Skip to content

General

General configuration options that don't fit elsewhere.

keyword

keyword: boolean

Enables sparse keyword indexing for this embeddings.

When enabled, this parameter creates a BM25 index for full text search. It also implicitly disables the defaults setting for vector search.

hybrid

hybrid: boolean

Enables hybrid (sparse + dense) indexing for this embeddings.

When enabled, this parameter creates a BM25 index for full text search. It has no effect on the defaults or path settings.

indexes

indexes: dict

Key value pairs defining subindexes for this embeddings. Each key is the index name and the value is the full configuration. This configuration can use any of the available configurations in a standard embeddings instance.

autoid

format: int|uuid function

Sets the auto id generation method. When this is not set, an autogenerated numeric sequence is used. This also supports UUID generation functions. For example, setting this value to uuid4 will generate random UUIDs. Setting this to uuid5 will generate deterministic UUIDs for each input data row.

columns

columns:
    text: name of the text column
    object: name of the object column

Sets the text and object column names. Defaults to text and object if not provided.

format

format: json|pickle

Sets the configuration storage format. Defaults to json.