"""
Offline RAG Indexer module.

提供完整的离线索引构建功能，包括：
- 文档加载（PDF、Word、TXT 等）
- 文本切分（递归、语义、父子块）
- 向量嵌入（支持 llama.cpp）
- 向量存储（Qdrant）
- 父文档存储（PostgreSQL）

示例用法：
    >>> from rag_indexer import IndexBuilder, IndexBuilderConfig, SplitterType
    >>> 
    >>> config = IndexBuilderConfig(
    ...     collection_name="my_docs",
    ...     splitter_type=SplitterType.PARENT_CHILD,
    ... )
    >>> builder = IndexBuilder(config)
    >>> 
    >>> # 或直接传参（向后兼容）
    >>> builder = IndexBuilder(collection_name="my_docs")
    >>> 
    >>> await builder.build_from_file("document.pdf")
"""

from .index_builder import IndexBuilder, IndexBuilderConfig, DocstoreConfig
from .loaders import DocumentLoader
from .splitters import SplitterType, get_splitter
from .config import (
    QDRANT_URL,
    QDRANT_API_KEY,
    LLAMACPP_EMBEDDING_URL,
    LLAMACPP_API_KEY,
    DB_URI,
    DOCSTORE_URI,
    RAG_OCR_LANGUAGES,
    RAG_DOC_LANGUAGES,
)

# 从 rag_core 重新导出常用组件
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent / "backend"))

from backend.rag_core import (
    LlamaCppEmbedder,
    QdrantVectorStore,
    PostgresDocStore,
    create_docstore,
)

__version__ = "2.0.0"

__all__ = [
    # 核心构建器与配置
    "IndexBuilder",
    "IndexBuilderConfig",
    "DocstoreConfig",
    
    # 加载器
    "DocumentLoader",
    
    # 切分相关
    "SplitterType",
    "get_splitter",
    
    # 配置
    "QDRANT_URL",
    "QDRANT_API_KEY",
    "LLAMACPP_EMBEDDING_URL",
    "LLAMACPP_API_KEY",
    "DB_URI",
    "DOCSTORE_URI",
    "RAG_OCR_LANGUAGES",
    "RAG_DOC_LANGUAGES",
    
    # 嵌入与向量存储
    "LlamaCppEmbedder",
    "QdrantVectorStore",
    
    # 文档存储
    "PostgresDocStore",
    "create_docstore",
]