Nomad changes

packages/java/dev/kreuzberg/ImageExtractionConfig.java

@@ -0,0 +1,255 @@
+// This file is auto-generated by alef — DO NOT EDIT.
+// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
+// To regenerate: alef generate
+// To verify freshness: alef verify --exit-code
+// Issues & docs: https://github.com/kreuzberg-dev/alef
+package dev.kreuzberg;
+
+import com.fasterxml.jackson.annotation.JsonProperty;
+import com.fasterxml.jackson.annotation.JsonInclude;
+import com.fasterxml.jackson.databind.annotation.JsonDeserialize;
+import com.fasterxml.jackson.databind.annotation.JsonPOJOBuilder;
+import org.jspecify.annotations.Nullable;
+
+/**
+ * Image extraction configuration.
+ */
+@JsonInclude(JsonInclude.Include.NON_ABSENT)
+@JsonDeserialize(builder = ImageExtractionConfig.Builder.class)
+public record ImageExtractionConfig(
+    /**
+     * Extract images from documents
+     */
+    @Nullable @JsonProperty("extract_images") Boolean extractImages,
+    /**
+     * Target DPI for image normalization
+     */
+    @Nullable @JsonProperty("target_dpi") Integer targetDpi,
+    /**
+     * Maximum dimension for images (width or height)
+     */
+    @Nullable @JsonProperty("max_image_dimension") Integer maxImageDimension,
+    /**
+     * Whether to inject image reference placeholders into markdown output.
+     * When {@code true} (default), image references like {@code ![Image 1](embedded:p1_i0)}
+     * are appended to the markdown. Set to {@code false} to extract images as data
+     * without polluting the markdown output.
+     */
+    @Nullable @JsonProperty("inject_placeholders") Boolean injectPlaceholders,
+    /**
+     * Automatically adjust DPI based on image content
+     */
+    @Nullable @JsonProperty("auto_adjust_dpi") Boolean autoAdjustDpi,
+    /**
+     * Minimum DPI threshold
+     */
+    @Nullable @JsonProperty("min_dpi") Integer minDpi,
+    /**
+     * Maximum DPI threshold
+     */
+    @Nullable @JsonProperty("max_dpi") Integer maxDpi,
+    /**
+     * Maximum number of image objects to extract per PDF page.
+     *
+     * Some PDFs (e.g. technical diagrams stored as thousands of raster fragments)
+     * can trigger extremely long or indefinite extraction times when every image
+     * object on a dense page is decoded individually via the PDF extractor. Setting this
+     * limit causes kreuzberg to stop collecting individual images once the count
+     * per page reaches the cap and emit a warning instead.
+     *
+     * {@code None} (default) means no limit — all images are extracted.
+     */
+    @Nullable @JsonProperty("max_images_per_page") Integer maxImagesPerPage,
+    /**
+     * When {@code true} (default), extracted images are classified by kind and grouped
+     * into clusters where they appear to belong to one figure.
+     */
+    @Nullable @JsonProperty("classify") Boolean classify,
+    /**
+     * When {@code true}, full-page renders produced during OCR preprocessing are captured
+     * and returned as {@code ImageKind.PageRaster} entries in {@code ExtractionResult.images}.
+     *
+     * **PDF + OCR only.** No rasters are captured for non-PDF inputs or when the
+     * document-level OCR bypass is active (whole-document backend). When OCR is
+     * enabled and this flag is set but the active backend skips per-page rendering,
+     * a {@code ProcessingWarning} is emitted in {@code ExtractionResult.processing_warnings}.
+     *
+     * Defaults to {@code false}. Enable when downstream consumers need page thumbnails
+     * (e.g. citation previews, visual grounding).
+     */
+    @Nullable @JsonProperty("include_page_rasters") Boolean includePageRasters,
+    /**
+     * Run OCR on extracted images and include the recognized text in the document content.
+     *
+     * When {@code true} (default) and {@code ExtractionConfig.ocr} is configured, extracted images
+     * are processed with the configured OCR backend. Set to {@code false} to extract images
+     * without OCR processing, even when OCR is enabled.
+     */
+    @Nullable @JsonProperty("run_ocr_on_images") Boolean runOcrOnImages,
+    /**
+     * When {@code true}, image OCR results are rendered as plain text without the
+     * {@code ![...](...)} markdown placeholder. Only takes effect when {@code run_ocr_on_images}
+     * is also {@code true}.
+     */
+    @Nullable @JsonProperty("ocr_text_only") Boolean ocrTextOnly,
+    /**
+     * When {@code true} and {@code ocr_text_only} is {@code false}, append the OCR text after
+     * the image placeholder in the rendered output.
