Class EdgeChunkerMediAdapter

Namespace

Qavren.Edge.Ingestion.DataIngestion

Assembly

Qavren.Edge.Ingestion.DataIngestion.dll

Wraps an SP3 IChunker behind MEDI's IngestionChunker<T> contract (spec 11, plan task 6.3 step 2).

It carries no constant. MEDI's shipped chunkers default to 2000 tokens with a 500-token overlap, four to eight times what a 384-dimension device model can encode; this adapter takes the ResolvedChunkOptions the caller already froze — normally through Resolve(ChunkModelProfile, IChunkTokenizer) against the real IChunkTokenizer — and hands that budget to the chunker verbatim.

Each IngestionChunk<T> carries the chunk's stored text as Content, its breadcrumb as Context, and the rest of the ChunkDraft under the metadata keys declared here, so EdgeVectorStoreMediWriter can write the same row SP3's own runner would.

public sealed class EdgeChunkerMediAdapter : IngestionChunker<string>

Inheritance

object

IngestionChunker<string>

EdgeChunkerMediAdapter

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Constructors

EdgeChunkerMediAdapter(IChunker, ResolvedChunkOptions, IChunkTokenizer, ILogger?)

Creates the adapter.

Fields

BlockKindKey

Chunk metadata: Kind's name.

CharEndKey

Chunk metadata: CharEnd.

CharStartKey

Chunk metadata: CharStart.

EmbedTextKey

Chunk metadata: EmbedText — breadcrumb plus body, the text SP3 embeds and hashes. Content is the stored text, never this.

OrdinalKey

Chunk metadata: Ordinal.

PageKey

Chunk metadata: Page, -1 when unknown.

TokenCountKey

Chunk metadata: TokenCount.

Properties

Chunker

The wrapped chunker.

Options

The frozen budget every document is chunked against.

Methods

ProcessAsync(IngestionDocument, CancellationToken)

Splits a document into chunks asynchronously.