jeevesagent.vectorstore.chroma

Chroma-backed vector store.

Wraps chromadb for persistent on-disk or hosted Chroma. Lazy import — install via pip install 'jeevesagent[vectorstore-chroma]'.

Embeddings come from our framework’s Embedder protocol so swapping embedders works the same across every vector store. We pass None as Chroma’s embedding_function and supply embeddings ourselves at add time.

Filter operators are translated from our Mongo-style language to Chroma’s native where syntax (which already speaks Mongo-ish $eq / $in / $gt etc., so the translation is mostly direct).

Classes

ChromaVectorStore

Vector store backed by chromadb.

Module Contents

class jeevesagent.vectorstore.chroma.ChromaVectorStore(embedder: jeevesagent.core.protocols.Embedder, *, collection_name: str = 'jeeves_vectors', persist_directory: str | None = None, client: Any = None)

Vector store backed by chromadb.

async add(chunks: list[jeevesagent.loader.base.Chunk], ids: list[str] | None = None) → list[str]

async count() → int

async delete(ids: list[str]) → None

classmethod from_chunks(chunks: list[jeevesagent.loader.base.Chunk], *, embedder: jeevesagent.core.protocols.Embedder, ids: list[str] | None = None, collection_name: str = 'jeeves_vectors', persist_directory: str | None = None, client: Any = None) → ChromaVectorStore

Async:

One-shot: construct a ChromaVectorStore + add chunks.

classmethod from_texts(texts: list[str], *, embedder: jeevesagent.core.protocols.Embedder, metadatas: list[dict[str, Any]] | None = None, ids: list[str] | None = None, collection_name: str = 'jeeves_vectors', persist_directory: str | None = None, client: Any = None) → ChromaVectorStore

Async:

One-shot: construct a ChromaVectorStore from raw text strings (each becomes a Chunk with the matching metadata dict, or empty if metadatas is None).

async get_by_ids(ids: list[str]) → list[jeevesagent.loader.base.Chunk]

async search(query: str, *, k: int = 4, filter: collections.abc.Mapping[str, Any] | None = None, diversity: float | None = None) → list[jeevesagent.vectorstore.base.SearchResult]

async search_by_vector(vector: list[float], *, k: int = 4, filter: collections.abc.Mapping[str, Any] | None = None, diversity: float | None = None) → list[jeevesagent.vectorstore.base.SearchResult]

property embedder: jeevesagent.core.protocols.Embedder

name = 'chroma'