+     */
+    @Nullable @JsonProperty("append_ocr_text") Boolean appendOcrText
+) {
+    public static Builder builder() {
+        return new Builder();
+    }
+    public ImageExtractionConfig{
+        if (targetDpi == null) targetDpi = 300;
+        if (maxImageDimension == null) maxImageDimension = 4096;
+        if (minDpi == null) minDpi = 72;
+        if (maxDpi == null) maxDpi = 600;
+    }
+
+    // CPD-OFF
+    @JsonPOJOBuilder(withPrefix = "with", buildMethodName = "build")
+    public static final class Builder {
+
+        @JsonProperty("extract_images")
+private Boolean extractImages = null;
+        @JsonProperty("target_dpi")
+private Integer targetDpi = null;
+        @JsonProperty("max_image_dimension")
+private Integer maxImageDimension = null;
+        @JsonProperty("inject_placeholders")
+private Boolean injectPlaceholders = null;
+        @JsonProperty("auto_adjust_dpi")
+private Boolean autoAdjustDpi = null;
+        @JsonProperty("min_dpi")
+private Integer minDpi = null;
+        @JsonProperty("max_dpi")
+private Integer maxDpi = null;
+        @JsonProperty("max_images_per_page")
+private Integer maxImagesPerPage = null;
+private Boolean classify = null;
+        @JsonProperty("include_page_rasters")
+private Boolean includePageRasters = null;
+        @JsonProperty("run_ocr_on_images")
+private Boolean runOcrOnImages = null;
+        @JsonProperty("ocr_text_only")
+private Boolean ocrTextOnly = null;
+        @JsonProperty("append_ocr_text")
+private Boolean appendOcrText = null;
+
+        /** Sets the extractImages field. */
+        @JsonProperty("extract_images")
+        public Builder withExtractImages(final @Nullable Boolean value) {
+            this.extractImages = value;
+            return this;
+        }
+
+        /** Sets the targetDpi field. */
+        @JsonProperty("target_dpi")
+        public Builder withTargetDpi(final @Nullable Integer value) {
+            this.targetDpi = value;
+            return this;
+        }
+
+        /** Sets the maxImageDimension field. */
+        @JsonProperty("max_image_dimension")
+        public Builder withMaxImageDimension(final @Nullable Integer value) {
+            this.maxImageDimension = value;
+            return this;
+        }
+
+        /** Sets the injectPlaceholders field. */
+        @JsonProperty("inject_placeholders")
+        public Builder withInjectPlaceholders(final @Nullable Boolean value) {
+            this.injectPlaceholders = value;
+            return this;
+        }
+
+        /** Sets the autoAdjustDpi field. */
+        @JsonProperty("auto_adjust_dpi")
+        public Builder withAutoAdjustDpi(final @Nullable Boolean value) {
+            this.autoAdjustDpi = value;
+            return this;
+        }
+
+        /** Sets the minDpi field. */
+        @JsonProperty("min_dpi")
+        public Builder withMinDpi(final @Nullable Integer value) {
+            this.minDpi = value;
+            return this;
+        }
+
+        /** Sets the maxDpi field. */
+        @JsonProperty("max_dpi")
+        public Builder withMaxDpi(final @Nullable Integer value) {
+            this.maxDpi = value;
+            return this;
+        }
+
+        /** Sets the maxImagesPerPage field. */
+        @JsonProperty("max_images_per_page")
+        public Builder withMaxImagesPerPage(final @Nullable Integer value) {
+            this.maxImagesPerPage = value;
+            return this;
+        }
+
+        /** Sets the classify field. */
+        @JsonProperty("classify")
+        public Builder withClassify(final @Nullable Boolean value) {
+            this.classify = value;
+            return this;
+        }
+
+        /** Sets the includePageRasters field. */
+        @JsonProperty("include_page_rasters")
+        public Builder withIncludePageRasters(final @Nullable Boolean value) {
+            this.includePageRasters = value;
+            return this;
+        }
+
+        /** Sets the runOcrOnImages field. */
+        @JsonProperty("run_ocr_on_images")
+        public Builder withRunOcrOnImages(final @Nullable Boolean value) {
+            this.runOcrOnImages = value;
+            return this;
+        }
+
+        /** Sets the ocrTextOnly field. */
+        @JsonProperty("ocr_text_only")
+        public Builder withOcrTextOnly(final @Nullable Boolean value) {
+            this.ocrTextOnly = value;
+            return this;
+        }
+
+        /** Sets the appendOcrText field. */
+        @JsonProperty("append_ocr_text")
+        public Builder withAppendOcrText(final @Nullable Boolean value) {
+            this.appendOcrText = value;
+            return this;
+        }
+
+        /** Builds the ImageExtractionConfig instance. */
+        public ImageExtractionConfig build() {
+            return new ImageExtractionConfig(
+                extractImages,
+                targetDpi,
+                maxImageDimension,
+                injectPlaceholders,
+                autoAdjustDpi,
+                minDpi,
+                maxDpi,
+                maxImagesPerPage,
+                classify,
+                includePageRasters,
+                runOcrOnImages,
+                ocrTextOnly,
+                appendOcrText
+            );
+        }
+    }
+    // CPD-ON
+    public static ImageExtractionConfig defaultInstance() {
+        throw new UnsupportedOperationException("defaultInstance is not yet bridged via JNI; use the Builder instead.");
+    }
+}