Embedding

Embedding & Vector Store Primitives

Platform contract for configuring embedding models and vector stores.

Scope (intentionally minimal):

• How to reference an embedding model (provider + model name + secret).

• How to reference a vector store (provider + connection).

NOT in scope (these belong to application code, not the platform):

• Chunking strategies (fixed/semantic/recursive/markdown).

• Retrieval pipelines (rerankers, multi-stage retrieval, filters).

• Document loaders / ingestion DSLs.

• End-to-end RAG pipeline orchestration.

These were removed in v1 because they describe one specific way to

build a RAG application; the platform's job is to expose the embed +

vector primitives so any RAG strategy can be built on top.

TypeScript Usage

import { EmbeddingModel, VectorStore, VectorStoreProvider } from '@objectstack/spec/ai';
import type { EmbeddingModel, VectorStore, VectorStoreProvider } from '@objectstack/spec/ai';

// Validate data
const result = EmbeddingModel.parse(data);

EmbeddingModel

Properties

VectorStore

Properties

VectorStoreProvider

Allowed Values

• pgvector
• chroma
• qdrant
• pinecone
• weaviate
• milvus
• redis
• opensearch
• elasticsearch
• custom