base

module wittgenstein_embeddings.base

Classes

• EmbeddingClient — Query/passage embedding interface (the E5 asymmetric-encoding contract).

wittgenstein_embeddings.base.EmbeddingClient

class EmbeddingClient()

Bases : ABC

Query/passage embedding interface (the E5 asymmetric-encoding contract).

intfloat/multilingual-e5-* models require literal "query: "/"passage: " prefixes depending on which side of a retrieval pair is embedded. Symmetric providers (OpenAI, Gemini, Ollama) implement both methods identically — callers never need to know which kind of model backs the instance.

Attributes

• dimension : int — Embedding width.

Methods

• query

• passage

• query_batch — Default: sequential calls. Providers with real batch APIs override this.

• passage_batch

wittgenstein_embeddings.base.EmbeddingClient.query

method EmbeddingClient.query(text: str) → list[float]

wittgenstein_embeddings.base.EmbeddingClient.passage

method EmbeddingClient.passage(text: str) → list[float]

wittgenstein_embeddings.base.EmbeddingClient.query_batch

method EmbeddingClient.query_batch(texts: list[str]) → list[list[float]]

Default: sequential calls. Providers with real batch APIs override this.

wittgenstein_embeddings.base.EmbeddingClient.passage_batch

method EmbeddingClient.passage_batch(texts: list[str]) → list[list[float]]

wittgenstein_embeddings.base.EmbeddingClient.dimension

property EmbeddingClient.dimension: int

Embedding width.

Static where the SDK exposes it (sentence-transformers' get_sentence_embedding_dimension()); lazily probed via a one-off query() call otherwise.