osyra_ome.adapters.llamaindex.vector_store

Private pre-release / network boundary: The currently usable customer surface is offline verification of an existing signed artifact against an out-of-band trust anchor. Memory/network RPC APIs and host snippets on this page describe protocol and interface shape; the public Edge bridge, package publication, and release acceptance remain pending. Do not treat api.osyra.ai:443 examples as a released customer route.

LlamaIndex :class:`BasePydanticVectorStore` audit-decorator over OME.

Same design as the LangChain vector-store adapter: pair any LlamaIndex :class:`BasePydanticVectorStore` implementation (Chroma, FAISS, Pinecone, Postgres) with the OME memory namespace so every :meth:`add` produces an audit-grade :class:`~osyra_ome.Claim`. :meth:`query` itself is delegated through unchanged.

Classes

class OmeVectorStore

Bases: BasePydanticVectorStore

LlamaIndex VectorStore audit-decorator over a delegate index.

Args: client: OmeClient bound to the destination workspace. delegate: any LlamaIndex :class:BasePydanticVectorStore. workspace_id: OME workspace identifier. If omitted, defers to the workspace_id bound on the wrapped client. collection: logical collection name; encoded into subject_id of every emitted Claim (did:web:collection.osyra.ai/<collection>).

BasePydanticVectorStore abstract methods covered: add, delete, query, client

Attributes

| Name | Type | Default | | --- | --- | --- | | is_embedding_query | bool | True | | stores_text | bool | True |

Methods

__init__

def __init__(self, *, client: OmeClient, delegate: BasePydanticVectorStore, workspace_id: str | None = None, collection: str = 'default') -> None

add

def add(self, nodes: Sequence[BaseNode], **kwargs: Any) -> list[str]

Persist nodes to the delegate AND to OME as Claims.

class_name @classmethod

def class_name(cls) -> str

client @property

def client(self) -> Any

Underlying delegate's client handle (per abstract).

delegate @property

def delegate(self) -> BasePydanticVectorStore

delete

def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None

query

def query(self, query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult

workspace_id @property

def workspace_id(self) -> str

written_claim_ids @property

def written_claim_ids(self) -> tuple[str, ...]