240 lines
5.3 KiB
YAML
240 lines
5.3 KiB
YAML
# Active retrieval configuration.
|
|
# Defaults are intentionally identical to the frozen 1.4.2 constants.
|
|
parameters:
|
|
retriex.retrieval.config:
|
|
hard_max_chunks: 6
|
|
hard_max_vectork: 18
|
|
hard_max_keywordk: 36
|
|
vector_score_threshold: 0.83
|
|
threshold_floor: 0.75
|
|
threshold_ceil: 0.90
|
|
list_bonus: 1.35
|
|
rrf_k: 50
|
|
keyword_topk_multiplier: 2.0
|
|
keyword_score_threshold: 0.35
|
|
keyword_rrf_weight: 1.15
|
|
scoped_vector_rrf_weight: 1.20
|
|
scoped_keyword_rrf_weight: 1.30
|
|
empty_rrf_fallback_topn: 1
|
|
max_chunks_per_doc: 2
|
|
min_chunk_distance: 2
|
|
dominant_doc_window: 6
|
|
dominant_doc_min_hits: 3
|
|
dominant_doc_max_chunks: 4
|
|
exact_document_max_chunks: 6
|
|
focused_product_window: 8
|
|
focused_product_min_score: 10.0
|
|
focused_product_min_gap: 4.0
|
|
focused_product_max_chunks: 4
|
|
catalog_list_shortcut_patterns:
|
|
- '/\balle\b/u'
|
|
- '/\bliste\b/u'
|
|
- '/\bauflistung\b/u'
|
|
- '/\buebersicht\b/u'
|
|
- '/\bübersicht\b/u'
|
|
- '/\bsortiment\b/u'
|
|
- '/\bwelche\b.*\b(gibt|verfügbar|verfuegbar|existieren)\b/u'
|
|
- '/\bzeige\b.*\b(produkte|geraete|geräte|modelle|artikel)\b/u'
|
|
- '/\bwas\b.*\b(gibt es|verfügbar|verfuegbar)\b/u'
|
|
exact_selection_token_variant_prefixes:
|
|
indikator:
|
|
- indikator
|
|
- indikatortyp
|
|
grenzwert:
|
|
- grenzwert
|
|
messbereich:
|
|
- messbereich
|
|
testomat:
|
|
- testomat
|
|
exact_selection_indicator_question_tokens:
|
|
- indikator
|
|
- indikatortyp
|
|
- reagenz
|
|
- reagens
|
|
exact_selection_indicator_question_phrases:
|
|
- mit welchem
|
|
- womit
|
|
exact_selection_indicator_table_heading_patterns:
|
|
- '/verf(?:ü|ue)gbare\s+indikatortypen|indikatortypen|indikatorvarianten/iu'
|
|
exact_selection_indicator_table_header_patterns:
|
|
- '/\|\s*(?:typ|indikator)\s*\|\s*(?:grenzwert|messbereich|bereich)/iu'
|
|
exact_selection_indicator_table_row_patterns:
|
|
- '/\|\s*[A-Z]{0,4}\s*\d{2,4}\s*[A-Z]?\s*\|\s*\d/iu'
|
|
exact_selection_indicator_table_required_primary_terms:
|
|
- indikator
|
|
exact_selection_indicator_table_required_context_terms:
|
|
- grenzwert
|
|
- messbereich
|
|
- bereich
|
|
exact_detail_tokens:
|
|
- indikator
|
|
- indikatoren
|
|
- indikatortyp
|
|
- indikatortypen
|
|
- reagenz
|
|
- reagens
|
|
- grenzwert
|
|
- messbereich
|
|
- bereich
|
|
- wasserhaerte
|
|
- wasserhärte
|
|
- resthaerte
|
|
- resthärte
|
|
- haerte
|
|
- härte
|
|
- aufloesung
|
|
- auflösung
|
|
- schnittstelle
|
|
- relais
|
|
- fehlercode
|
|
- code
|
