diff --git a/start-site/src/main/resources/application.yml b/start-site/src/main/resources/application.yml index 8438d4499a..92730de7e7 100644 --- a/start-site/src/main/resources/application.yml +++ b/start-site/src/main/resources/application.yml @@ -1678,6 +1678,36 @@ initializr: links: - rel: reference href: https://docs.spring.io/spring-ai/reference/api/vectordbs/weaviate.html + - name: Markdown Document Reader + id: spring-ai-markdown-document-reader + group-id: org.springframework.ai + artifact-id: spring-ai-markdown-document-reader + description: Spring AI Markdown document reader. It allows to load Markdown documents, converting them into a list of Spring AI Document objects. + bom: spring-ai + starter: false + links: + - rel: reference + href: https://docs.spring.io/spring-ai/reference/api/etl-pipeline.html#_markdown + - name: Tika Document Reader + id: spring-ai-tika-document-reader + group-id: org.springframework.ai + artifact-id: spring-ai-tika-document-reader + description: Spring AI Tika document reader. It uses Apache Tika to extract text from a variety of document formats, such as PDF, DOC/DOCX, PPT/PPTX, and HTML. The documents are converted into a list of Spring AI Document objects. + bom: spring-ai + starter: false + links: + - rel: reference + href: https://docs.spring.io/spring-ai/reference/api/etl-pipeline.html#_tika_docx_pptx_html + - name: PDF Document Reader + id: spring-ai-pdf-document-reader + group-id: org.springframework.ai + artifact-id: spring-ai-pdf-document-reader + description: Spring AI PDF document reader. It uses Apache PdfBox to extract text from PDF documents and converting them into a list of Spring AI Document objects. + bom: spring-ai + starter: false + links: + - rel: reference + href: https://docs.spring.io/spring-ai/reference/api/etl-pipeline.html#_pdf_page - name: Timefold Solver id: timefold-solver compatibilityRange: "[3.2.0,3.4.0-M1)"