Commit graph

6 commits

Author SHA1 Message Date
Yiorgis Gozadinos
0dec3d4e63
Make three tests assert what they are about
`test_an_image_query_builds_no_reranker` never submitted an image query: it
opened clients and found nothing built, which is lazy construction. It sends one
now, so consulting the reranker before the query type fails it.

`TestComparingEmbedders` called `_require_one_embedder` and asserted nothing.
It rejects a disagreement and accepts an absent record, and searches through.

Three `ModelRetry` tests took any reason where the reason is the subject.
2026-08-27 18:04:28 +03:00
Yiorgis Gozadinos
5ecffdedf2
Read a created database's embedder with its settings
Creating re-read the settings blob and left `stored_embedding` at None, so a
client that created a database compared as though it recorded no embedder.
`_remember_settings` takes both, and the comment no longer says one follows the
other.
2026-08-27 18:04:27 +03:00
Yiorgis Gozadinos
b6bc54c69e
Answer for an unknown database name with one type
A name nothing covers raised `KeyError` in four places and
`AmbiguousDatabaseError` in a fifth, so a caller had to catch both and neither
name said what happened. `UnknownDatabaseError` is all of them, exported from
`haiku.rag.store` beside the other errors.

It subclasses `KeyError`, since selecting by name is a lookup, and prints its
message plainly rather than quoted as a missing key. Both CLIs turn it into the
same clean exit they already gave the others.
2026-08-27 18:04:27 +03:00
Yiorgis Gozadinos
de6da8b375
Pin what reciprocal rank fusion produces
`_fuse` ran in tests without anything asserting its output, so reversing the
sort or dropping the truncation changed nothing. Databases interleave by rank,
the score is the reciprocal of it, ties keep configured order, and the limit
cuts the fused list.

Every native score in one database beats every one in the other, so ranking by
score rather than position fails all four.
2026-08-27 16:01:28 +03:00
Yiorgis Gozadinos
9ed66e3a06
Search one database the ordinary way, however it was selected
`sources=["alpha"]` on a client covering a set went through fusion, which
scores position: a result the database ranked at 0.6549 was reported as
1/(60+rank). Embedding also moved ahead of the repository, so a filter matching
no document embedded the query anyway.

A selection of one now runs the single-database search. Fusion reconciles
rankings from separate indexes, and one ranking has nothing to reconcile.

A reranker that returns chunks it built rather than the ones it was given loses
which database each came from, since ownership is by identity. That is named
now instead of surfacing as a KeyError, and stated on `RerankerBase._rerank`.
2026-08-27 14:41:10 +03:00
Yiorgis Gozadinos
ca2e28559e
Split the multi-database tests by subject
Two files of 1,405 and 814 lines become seven: scope resolution, lifecycle,
search, documents, expansion, citations and capabilities. `_config`, `_seed`
and the rest move to `helpers.py`, importable by the sandbox tests that share
them, and the package points VCR back at `tests/cassettes/multi_db/`.
2026-08-26 13:43:53 +03:00