Langfuse aggregates scores by name, so one name may only carry values on
one scale. recall_top_score was emitted for every method, mixing HYBRID's
LR-sigmoid probability and AGENTIC's cross-encoder score (both comparable
in [0, 1]) with KEYWORD's unbounded BM25 and single-route VECTOR's cosine.
A chart on that name averaged the two scales, and in practice a keyword
score can read numerically higher than a calibrated one while meaning less.
Uncalibrated methods now report recall_top_score_raw, leaving
recall_top_score comparable across methods and over time. Every recall
score also carries metadata = {method, calibrated}: a structured field
Langfuse persists and can split on, which the free-text comment could not
serve. The comment stays for reading individual scores.
Breaking for anyone charting recall_top_score for keyword search; 1.2.0 is
four days old, so this is the cheapest moment to correct the naming.
Claude-Session: https://claude.ai/code/session_01UyKinsWs1MgoARPoB9R4NW
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| component | ||
| config | ||
| core | ||
| entrypoints | ||
| infra | ||
| memory | ||
| service | ||
| templates | ||
| README.md | ||
| __init__.py | ||
| py.typed | ||
README.md
everos package
Source layout for the everos Python package. This README is a quick
orientation; full architectural detail lives elsewhere.
Layout
everos/
├── entrypoints/ Presentation: cli + api
├── service/ Application: use case orchestration
├── memory/ Domain: extract + search + cascade + prompt_slots + models
├── infra/ Infrastructure: persistence/{markdown, sqlite, lancedb}
├── component/ Cross-cutting providers: llm / embedding / config / utils
├── core/ Runtime base: observability / lifespan / context
└── config/ Data: Settings + default.toml + prompt_slots templates
Each subpackage has a top-level __init__.py describing its responsibility
and public API.
Dependency rule
entrypoints → service → memory → infra
↓
component / core / config
Single-direction; enforced by import-linter in CI.
Further reading
- Architecture: ../../docs/architecture.md
- Coding rules (auto-loaded by Claude Code): ../../.claude/rules/