102 lines
3.3 KiB
Java
Generated
102 lines
3.3 KiB
Java
Generated
// 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 java.util.List;
|
|
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;
|
|
|
|
/**
|
|
* A text chunk with optional embedding and metadata.
|
|
*
|
|
* Chunks are created when chunking is enabled in {@code ExtractionConfig}. Each chunk
|
|
* contains the text content, optional embedding vector (if embedding generation
|
|
* is configured), and metadata about its position in the document.
|
|
*/
|
|
@JsonInclude(JsonInclude.Include.NON_ABSENT)
|
|
@JsonDeserialize(builder = Chunk.Builder.class)
|
|
public record Chunk(
|
|
/**
|
|
* The text content of this chunk.
|
|
*/
|
|
@JsonProperty("content") String content,
|
|
/**
|
|
* Semantic structural classification of this chunk.
|
|
*
|
|
* Assigned by the heuristic classifier based on content patterns and
|
|
* heading context. Defaults to {@code ChunkType.Unknown} when no rule matches.
|
|
*/
|
|
@Nullable @JsonProperty("chunk_type") ChunkType chunkType,
|
|
/**
|
|
* Optional embedding vector for this chunk.
|
|
*
|
|
* Only populated when {@code EmbeddingConfig} is provided in chunking configuration.
|
|
* The dimensionality depends on the chosen embedding model.
|
|
*/
|
|
@Nullable @JsonProperty("embedding") List<Float> embedding,
|
|
/**
|
|
* Metadata about this chunk's position and properties.
|
|
*/
|
|
@JsonProperty("metadata") ChunkMetadata metadata
|
|
) {
|
|
public static Builder builder() {
|
|
return new Builder();
|
|
}
|
|
|
|
// CPD-OFF
|
|
@JsonPOJOBuilder(withPrefix = "with", buildMethodName = "build")
|
|
public static final class Builder {
|
|
|
|
private String content = "";
|
|
@JsonProperty("chunk_type")
|
|
@Nullable private ChunkType chunkType = ChunkType.Unknown;
|
|
private List<Float> embedding = null;
|
|
private ChunkMetadata metadata = null;
|
|
|
|
/** Sets the content field. */
|
|
@JsonProperty("content")
|
|
public Builder withContent(final String value) {
|
|
this.content = value;
|
|
return this;
|
|
}
|
|
|
|
/** Sets the chunkType field. */
|
|
@JsonProperty("chunk_type")
|
|
public Builder withChunkType(final @Nullable ChunkType value) {
|
|
this.chunkType = value;
|
|
return this;
|
|
}
|
|
|
|
/** Sets the embedding field. */
|
|
@JsonProperty("embedding")
|
|
public Builder withEmbedding(final @Nullable List<Float> value) {
|
|
this.embedding = value;
|
|
return this;
|
|
}
|
|
|
|
/** Sets the metadata field. */
|
|
@JsonProperty("metadata")
|
|
public Builder withMetadata(final ChunkMetadata value) {
|
|
this.metadata = value;
|
|
return this;
|
|
}
|
|
|
|
/** Builds the Chunk instance. */
|
|
public Chunk build() {
|
|
return new Chunk(
|
|
content,
|
|
chunkType,
|
|
embedding,
|
|
metadata
|
|
);
|
|
}
|
|
}
|
|
// CPD-ON
|
|
}
|