rag/config.py

from __future__ import annotations

from dataclasses import dataclass


@dataclass(frozen=True)
class Settings:
    # Hugging Face dataset
    dataset_name: str = "rag-datasets/rag-mini-wikipedia"
    corpus_config: str = "text-corpus"
    qa_config: str = "question-answer"

    # Chunking
    chunk_chars: int = 900
    overlap_chars: int = 150

    # Retrieval
    top_k_bm25: int = 8
    top_k_dense: int = 8
    top_k_final: int = 6

    # Dense model
    embed_model: str = "sentence-transformers/all-MiniLM-L6-v2"

    # Optional reranker
    rerank_model: str = "cross-encoder/ms-marco-MiniLM-L-6-v2"
    rerank_top_n: int = 20  # candidates to rerank

    # OpenAI
    default_openai_model: str = "gpt-4o-mini"

    # Artifacts
    artifacts_dir: str = "artifacts"
    chunks_jsonl: str = "chunks.jsonl"
    embeddings_npy: str = "embeddings.npy"


SETTINGS = Settings()