haiku.rag/haiku_rag_slim/haiku/rag/reranking
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
..
__init__.py Add per-endpoint api_key to model and embedding config 2026-08-23 23:54:40 +03:00
base.py Search one database the ordinary way, however it was selected 2026-08-27 14:41:10 +03:00
cohere.py Reject unknown and out-of-range configuration values 2026-08-19 15:32:51 +03:00
cross_encoder.py Reject unknown and out-of-range configuration values 2026-08-19 15:32:51 +03:00
jina.py Pool HTTP clients for vLLM embedding and vLLM/Jina reranking 2026-07-09 10:32:44 +03:00
jina_local.py Reject unknown and out-of-range configuration values 2026-08-19 15:32:51 +03:00
vllm.py Add per-endpoint api_key to model and embedding config 2026-08-23 23:54:40 +03:00
zeroentropy.py Delete comments that restate the line below them 2026-08-20 15:22:33 +03:00