Package Methods (0.2.3)

_get_iam_principal_email(credentials: google.auth.credentials.Credentials) -> str

PostgresChatStore( key: object, engine: PostgresEngine, chat_store: AsyncPostgresChatStore )

add_message( key: str, message: llama_index.core.base.llms.types.ChatMessage ) -> None

adelete_last_message( key: str, ) -> typing.Optional[llama_index.core.base.llms.types.ChatMessage]

adelete_message( key: str, idx: int ) -> typing.Optional[llama_index.core.base.llms.types.ChatMessage]

adelete_messages( key: str, ) -> typing.Optional[typing.List[llama_index.core.base.llms.types.ChatMessage]]

aget_keys() -> typing.List[str]

aget_messages( key: str, ) -> typing.List[llama_index.core.base.llms.types.ChatMessage]

aset_messages( key: str, messages: typing.List[llama_index.core.base.llms.types.ChatMessage] ) -> None

async_add_message( key: str, message: llama_index.core.base.llms.types.ChatMessage ) -> None

class_name() -> str

create( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, table_name: str, schema_name: str = "public", ) -> llama_index_cloud_sql_pg.chat_store.PostgresChatStore

create_sync( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, table_name: str, schema_name: str = "public", ) -> llama_index_cloud_sql_pg.chat_store.PostgresChatStore

delete_last_message( key: str, ) -> typing.Optional[llama_index.core.base.llms.types.ChatMessage]

delete_message( key: str, idx: int ) -> typing.Optional[llama_index.core.base.llms.types.ChatMessage]

delete_messages( key: str, ) -> typing.Optional[typing.List[llama_index.core.base.llms.types.ChatMessage]]

get_keys() -> typing.List[str]

get_messages(key: str) -> typing.List[llama_index.core.base.llms.types.ChatMessage]

model_post_init(context: Any, /) -> None

set_messages( key: str, messages: typing.List[llama_index.core.base.llms.types.ChatMessage] ) -> None

PostgresDocumentStore( key: object, engine: llama_index_cloud_sql_pg.engine.PostgresEngine, document_store: llama_index_cloud_sql_pg.async_document_store.AsyncPostgresDocumentStore, )

add_documents( docs: typing.Sequence[llama_index.core.schema.BaseNode], allow_update: bool = True, batch_size: int = 1, store_text: bool = True, ) -> None

adelete_document(doc_id: str, raise_error: bool = True) -> None

adelete_ref_doc(ref_doc_id: str, raise_error: bool = True) -> None

adocument_exists(doc_id: str) -> bool

aget_all_document_hashes() -> dict[str, str]

aget_all_ref_doc_info() -> ( typing.Optional[dict[str, llama_index.core.storage.docstore.types.RefDocInfo]] )

aget_document( doc_id: str, raise_error: bool = True ) -> typing.Optional[llama_index.core.schema.BaseNode]

aget_document_hash(doc_id: str) -> typing.Optional[str]

aget_ref_doc_info( ref_doc_id: str, ) -> typing.Optional[llama_index.core.storage.docstore.types.RefDocInfo]

aref_doc_exists(ref_doc_id: str) -> bool

aset_document_hash(doc_id: str, doc_hash: str) -> None

aset_document_hashes(doc_hashes: dict[str, str]) -> None

async_add_documents( docs: typing.Sequence[llama_index.core.schema.BaseNode], allow_update: bool = True, batch_size: int = 1, store_text: bool = True, ) -> None

create( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, table_name: str, schema_name: str = "public", batch_size: int = 1, ) -> llama_index_cloud_sql_pg.document_store.PostgresDocumentStore

create_sync( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, table_name: str, schema_name: str = "public", batch_size: int = 1, ) -> llama_index_cloud_sql_pg.document_store.PostgresDocumentStore

delete_document(doc_id: str, raise_error: bool = True) -> None

delete_ref_doc(ref_doc_id: str, raise_error: bool = True) -> None

document_exists(doc_id: str) -> bool

get_all_document_hashes() -> dict[str, str]

