Embedding Functions

Embedding Function Base Classes

EmbeddingFunction

Protocol for embedding functions. To implement a new embedding function, you need to implement the following methods:

init
call
name
build_from_config
get_config

Additionally, you should register the embedding function so it will automatically be used by the Chroma client.

@register_embedding_function
class MyEmbeddingFunction(EmbeddingFunction[Documents]):
    ...

Methods __init__(), build_from_config(), default_space(), embed_query(), embed_with_retries(), get_config(), is_legacy(), name(), supported_spaces(), validate_config(), validate_config_update()

SparseEmbeddingFunction

Protocol for sparse embedding functions. To implement a new sparse embedding function, you need to implement the following methods:

call
init
name
build_from_config
get_config

Methods __init__(), build_from_config(), embed_query(), embed_with_retries(), get_config(), name(), validate_config(), validate_config_update()

Registration

register_embedding_function

@register_embedding_function
class MyEmbedding(EmbeddingFunction):
    @classmethod
    def name(cls): return "my_embedding"

Or directly:

register_embedding_function(MyEmbedding)

Any

The embedding function class to register.

register_sparse_embedding_function

@register_sparse_embedding_function
class MySparseEmbeddingFunction(SparseEmbeddingFunction):
    @classmethod
    def name(cls): return "my_sparse_embedding"

Any

Types

Embedding

Embedding[Tuple[Any, Ellipsis], dtype[Union[int32, float32]]]

SparseVector

Sparse vector using parallel indices and values arrays. Properties

List[int]

List[float]

Optional[IDs]

Methods __init__(), from_dict(), to_dict()

Self-Hosted Chroma

SDKs

Beta SDKs

APIs

Dictionary Syntax

Architecture

Embedding Function Base Classes