Nomad changes

docs/snippets/java/api/batch_extract_bytes_sync.md

@@ -0,0 +1,22 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.BatchBytesItem;
+import dev.kreuzberg.ExtractionConfig;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+import java.util.List;
+import java.util.Arrays;
+
+byte[] doc1 = Files.readAllBytes(Paths.get("doc1.pdf"));
+byte[] doc2 = Files.readAllBytes(Paths.get("doc2.docx"));
+
+List<BatchBytesItem> items = Arrays.asList(
+    new BatchBytesItem(doc1, "application/pdf", null),
+    new BatchBytesItem(doc2, "application/vnd.openxmlformats-officedocument.wordprocessingml.document", null)
+);
+
+ExtractionConfig config = ExtractionConfig.builder().build();
+List<ExtractionResult> results = Kreuzberg.batchExtractBytesSync(items, config);
+System.out.println("Processed " + results.size() + " documents");
+```

docs/snippets/java/api/batch_extract_files_sync.md

@@ -0,0 +1,22 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.BatchFileItem;
+import dev.kreuzberg.ExtractionConfig;
+import java.nio.file.Paths;
+import java.util.List;
+import java.util.Arrays;
+
+List<BatchFileItem> items = Arrays.asList(
+    new BatchFileItem(Paths.get("doc1.pdf"), null),
+    new BatchFileItem(Paths.get("doc2.docx"), null),
+    new BatchFileItem(Paths.get("doc3.pptx"), null)
+);
+
+ExtractionConfig config = ExtractionConfig.builder().build();
+List<ExtractionResult> results = Kreuzberg.batchExtractFilesSync(items, config);
+
+for (ExtractionResult result : results) {
+    System.out.println("Content length: " + result.content().length());
+}
+```

docs/snippets/java/api/client_chunk_text.md

@@ -0,0 +1,30 @@
+<!-- snippet:skip -->
+```java title="Java"
+import java.net.http.HttpClient;
+import java.net.http.HttpRequest;
+import java.net.http.HttpResponse;
+import java.net.URI;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.annotation.JsonProperty;
+import java.util.List;
+
+record ChunkRequest(String text, @JsonProperty("chunker_type") String chunkerType, ChunkConfig config) {}
+record ChunkConfig(@JsonProperty("max_characters") int maxCharacters, int overlap, boolean trim) {}
+record ChunkItem(String content, @JsonProperty("byte_start") int byteStart, @JsonProperty("chunk_index") int chunkIndex) {}
+
+HttpClient client = HttpClient.newHttpClient();
+ObjectMapper mapper = new ObjectMapper();
+
+ChunkRequest req = new ChunkRequest("Your long text here...", "text", new ChunkConfig(1000, 50, true));
+String json = mapper.writeValueAsString(req);
+
+var request = HttpRequest.newBuilder()
+    .uri(URI.create("http://localhost:8000/chunk"))
+    .header("Content-Type", "application/json")
+    .POST(HttpRequest.BodyPublishers.ofString(json))
+    .build();
+
+HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
+var result = mapper.readTree(response.body());
+System.out.println("Created " + result.get("chunk_count").asInt() + " chunks");
+```

docs/snippets/java/api/client_extract_single_file.md

@@ -0,0 +1,22 @@
+```java title="Java"
+import java.net.http.HttpClient;
+import java.net.http.HttpRequest;
+import java.net.http.HttpResponse;
+import java.net.URI;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+
+HttpClient client = HttpClient.newHttpClient();
+
+try (var fileStream = Files.newInputStream(Paths.get("document.pdf"))) {
+    byte[] content = fileStream.readAllBytes();
+    var request = HttpRequest.newBuilder()
+        .uri(URI.create("http://localhost:8000/extract"))
+        .header("Content-Type", "application/octet-stream")
+        .POST(HttpRequest.BodyPublishers.ofByteArray(content))
+        .build();
+
+    HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
+    System.out.println(response.body());
+}
+```