get_all_ref_doc_info() -> ( typing.Optional[dict[str, llama_index.core.storage.docstore.types.RefDocInfo]] )

get_document( doc_id: str, raise_error: bool = True ) -> typing.Optional[llama_index.core.schema.BaseNode]

get_document_hash(doc_id: str) -> typing.Optional[str]

get_ref_doc_info( ref_doc_id: str, ) -> typing.Optional[llama_index.core.storage.docstore.types.RefDocInfo]

ref_doc_exists(ref_doc_id: str) -> bool

set_document_hash(doc_id: str, doc_hash: str) -> None

set_document_hashes(doc_hashes: dict[str, str]) -> None

__post_init__()

PostgresEngine( key: object, pool: sqlalchemy.ext.asyncio.engine.AsyncEngine, loop: typing.Optional[asyncio.events.AbstractEventLoop], thread: typing.Optional[threading.Thread], )

_ainit_chat_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

_ainit_doc_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

_ainit_index_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

_ainit_vector_store_table( table_name: str, vector_size: int, schema_name: str = "public", id_column: typing.Union[str, llama_index_cloud_sql_pg.engine.Column] = "node_id", text_column: str = "text", embedding_column: str = "embedding", metadata_json_column: str = "li_metadata", metadata_columns: list[llama_index_cloud_sql_pg.engine.Column] = [], ref_doc_id_column: str = "ref_doc_id", node_column: str = "node_data", stores_text: bool = True, overwrite_existing: bool = False, ) -> None

_aload_table_schema( table_name: str, schema_name: str = "public" ) -> sqlalchemy.sql.schema.Table

_create( project_id: str, region: str, instance: str, database: str, ip_type: typing.Union[str, google.cloud.sql.connector.enums.IPTypes], user: typing.Optional[str] = None, password: typing.Optional[str] = None, loop: typing.Optional[asyncio.events.AbstractEventLoop] = None, thread: typing.Optional[threading.Thread] = None, quota_project: typing.Optional[str] = None, iam_account_email: typing.Optional[str] = None, ) -> llama_index_cloud_sql_pg.engine.PostgresEngine

_run_as_async( coro: typing.Awaitable[llama_index_cloud_sql_pg.engine.T], ) -> llama_index_cloud_sql_pg.engine.T

_run_as_sync( coro: typing.Awaitable[llama_index_cloud_sql_pg.engine.T], ) -> llama_index_cloud_sql_pg.engine.T

afrom_instance( project_id: str, region: str, instance: str, database: str, user: typing.Optional[str] = None, password: typing.Optional[str] = None, ip_type: typing.Union[ str, google.cloud.sql.connector.enums.IPTypes ] = IPTypes.PUBLIC, quota_project: typing.Optional[str] = None, iam_account_email: typing.Optional[str] = None, ) -> llama_index_cloud_sql_pg.engine.PostgresEngine

ainit_chat_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

ainit_doc_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

ainit_index_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

ainit_vector_store_table( table_name: str, vector_size: int, schema_name: str = "public", id_column: typing.Union[str, llama_index_cloud_sql_pg.engine.Column] = "node_id", text_column: str = "text", embedding_column: str = "embedding", metadata_json_column: str = "li_metadata", metadata_columns: list[llama_index_cloud_sql_pg.engine.Column] = [], ref_doc_id_column: str = "ref_doc_id", node_column: str = "node_data", stores_text: bool = True, overwrite_existing: bool = False, ) -> None

close() -> None

from_engine( engine: sqlalchemy.ext.asyncio.engine.AsyncEngine, loop: typing.Optional[asyncio.events.AbstractEventLoop] = None, ) -> llama_index_cloud_sql_pg.engine.PostgresEngine

from_engine_args( url: typing.Union[str, sqlalchemy.engine.url.URL], **kwargs: typing.Any ) -> llama_index_cloud_sql_pg.engine.PostgresEngine

from_instance( project_id: str, region: str, instance: str, database: str, user: typing.Optional[str] = None, password: typing.Optional[str] = None, ip_type: typing.Union[ str, google.cloud.sql.connector.enums.IPTypes ] = IPTypes.PUBLIC, quota_project: typing.Optional[str] = None, iam_account_email: typing.Optional[str] = None, ) -> llama_index_cloud_sql_pg.engine.PostgresEngine