|
- wert
|
|
- werte
|
|
generic_exact_selection_cleanup_profile: retrieval_reference_cleanup
|
|
generic_exact_selection_tokens:
|
|
- keine
|
|
- welche
|
|
generic_product_tokens:
|
|
- produkt
|
|
- produkte
|
|
- produktkarte
|
|
- titel
|
|
- geraet
|
|
- gerät
|
|
- messgeraet
|
|
- messgerät
|
|
- wasser
|
|
- haerte
|
|
- härte
|
|
- resthaerte
|
|
- resthärte
|
|
- analyse
|
|
- analysator
|
|
- automat
|
|
- online
|
|
- messung
|
|
- messen
|
|
- preis
|
|
- preise
|
|
- kosten
|
|
- info
|
|
- infos
|
|
- passend
|
|
- richtige
|
|
- richtiges
|
|
- geeignet
|
|
- geeignete
|
|
- welche
|
|
- welcher
|
|
- welches
|
|
- brauche
|
|
- suche
|
|
important_short_model_tokens:
|
|
- th
|
|
- tc
|
|
- tp
|
|
- tm
|
|
- ph
|
|
- rx
|
|
family_descriptor_tokens:
|
|
- evo
|
|
- eco
|
|
- self
|
|
- clean
|
|
- mini
|
|
- pro
|
|
- plus
|
|
- basic
|
|
- lab
|
|
- inline
|
|
- compact
|
|
- panel
|
|
- sc
|
|
looks_like_reagent_tokens:
|
|
- indikator
|
|
- reagenz
|
|
- reagenz
|
|
- laborchemikalie
|
|
- chemikalie
|
|
- sicherheitsdatenblatt
|
|
- sdb
|
|
- msds
|
|
- ufi
|
|
- gebinde
|
|
- flasche
|
|
- ersatzteil
|
|
- zubehoer
|
|
- zubehör
|
|
- service set
|
|
- filtereinsatz
|
|
- kerzenfilter
|
|
- druckregler
|
|
- ph
|
|
looks_like_safety_docs:
|
|
- sicherheitsdatenblatt
|
|
- sdb
|
|
- msds
|
|
- gefahrenbewertung
|
|
- gefahrenpiktogramm
|
|
- signalwort
|
|
- lagerung
|
|
- transport
|
|
- clp
|
|
- kennzeichnung
|
|
- h290
|
|
- pbt
|
|
- vpvb
|
|
looks_like_reagent_words:
|
|
- indikator
|
|
- reagenz
|
|
- reagens
|
|
- chemie
|
|
- chemikalie
|
|
- sdb
|
|
- sicherheitsdatenblatt
|
|
- msds
|
|
- flasche
|
|
- gebinde
|
|
looks_like_document_words:
|
|
- datenblatt
|
|
- dokument
|
|
- pdf
|
|
- handbuch
|
|
- manual
|
|
- beschreibung
|
|
- sdb
|
|
- sicherheitsdatenblatt
|
|
- msds
|
|
looks_like_safety_words:
|
|
- gefahr
|
|
- gefahrgut
|
|
- clp
|
|
- h290
|
|
- sicherheit
|
|
- kennzeichnung
|
|
- transport
|
|
- lagerung
|
|
- piktogramm
|
|
looks_like_device_words:
|
|
- geraet
|
|
- gerät
|
|
- messgeraet
|
|
- messgerät
|
|
- analysator
|
|
- automat
|
|
- messung
|
|
- messen
|
|
- ueberwachung
|
|
- überwachung
|
|
- online
|
|
- monitor
|
|
- modell
|
|
- analysegerät
|
|
- tester
|
|
|
|
# Vocabulary-backed retrieval token lists live in config/retriex/vocabulary.yaml.
|
|
# The old per-key entries may still be added here to override a specific view.
|
|
|
|
# Backwards-compatible name for existing config diagnostics.
|
|
retriex.retrieval.inventory: '%retriex.retrieval.config%'
|