agrag.embedding

Text embedding: turn strings into dense vectors.

Modules:

• base – The Embedder and EmbeddingCache protocols.
• errors – Errors that the embedding layer raises.
• fastembed_bm25 – BM25 sparse embedder backed by FastEmbed.
• fastembed_dense – Dense embedder backed by FastEmbed and ONNX Runtime.
• sentence_transformers – Sentence-transformers embedder implementation.
• settings – Settings for the dense embedders.
• sparse_base – Sparse lexical vectors and the sparse embedder protocol.

Classes:

• Embedder – A component that turns text into dense embedding vectors.
• EmbeddingSettings – Configuration shared by the FastEmbed and sentence-transformers embedders.
• FastEmbedBM25Embedder – A sparse BM25 embedder built on FastEmbed.
• FastEmbedEmbedder – A dense embedder built on FastEmbed, which runs ONNX models on the CPU.
• SentenceTransformerEmbedder – An embedder backed by sentence-transformers.
• SparseEmbedder – A component that turns text into sparse lexical vectors, for hybrid search.
• SparseVector – A sparse vector: nonzero indices and their values.

Functions:

• build_embedder – Build an embedder from a model name, or return an embedder unchanged.