init_chat_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

init_doc_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

init_index_store_table( table_name: str, schema_name: str = "public", overwrite_existing: bool = False ) -> None

init_vector_store_table( table_name: str, vector_size: int, schema_name: str = "public", id_column: typing.Union[str, llama_index_cloud_sql_pg.engine.Column] = "node_id", text_column: str = "text", embedding_column: str = "embedding", metadata_json_column: str = "li_metadata", metadata_columns: list[llama_index_cloud_sql_pg.engine.Column] = [], ref_doc_id_column: str = "ref_doc_id", node_column: str = "node_data", stores_text: bool = True, overwrite_existing: bool = False, ) -> None

PostgresIndexStore( key: object, engine: llama_index_cloud_sql_pg.engine.PostgresEngine, index_store: llama_index_cloud_sql_pg.async_index_store.AsyncPostgresIndexStore, )

aadd_index_struct( index_struct: llama_index.core.data_structs.data_structs.IndexStruct, ) -> None

add_index_struct( index_struct: llama_index.core.data_structs.data_structs.IndexStruct, ) -> None

adelete_index_struct(key: str) -> None

aget_index_struct( struct_id: typing.Optional[str] = None, ) -> typing.Optional[llama_index.core.data_structs.data_structs.IndexStruct]

aindex_structs() -> list[llama_index.core.data_structs.data_structs.IndexStruct]

async_add_index_struct( index_struct: llama_index.core.data_structs.data_structs.IndexStruct, ) -> None

async_index_structs() -> ( list[llama_index.core.data_structs.data_structs.IndexStruct] )

create( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, table_name: str, schema_name: str = "public", ) -> llama_index_cloud_sql_pg.index_store.PostgresIndexStore

create_sync( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, table_name: str, schema_name: str = "public", ) -> llama_index_cloud_sql_pg.index_store.PostgresIndexStore

delete_index_struct(key: str) -> None

get_index_struct( struct_id: typing.Optional[str] = None, ) -> typing.Optional[llama_index.core.data_structs.data_structs.IndexStruct]

index_structs() -> list[llama_index.core.data_structs.data_structs.IndexStruct]

index_options() -> str

_generate_next_value_(start, count, last_values)

index_options() -> str

to_string() -> str

index_options() -> str

to_string() -> str

to_string() -> str

PostgresReader( key: object, engine: PostgresEngine, reader: AsyncPostgresReader, is_remote: bool = True, )

alazy_load_data() -> typing.AsyncIterable[llama_index.core.schema.Document]

aload_data() -> list[llama_index.core.schema.Document]

class_name() -> str

create( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, query: typing.Optional[str] = None, table_name: typing.Optional[str] = None, schema_name: str = "public", content_columns: typing.Optional[list[str]] = None, metadata_columns: typing.Optional[list[str]] = None, metadata_json_column: typing.Optional[str] = None, format: typing.Optional[str] = None, formatter: typing.Optional[typing.Callable] = None, is_remote: bool = True, ) -> llama_index_cloud_sql_pg.reader.PostgresReader

create_sync( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, query: typing.Optional[str] = None, table_name: typing.Optional[str] = None, schema_name: str = "public", content_columns: typing.Optional[list[str]] = None, metadata_columns: typing.Optional[list[str]] = None, metadata_json_column: typing.Optional[str] = None, format: typing.Optional[str] = None, formatter: typing.Optional[typing.Callable] = None, is_remote: bool = True, ) -> llama_index_cloud_sql_pg.reader.PostgresReader

lazy_load_data() -> typing.Iterable[llama_index.core.schema.Document]

load_data() -> list[llama_index.core.schema.Document]

model_post_init(context: Any, /) -> None

PostgresVectorStore( key: object, engine: PostgresEngine, vs: AsyncPostgresVectorStore, stores_text: bool = True, is_embedding_query: bool = True, )

