Commit graph

6 commits

Author SHA1 Message Date
Yiorgis Gozadinos
72ef18e39d
Reject unknown and out-of-range configuration values
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.
2026-08-19 15:32:51 +03:00
Yiorgis Gozadinos
d63199d96d
Keep cross-encoder rerank scores apart when they saturate
mxbai-rerank-base-v2 ships a Sigmoid activation and evaluates it in bf16, so
every strongly-relevant candidate rounds to exactly 1.0. Ties then leave the
order to the stable sort, which preserves the incoming hybrid ranking: on 100
t2_finqa retrieval cases the reranker scored MAP 0.661 against 0.659 with no
reranker at all, and 0.742 once the scores separate.

Ask the model for logits and apply the sigmoid here, where it runs in float64.
Scores stay 0-1, matching the cohere, vllm and zeroentropy rerankers.

Also drop the remaining pyright references; the project type-checks with ty.
2026-08-07 14:07:53 +03:00
Yiorgis Gozadinos
38079ff89a
Hoist reranker empty-input guard into base; stop factory tests loading models 2026-06-29 14:20:23 +03:00
Yiorgis Gozadinos
5de4d50622
coverage 2026-05-14 15:54:43 +03:00
Yiorgis Gozadinos
57f273e000
Minor fixes, CI should build 2026-05-14 15:43:36 +03:00
Yiorgis Gozadinos
519afe6709
Add cross-encoder reranking provider 2026-05-14 15:43:35 +03:00