Embedder class

Processes text into vector embeddings for semantic search and similarity analysis.

The Embedder class takes raw text, divides it into chunks, and then generates vector embeddings for each chunk using the specified embed driver and model. This is a key component in building semantic search capabilities and enabling retrieval-augmented generation (RAG) systems.

Constructors

Embedder.new({required Future<List<double>> embedder(String content), required Chunker chunker, int overlap = 500})

Creates a new Embedder with the specified parameters.

Properties

chunker → Chunker

The chunker used to divide text into manageable pieces

final

embedder → Future<List<double>> Function(String content)

The driver used to generate embeddings

final

hashCode → int

The hash code for this object.

no setter, inherited

overlap → int

The amount of text overlap between chunks in characters

final

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

transform(Stream<String> rawFeed, {int semaphoreBuffer = 4}) → Stream<EmbeddedChunk>

Transforms a stream of raw text into a stream of embedded chunks.

Operators

operator ==(Object other) → bool

The equality operator.

inherited