aapply_vector_index( index: llama_index_cloud_sql_pg.indexes.BaseIndex, name: typing.Optional[str] = None, concurrently: bool = False, ) -> None

aclear() -> None

add( nodes: typing.Sequence[llama_index.core.schema.BaseNode], **add_kwargs: typing.Any ) -> list[str]

adelete(ref_doc_id: str, **delete_kwargs: typing.Any) -> None

adelete_nodes( node_ids: typing.Optional[list[str]] = None, filters: typing.Optional[ llama_index.core.vector_stores.types.MetadataFilters ] = None, **delete_kwargs: typing.Any ) -> None

adrop_vector_index(index_name: typing.Optional[str] = None) -> None

aget_nodes( node_ids: typing.Optional[list[str]] = None, filters: typing.Optional[ llama_index.core.vector_stores.types.MetadataFilters ] = None, ) -> list[llama_index.core.schema.BaseNode]

ais_valid_index(index_name: typing.Optional[str] = None) -> bool

apply_vector_index( index: llama_index_cloud_sql_pg.indexes.BaseIndex, name: typing.Optional[str] = None, concurrently: bool = False, ) -> None

aquery( query: llama_index.core.vector_stores.types.VectorStoreQuery, **kwargs: typing.Any ) -> llama_index.core.vector_stores.types.VectorStoreQueryResult

areindex(index_name: typing.Optional[str] = None) -> None

aset_maintenance_work_mem(num_leaves: int, vector_size: int) -> None

async_add( nodes: typing.Sequence[llama_index.core.schema.BaseNode], **kwargs: typing.Any ) -> list[str]

class_name() -> str

clear() -> None

create( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, table_name: str, schema_name: str = "public", id_column: str = "node_id", text_column: str = "text", embedding_column: str = "embedding", metadata_json_column: str = "li_metadata", metadata_columns: list[str] = [], ref_doc_id_column: str = "ref_doc_id", node_column: str = "node_data", stores_text: bool = True, is_embedding_query: bool = True, distance_strategy: llama_index_cloud_sql_pg.indexes.DistanceStrategy = DistanceStrategy.COSINE_DISTANCE, index_query_options: typing.Optional[ llama_index_cloud_sql_pg.indexes.QueryOptions ] = None, ) -> llama_index_cloud_sql_pg.vector_store.PostgresVectorStore

create_sync( engine: llama_index_cloud_sql_pg.engine.PostgresEngine, table_name: str, schema_name: str = "public", id_column: str = "node_id", text_column: str = "text", embedding_column: str = "embedding", metadata_json_column: str = "li_metadata", metadata_columns: list[str] = [], ref_doc_id_column: str = "ref_doc_id", node_column: str = "node_data", stores_text: bool = True, is_embedding_query: bool = True, distance_strategy: llama_index_cloud_sql_pg.indexes.DistanceStrategy = DistanceStrategy.COSINE_DISTANCE, index_query_options: typing.Optional[ llama_index_cloud_sql_pg.indexes.QueryOptions ] = None, ) -> llama_index_cloud_sql_pg.vector_store.PostgresVectorStore

delete(ref_doc_id: str, **delete_kwargs: typing.Any) -> None

delete_nodes( node_ids: typing.Optional[list[str]] = None, filters: typing.Optional[ llama_index.core.vector_stores.types.MetadataFilters ] = None, **delete_kwargs: typing.Any ) -> None

drop_vector_index(index_name: typing.Optional[str] = None) -> None

get_nodes( node_ids: typing.Optional[list[str]] = None, filters: typing.Optional[ llama_index.core.vector_stores.types.MetadataFilters ] = None, ) -> list[llama_index.core.schema.BaseNode]

is_valid_index(index_name: typing.Optional[str] = None) -> bool

model_post_init(context: Any, /) -> None

query( query: llama_index.core.vector_stores.types.VectorStoreQuery, **kwargs: typing.Any ) -> llama_index.core.vector_stores.types.VectorStoreQueryResult

reindex(index_name: typing.Optional[str] = None) -> None

set_maintenance_work_mem(num_leaves: int, vector_size: int) -> None