Add rag module: Spring AI 2.0 RAG with pgvector, chunking, reranking and a faithfulness check

Co-Authored-By: Claude Sonnet 5 <[email protected]> Claude-Session: https://claude.ai/code/session_01B38FGKKam5SCGgwgduVAh3
2026-09-21 19:09:05 +00:00
commit 1d4625a1c2
62 changed files with 3715 additions and 0 deletions
@@ -0,0 +1,25 @@
+import java.util.List;
+
+import org.springframework.ai.document.Document;
+import org.springframework.ai.reader.pdf.PagePdfDocumentReader;
+import org.springframework.ai.reader.pdf.config.PdfDocumentReaderConfig;
+import org.springframework.ai.transformer.splitter.TokenTextSplitter;
+import org.springframework.core.io.Resource;
+
+/**
+ * The two Spring AI calls from the 1.x article's ingestion service, unchanged (including the
+ * regex, which lost its backslash when the article was first published). Compiled, not run.
+ */
+class LegacyIngestion {
+
+    List<Document> ingest(Resource pdfResource) {
+        PdfDocumentReaderConfig readerConfig = PdfDocumentReaderConfig.builder()
+                .withPageExtractedTextFormatter(text -> text.replaceAll("s{3,}", "  "))
+                .withPagesPerDocument(1)
+                .build();
+        List<Document> pages = new PagePdfDocumentReader(pdfResource, readerConfig).get();
+
+        TokenTextSplitter splitter = new TokenTextSplitter(512, 128, 5, 10_000, true);
+        return splitter.apply(pages);
+    }
+}