72ef18e39d
Every section inherited plain BaseModel, so unknown keys were dropped silently: providers.docling_serve.timeout was documented for months while being ignored, and a typo in any setting took the default. Sections now derive from ConfigModel, which forbids extras, so a stale or misspelled key fails with its path. This already found search.context_radius in a live app config and providers.vllm in soliplex's example. converter, chunker and chunker_type are Literals. Sizes, limits, dimensions, token budgets, attempt counts and breaker thresholds must be positive; retention, delays, intervals and cooldowns non-negative; similarity_threshold within 0-1; port within 0-65535. port 0 keeps its OS-assigned meaning and worker_count allows 0 for an API-and-reaper-only process. get_reranker caught ImportError and returned None, so a configured reranker whose extra was missing silently disappeared. It now propagates. raise_missing_extra names the install command and re-raises when the failure came from inside an installed package, so a broken transitive import is not reported as a missing one. zeroentropy imported bare and now guards like the others. The haiku.rag package declares the jina extra. jina-local already worked there through cross-encoder's transitive transformers and torch; the resolved package set is unchanged, but the support is now promised rather than inherited. Provider fields stay unconstrained: get_model ends in a pass-through to pydantic-ai for any provider it supports, so a Literal there would reject valid configurations.
48 lines
1.6 KiB
Python
48 lines
1.6 KiB
Python
from haiku.rag.utils import raise_missing_extra
|
|
|
|
try:
|
|
from zeroentropy import AsyncZeroEntropy
|
|
except ModuleNotFoundError as e: # pragma: no cover
|
|
raise_missing_extra("zeroentropy", "zeroentropy", e)
|
|
|
|
from haiku.rag.reranking.base import RerankerBase
|
|
from haiku.rag.store.models.chunk import Chunk
|
|
|
|
|
|
class ZeroEntropyReranker(RerankerBase): # pragma: no cover
|
|
"""Zero Entropy reranker implementation using the zerank-1 model."""
|
|
|
|
def __init__(self, model: str = "zerank-1"):
|
|
"""Initialize the Zero Entropy reranker.
|
|
|
|
Args:
|
|
model: The Zero Entropy model to use (default: "zerank-1")
|
|
"""
|
|
self._model = model
|
|
# Zero Entropy SDK reads ZEROENTROPY_API_KEY from environment by default
|
|
self._client = AsyncZeroEntropy()
|
|
|
|
async def _rerank(
|
|
self, query: str, chunks: list[Chunk], top_n: int = 10
|
|
) -> list[tuple[Chunk, float]]:
|
|
# Prepare documents for Zero Entropy API
|
|
documents = [chunk.content for chunk in chunks]
|
|
|
|
# Call Zero Entropy reranking API
|
|
model_name = self._model or "zerank-1"
|
|
response = await self._client.models.rerank(
|
|
model=model_name,
|
|
query=query,
|
|
documents=documents,
|
|
)
|
|
|
|
# Zero Entropy returns results sorted by relevance with scores
|
|
reranked_results = []
|
|
for result in response.results[:top_n]:
|
|
chunk_index = result.index
|
|
score = result.relevance_score
|
|
|
|
if chunk_index < len(chunks):
|
|
reranked_results.append((chunks[chunk_index], score))
|
|
|
|
return reranked_results
|