docs/snippets/java/api/combining_all_features.md

@@ -0,0 +1,28 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.*;
+import java.nio.file.Paths;
+import java.util.Optional;
+
+ExtractionConfig config = ExtractionConfig.builder()
+    .withOcr(Optional.of(OcrConfig.builder()
+        .withBackend("tesseract")
+        .withLanguages(Optional.of(java.util.List.of("eng", "deu")))
+        .build()))
+    .withChunking(Optional.of(ChunkingConfig.builder()
+        .withMaxChars(Optional.of(512L))
+        .withMaxOverlap(Optional.of(50L))
+        .build()))
+    .withEnableQualityProcessing(true)
+    .build();
+
+ExtractionResult result = Kreuzberg.extractFileSync(Paths.get("document.pdf"), config);
+System.out.println("Content: " + result.content().substring(0, 100) + "...");
+if (result.tables() != null) {
+    System.out.println("Tables: " + result.tables().size());
+}
+if (result.qualityScore() != null) {
+    System.out.println("Quality: " + result.qualityScore());
+}
+```

docs/snippets/java/api/error_handling.md

@@ -0,0 +1,16 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import dev.kreuzberg.KreuzbergRsException;
+import java.nio.file.Paths;
+
+try {
+    ExtractionConfig config = ExtractionConfig.builder().build();
+    ExtractionResult result = Kreuzberg.extractFileSync(Paths.get("missing.pdf"), config);
+    System.out.println(result.content());
+} catch (KreuzbergRsException e) {
+    System.err.println("Extraction failed: " + e.getMessage());
+    System.err.println("Error code: " + e.getCode());
+}
+```

docs/snippets/java/api/error_handling_extract.md

@@ -0,0 +1,28 @@
+```java title="Java"
+import java.net.http.HttpClient;
+import java.net.http.HttpRequest;
+import java.net.http.HttpResponse;
+import java.net.URI;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+HttpClient client = HttpClient.newHttpClient();
+byte[] fileBytes = Files.readAllBytes(Paths.get("document.pdf"));
+
+var request = HttpRequest.newBuilder()
+    .uri(URI.create("http://localhost:8000/extract"))
+    .header("Content-Type", "application/octet-stream")
+    .POST(HttpRequest.BodyPublishers.ofByteArray(fileBytes))
+    .build();
+
+HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
+
+if (response.statusCode() != 200) {
+    ObjectMapper mapper = new ObjectMapper();
+    var error = mapper.readTree(response.body());
+    System.err.println("Error: " + error.get("error_type").asText() + " - " + error.get("message").asText());
+} else {
+    System.out.println("Success: " + response.body());
+}
+```

docs/snippets/java/api/extract_bytes_async.md

@@ -0,0 +1,14 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+
+byte[] data = Files.readAllBytes(Paths.get("document.pdf"));
+ExtractionConfig config = ExtractionConfig.builder().build();
+ExtractionResult result = Kreuzberg.extractBytes(data, "application/pdf", config);
+
+System.out.println(result.content());
+System.out.println(result.mimeType());
+```

docs/snippets/java/api/extract_bytes_sync.md

@@ -0,0 +1,14 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+
+byte[] data = Files.readAllBytes(Paths.get("document.pdf"));
+ExtractionConfig config = ExtractionConfig.builder().build();
+ExtractionResult result = Kreuzberg.extractBytesSync(data, "application/pdf", config);
+
+System.out.println(result.content());
+System.out.println(result.mimeType());
+```

docs/snippets/java/api/extract_file_async.md

@@ -0,0 +1,12 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import java.nio.file.Paths;
+
+ExtractionConfig config = ExtractionConfig.builder().build();
+ExtractionResult result = Kreuzberg.extractFile(Paths.get("document.pdf"), config);
+
+System.out.println(result.content());
+System.out.println(result.mimeType());
+```

docs/snippets/java/api/extract_file_sync.md

@@ -0,0 +1,13 @@
+```java title="Java"
+import dev.kreuzberg.Kreuzberg;
+import dev.kreuzberg.ExtractionResult;
+import dev.kreuzberg.ExtractionConfig;
+import java.nio.file.Paths;
+
+ExtractionConfig config = ExtractionConfig.builder().build();
+ExtractionResult result = Kreuzberg.extractFileSync(Paths.get("document.pdf"), config);
+
+System.out.println(result.content());
+System.out.println("Tables: " + (result.tables() != null ? result.tables().size() : 0));
+System.out.println("Metadata: " + result.metadata());
+```