Skip to main content

Interface: IEmbedder

Defined in: internal/embedder/types.ts:31

Text → vector, one fixed model.

Implemented by Embedder; the type of IAIGatewayDeps.embedder, so a host may pass its own in overrides.

Properties​

dimensions​

readonly dimensions: number

Defined in: internal/embedder/types.ts:99

dimensions -- the length of every vector this embedder produces

About​

The ruler's length.

The configured dimensions, as the index must have been created with.

Who needs it​

KbIngestor.checkIndex, compared with VectorStore.describeIndex before every ingest.

embeddingModelId​

readonly embeddingModelId: string

Defined in: internal/embedder/types.ts:114

embeddingModelId -- the model every vector comes from

About​

Written with every record, so the index can refuse a vector of another model.

The configured embeddingModelId.

Who needs it​

KbIngestor.ingestDocument, on every IChunkRecord it writes; KbIngestor.checkIndex, compared with the index.

Methods​

embed()​

embed(__namedParameters): Promise<number[][]>

Defined in: internal/embedder/types.ts:52

embed -- the vectors of many texts

About​

One vector per text, in the same order, all of the same length.

Sends the texts in batches of batchSize to LLMClient.embed, one call after the other, and returns the vectors in the order of the texts. Throws when a batch comes back with another number of vectors than texts (error 5372630367606, a 502) or with a vector of another length than dimensions (error 5372630367840, a 500).

Who needs it​

KbIngestor.ingestDocument, for the chunks of one document (heading path and text together); embedOne.

Pitfalls​

A failing batch stops the call; the vectors of the earlier batches are lost, nothing is written. Every batch is one usage-guard check and one trace of kind EMBED.

Parameters​

__namedParameters​
meta​

ILLMClientCallMeta

For the usage adapter and the trace; kind = EMBED.

texts​

string[]

Returns​

Promise<number[][]>

embedOne()​

embedOne(__namedParameters): Promise<number[]>

Defined in: internal/embedder/types.ts:76

embedOne -- the vector of one text

About​

The query side of embed.

embed with one text; returns its vector.

Who needs it​

KbRetriever.retrieve, for the rewritten query of every call with a knowledge base.

Parameters​

__namedParameters​
meta​

ILLMClientCallMeta

text​

string

Returns​

Promise<number[]>