Merge pull request #1619 from tzolov

* pr/1619: Polish "Add Spring AI document readers to initializr" Add Spring AI document readers to initializr Closes gh-1619
spring-io · Oct 16, 2024 · 64a1123 · 64a1123
2 parents da6cf78 + ffa75d1
commit 64a1123
Showing 1 changed file with 30 additions and 0 deletions.
diff --git 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)"