Fulltext

Elasticsearch implementation of fulltext search and CRUD capability.

ElasticsearchFulltextCapability(index_name, client, query_field='text', encryption=None, default_batch_size=None)

Bases: ElasticLikeCore, BaseFulltextCapability

Elasticsearch implementation of FulltextCapability protocol.

This class provides document CRUD operations and flexible querying using Elasticsearch.

Attributes:

Name	Type	Description
index_name	str	The name of the Elasticsearch index.
client	AsyncElasticsearch	AsyncElasticsearch client.
query_field	str	The field name to use for text content.

Initialize the Elasticsearch fulltext capability.

Parameters:

Name	Type	Description	Default
index_name	str	The name of the Elasticsearch index.	required
client	AsyncElasticsearch	The Elasticsearch client.	required
query_field	str	The field name to use for text content. Defaults to "text".	'text'
encryption	EncryptionCapability | None	Encryption capability for field-level encryption. Defaults to None.	None
default_batch_size	int | None	Default batch size for operations. Defaults to None.	None

delete_by_id(id_) async

Deletes records from the data store based on IDs.

Parameters:

Name	Type	Description	Default
id_	str | list[str]	ID or list of IDs to delete.	required

get_size() async

Returns the total number of documents in the index.

Returns:

Name	Type	Description
int	int	The total number of documents.

retrieve(strategy=SupportedQueryMethods.BY_FIELD, query=None, filters=None, options=None, **kwargs) async

retrieve(strategy: Literal[SupportedQueryMethods.BY_FIELD] | None = SupportedQueryMethods.BY_FIELD, query: str | None = None, filters: FilterClause | QueryFilter | None = None, options: QueryOptions | None = None, **kwargs: Any) -> list[Chunk]

retrieve(strategy: Literal[SupportedQueryMethods.BM25], query: str, filters: FilterClause | QueryFilter | None = None, options: QueryOptions | None = None, k1: float | None = None, b: float | None = None, **kwargs: Any) -> list[Chunk]

retrieve(strategy: Literal[SupportedQueryMethods.AUTOCOMPLETE], query: str, field: str, size: int = 20, fuzzy_tolerance: int = 1, min_prefix_length: int = 3, filter_query: dict[str, Any] | None = None, **kwargs: Any) -> list[str]

retrieve(strategy: Literal[SupportedQueryMethods.AUTOSUGGEST], query: str, search_fields: list[str], autocomplete_field: str, size: int = 20, min_length: int = 3, filter_query: dict[str, Any] | None = None, **kwargs: Any) -> list[str]

retrieve(strategy: Literal[SupportedQueryMethods.SHINGLES], query: str, field: str, size: int = 20, min_length: int = 3, max_length: int = 30, filter_query: dict[str, Any] | None = None, **kwargs: Any) -> list[str]

Public implementation for retrieving records from the datastore.

This method supports multiple retrieval strategies including fulltext search (BM25), metadata filtering (BY_FIELD), and autocomplete/autosuggest features. It handles validation and dispatching to the appropriate internal method.

Parameters:

Name	Type	Description	Default
strategy	SupportedQueryMethods	The retrieval strategy to use. Defaults to BY_FIELD.	BY_FIELD
query	str | None	The query string for text-based strategies. Required for strategies other than BY_FIELD.	None
filters	FilterClause | QueryFilter | None	Query filters to restrict the search results.	None
options	QueryOptions | None	Query options for sorting, pagination, and field selection.	None
**kwargs	Any	Additional strategy-specific parameters passed to the implementation.	{}

Returns:

Type	Description
list[Chunk] | list[str]	list[Chunk] | list[str]: A list of Chunks for document retrieval strategies, or a list of strings for suggestion strategies (autocomplete, autosuggest, shingles).

Examples:

from gllm_datastore.core.filters import filter as F

# Field-based retrieval with direct FilterClause
results = await data_store.retrieve(
    strategy=SupportedQueryMethods.BY_FIELD,
    filters=F.eq("metadata.category", "AI")
)

# BM25 keyword search
results = await data_store.retrieve(
    strategy=SupportedQueryMethods.BM25,
    query="machine learning",
    options=QueryOptions(limit=10)
)

# Autocomplete suggestions
suggestions = await data_store.retrieve(
    strategy=SupportedQueryMethods.AUTOCOMPLETE,
    query="artificial",
    field="title"
)

Raises:

Type	Description
ValueError	If the query is missing for strategies that require it, or if an unsupported strategy is provided.

SupportedQueryMethods

Bases: StrEnum

Supported query methods for Elasticsearch fulltext capability.