e8f00fcff4
haiku.rag.config exported two configuration instances: the lazy _config behind get_config/set_config, and Config, loaded at import time. Nothing linked them, and eleven signatures captured Config as a default argument, so set_config could not reach the factories, the client, the store or the MCP server. reranking/base.py went further and snapshotted the configured reranker name into a class attribute at import. Config is removed. Internal defaults are config: AppConfig | None = None, resolved through get_config() per call. RerankerBase._model is None and CohereReranker takes its model name as an argument, like every other reranker. The suite patched attributes on Config while production read the instance get_config() returns, a different object, so those patches were no-ops waiting to happen. They now go through get_config().
32 lines
1 KiB
Python
32 lines
1 KiB
Python
"""Document chunker abstraction for haiku.rag."""
|
|
|
|
from haiku.rag.chunkers.base import DocumentChunker
|
|
from haiku.rag.config import AppConfig, get_config
|
|
|
|
__all__ = ["DocumentChunker", "get_chunker"]
|
|
|
|
|
|
def get_chunker(config: AppConfig | None = None) -> DocumentChunker:
|
|
"""Get a document chunker instance based on configuration.
|
|
|
|
Args:
|
|
config: Configuration to use. Defaults to the current global config.
|
|
|
|
Returns:
|
|
DocumentChunker instance configured according to the config.
|
|
|
|
Raises:
|
|
ValueError: If the chunker provider is not recognized.
|
|
"""
|
|
config = config if config is not None else get_config()
|
|
if config.processing.chunker == "docling-local":
|
|
from haiku.rag.chunkers.docling_local import DoclingLocalChunker
|
|
|
|
return DoclingLocalChunker(config)
|
|
|
|
if config.processing.chunker == "docling-serve":
|
|
from haiku.rag.chunkers.docling_serve import DoclingServeChunker
|
|
|
|
return DoclingServeChunker(config)
|
|
|
|
raise ValueError(f"Unsupported chunker: {config.processing.chunker}")
|