跳转至

apogee-ai-search

Hybrid retrieval (BM25 + dense + reranker) over apogee-core index abstractions.

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_search import X works for each name.

Layer Symbols
Application · DTOs BenchDTO, IndexDTO, QueryDTO
Application · Use cases BenchSearchUseCase, BulkIndexUseCase, IndexDocumentsUseCase, SearchUseCase
Domain SearchDocument, SearchHit, SearchQuery, SearchResult
Domain · Enums IndexKind, SearcherKind
Domain · Exceptions IndexNotReadyError, SearchError
Domain · Protocols (ports) IIndex, ISearcher
Infrastructure BM25Searcher, HybridSearcher, InMemoryInvertedIndex, InMemoryVectorIndex, VectorSearcher, cosine, tokenize

Install

Bash
pip install apogee-ai-search

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

Extra Pulls in
elasticsearch elasticsearch>=8.13
opensearch opensearch-py>=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-search --help