Saltar a contenido

apogee-ai-data

DVC-style versioning + synthetic data + labelling + feature store, all in one package.

This page is being expanded

The tables below are generated from the package source, so they are accurate. Narrative guides and worked examples are being written module by module.

Public API

Everything below is exported from the package root, so from apogee_ai_data import X works for each name.

Layer Symbols
Application · DTOs BenchDTO, ChunkDTO, IndexDTO, LoadDTO, RetrieveDTO
Application · Use cases BenchRetrievalUseCase, ChunkDocumentsUseCase, IndexDocumentsUseCase, LoadDocumentsUseCase, RetrieveUseCase
Domain Chunk, ChunkPolicy, Dataset, Document, Embedding, RetrievalHit, RetrievalQuery, RetrievalResult
Domain · Enums ChunkerKind, DocumentKind, EmbedderKind, RetrieverKind, VectorStoreKind
Domain · Exceptions ChunkerError, DataError, EmbedderError, LoaderError, RetrievalError, VectorStoreError
Domain · Protocols (ports) IChunker, ILoader, IRetriever, ITextEmbedder, IVectorStore
Infrastructure BM25Retriever, CodeLoader, DenseRetriever, FaissVectorStore, FixedSizeChunker, HashingTextEmbedder, HtmlLoader, HybridRetriever, InMemoryVectorStore, JsonVectorStore, JsonlLoader, MarkdownLoader, PdfLoader, RecursiveChunker, SentenceTransformersEmbedder, TextLoader, TokenChunker

Install

Bash
pip install apogee-ai-data

The base install has no required third-party dependency. Each extra unlocks one adapter.

Extra Pulls in
pdf pypdf>=4.0
markdown markdown>=3.5
html beautifulsoup4>=4.12
faiss faiss-cpu>=1.7
qdrant qdrant-client>=1.7
chroma chromadb>=0.4
sentence-transformers sentence-transformers>=2.5

CLI

Installed as a console script, and registered as an apogee plugin so the same subcommands work under the global binary.

Bash
apogee-data --help