fil/packages/java/dev/kreuzberg/EmbeddingConfig.java

// 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;

/**
 * Embedding configuration for text chunks.
 *
 * Configures embedding generation using ONNX models via the vendored embedding engine.
 * Requires the {@code embeddings} feature to be enabled.
 */
@JsonInclude(JsonInclude.Include.NON_ABSENT)
@JsonDeserialize(builder = EmbeddingConfig.Builder.class)
public record EmbeddingConfig(
    /**
     * The embedding model to use (defaults to "balanced" preset if not specified)
     */
    @Nullable @JsonProperty("model") EmbeddingModelType model,
    /**
     * Whether to normalize embedding vectors (recommended for cosine similarity)
     */
    @Nullable @JsonProperty("normalize") Boolean normalize,
    /**
     * Batch size for embedding generation
     */
    @Nullable @JsonProperty("batch_size") Long batchSize,
    /**
     * Show model download progress
     */
    @Nullable @JsonProperty("show_download_progress") Boolean showDownloadProgress,
    /**
     * Custom cache directory for model files
     *
     * Defaults to {@code ~/.cache/kreuzberg/embeddings/} if not specified.
     * Allows full customization of model download location.
     */
    @JsonProperty("cache_dir") java.nio.file.@Nullable Path cacheDir,
    /**
     * Hardware acceleration for the embedding ONNX model.
     *
     * When set, controls which execution provider (CPU, CUDA, CoreML, TensorRT)
     * is used for inference. Defaults to {@code None} (auto-select per platform).
     */
    @Nullable @JsonProperty("acceleration") AccelerationConfig acceleration,
    /**
     * Maximum wall-clock duration (in seconds) for a single {@code embed()} call when
     * using EmbeddingModelType.Plugin.
     *
     * Applies only to the in-process plugin path — protects against hung
     * host-language backends (e.g. a Python callback deadlocked on the GIL,
     * a model stuck on CUDA OOM retries, etc.). On timeout, the dispatcher
     * returns {@code Plugin} instead of blocking forever.
     *
     * {@code None} disables the timeout. The default (60 seconds) is conservative
     * for common in-process inference; increase for large batches on slow
     * hardware.
     */
    @Nullable @JsonProperty("max_embed_duration_secs") Long maxEmbedDurationSecs
) {
    public static Builder builder() {
        return new Builder();
    }
    public EmbeddingConfig{
        if (batchSize == null) batchSize = 32L;
    }

    // CPD-OFF
    @JsonPOJOBuilder(withPrefix = "with", buildMethodName = "build")
    public static final class Builder {

        @Nullable private EmbeddingModelType model = null;
private Boolean normalize = null;
        @JsonProperty("batch_size")
private Long batchSize = null;
        @JsonProperty("show_download_progress")
private Boolean showDownloadProgress = null;
        @JsonProperty("cache_dir")
private java.nio.file.Path cacheDir = null;
        @Nullable private AccelerationConfig acceleration = null;
        @JsonProperty("max_embed_duration_secs")
private Long maxEmbedDurationSecs = null;

        /** Sets the model field. */
        @JsonProperty("model")
        public Builder withModel(final @Nullable EmbeddingModelType value) {
            this.model = value;
            return this;
        }

        /** Sets the normalize field. */
        @JsonProperty("normalize")
        public Builder withNormalize(final @Nullable Boolean value) {
            this.normalize = value;
            return this;
        }

        /** Sets the batchSize field. */
        @JsonProperty("batch_size")
        public Builder withBatchSize(final @Nullable Long value) {
            this.batchSize = value;
            return this;
        }

        /** Sets the showDownloadProgress field. */
        @JsonProperty("show_download_progress")
        public Builder withShowDownloadProgress(final @Nullable Boolean value) {
            this.showDownloadProgress = value;
            return this;
        }

        /** Sets the cacheDir field. */
        @JsonProperty("cache_dir")
        public Builder withCacheDir(final java.nio.file.@Nullable Path value) {
            this.cacheDir = value;
            return this;
        }

        /** Sets the acceleration field. */
        @JsonProperty("acceleration")
        public Builder withAcceleration(final @Nullable AccelerationConfig value) {
            this.acceleration = value;
            return this;
        }

        /** Sets the maxEmbedDurationSecs field. */
        @JsonProperty("max_embed_duration_secs")
        public Builder withMaxEmbedDurationSecs(final @Nullable Long value) {
            this.maxEmbedDurationSecs = value;
            return this;
        }

        /** Builds the EmbeddingConfig instance. */
        public EmbeddingConfig build() {
            return new EmbeddingConfig(
                model,
                normalize,
                batchSize,
                showDownloadProgress,
                cacheDir,
                acceleration,
                maxEmbedDurationSecs
            );
        }
    }
    // CPD-ON
    public static EmbeddingConfig defaultInstance() {
        throw new UnsupportedOperationException("defaultInstance is not yet bridged via JNI; use the Builder instead.");
    }
}