document> enrichDocuments(List<Document> documents) {
        return this.enricher.apply(documents);
    }
}

"""
Here is the content of the section:
{context_str}

Summarize the key topics and entities of the section.

Summary:
"""

ChatModel chatModel = // initialize your chat model
SummaryMetadataEnricher enricher = new SummaryMetadataEnricher(chatModel,
    List.of(SummaryType.PREVIOUS, SummaryType.CURRENT, SummaryType.NEXT));

Document doc1 = new Document("Content of document 1");
Document doc2 = new Document("Content of document 2");

List<Document> enrichedDocs = enricher.apply(List.of(this.doc1, this.doc2));

// Check the metadata of the enriched documents
for (Document doc : enrichedDocs) {
    System.out.println("Current summary: " + doc.getMetadata().get("section_summary"));
    System.out.println("Previous summary: " + doc.getMetadata().get("prev_section_summary"));
    System.out.println("Next summary: " + doc.getMetadata().get("next_section_summary"));
}

@Component
class MyDocumentWriter {

    public void writeDocuments(List<Document> documents) {
        FileDocumentWriter writer = new FileDocumentWriter("output.txt", true, MetadataMode.ALL, false);
        writer.accept(documents);
    }
}

### Doc: [index], pages:[start_page_number,end_page_number]

List<Document> documents = // initialize your documents
FileDocumentWriter writer = new FileDocumentWriter("output.txt", true, MetadataMode.ALL, true);
writer.accept(documents);