Spring Ai In Action Pdf Github ((new)) May 2026

@RestController public class ChatController private final ChatClient chatClient; private final VectorStore vectorStore; @GetMapping("/ask") public String askAboutGitHubPdfs(@RequestParam String question) // Retrieve relevant PDF chunks List<Document> relevantDocs = vectorStore.similaritySearch(question); // Create system prompt with context String context = relevantDocs.stream() .map(Document::getText) .collect(Collectors.joining("\n---\n")); return chatClient.call(new Prompt( List.of(new SystemMessage("Answer based only on: " + context), new UserMessage(question)) )).getResult().getOutput().getText();

@Service public class PdfDocumentService public List<Document> parsePdfs(List<byte[]> pdfBytesList) return pdfBytesList.stream() .flatMap(bytes -> ByteArrayInputStream bais = new ByteArrayInputStream(bytes); TikaDocumentReader reader = new TikaDocumentReader(bais); return reader.get().stream(); // Returns List<Document> ) .collect(Collectors.toList()); spring ai in action pdf github

@Service public class GitHubPdfFetcher private final GitHub github = new GitHubBuilder().withOAuthToken(System.getenv("GITHUB_TOKEN")).build(); public List<byte[]> fetchPdfsFromRepo(String repoName, String path) throws IOException GHRepository repo = github.getRepository(repoName); List<GHContent> pdfs = repo.getDirectoryContent(path).stream() .filter(c -> c.getName().endsWith(".pdf")) .toList(); return pdfs.stream().map(content -> try (InputStream is = content.read()) return is.readAllBytes(); catch (IOException e) throw new RuntimeException(e); ).collect(Collectors.toList()); private final VectorStore vectorStore

@Service public class IngestionPipeline private final TokenTextSplitter splitter = new TokenTextSplitter(500, 100); // 500 tokens per chunk private final VectorStore vectorStore; private final EmbeddingClient embeddingClient; @Autowired public IngestionPipeline(VectorStore vectorStore, EmbeddingClient embeddingClient) this.vectorStore = vectorStore; this.embeddingClient = embeddingClient; relevantDocs = vectorStore.similaritySearch(question)

To put this paper itself "in action", the accompanying GitHub repo would be: