102 lines
3.2 KiB
YAML
102 lines
3.2 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: {}
|
|
exact_selection_token_variant_suffixes:
|
|
- typen
|
|
- innen
|
|
- enen
|
|
- ern
|
|
- en
|
|
- er
|
|
- es
|
|
- e
|
|
- s
|
|
- n
|
|
exact_selection_indicator_question_tokens: []
|
|
exact_selection_indicator_question_phrases: []
|
|
exact_selection_indicator_table_heading_patterns: []
|
|
exact_selection_indicator_table_header_patterns: []
|
|
exact_selection_indicator_table_row_patterns: []
|
|
exact_selection_indicator_table_required_primary_terms: []
|
|
exact_selection_indicator_table_required_context_terms: []
|
|
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
|
|
vocabulary_views:
|
|
generic_product_tokens: retrieval.generic_product_tokens
|
|
important_short_model_tokens: retrieval.important_short_model_tokens
|
|
family_descriptor_tokens: retrieval.family_descriptor_tokens
|
|
looks_like_reagent_tokens: retrieval.looks_like_reagent_tokens
|
|
looks_like_safety_docs: retrieval.looks_like_safety_docs
|
|
looks_like_reagent_words: retrieval.looks_like_reagent_words
|
|
looks_like_document_words: retrieval.looks_like_document_words
|
|
looks_like_safety_words: retrieval.looks_like_safety_words
|
|
looks_like_device_words: retrieval.looks_like_device_words
|
|
|
|
# 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%'
|