feat: add deterministic content extractor selector engine with F1 consensus

This commit is contained in:
2026-08-20 22:09:43 -03:00
parent 6a45368cb0
commit ff7a50e0eb
46 changed files with 18503 additions and 2813 deletions
+22 -6
View File
@@ -44,10 +44,10 @@
"42": "1. Input Schemas",
"43": "2. Basic CLI Usage Examples",
"44": "2. Standard Streams & Exit Codes",
"45": "classifier.py",
"45": "ClassificationResult",
"46": "InherenceClassifier",
"47": "detect_language",
"48": "ClassificationError",
"47": "classifier.py",
"48": "main",
"49": "content_northvolt_de.md",
"50": "content_presal_pt.md",
"51": "content_tangential_es.md",
@@ -99,12 +99,12 @@
"97": "🧠 TextNLPClassifierApp",
"98": "Extraction Pipeline Checklist: Article Content Multi-Engine Extractor",
"99": "sample_rss_xml",
"100": "main",
"100": "models.py",
"101": "ECPSnapshot",
"102": "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)",
"103": "4. Requisitos Funcionais (FR)",
"104": "Tasks: Article Content Multi-Engine Extractor",
"105": "models.py",
"105": "LocalEmbeddingsAdapter",
"106": "Implementation Plan: Article Content Multi-Engine Extractor",
"107": "2. Cenários de Validação",
"108": "1. Technical Decisions & Tradeoffs",
@@ -113,5 +113,21 @@
"111": "Specification Quality Checklist: Multilingual NLP Entity Inherence Classifier",
"112": "CLI Contract: Article Content Multi-Engine Extractor",
"113": "001-multilingual-entity-classifier/spec.md",
"114": "JSON Schema Contract: Article Content Multi-Engine Extractor"
"114": "JSON Schema Contract: Article Content Multi-Engine Extractor",
"115": "PRD — Seleção determinística da biblioteca de extração de conteúdo",
"116": "select_article_extractor.py",
"117": "1. Text Normalization Pipeline",
"118": "Tasks: Deterministic Article Content Selection",
"119": "select_article_extractor",
"120": "process_batch",
"122": "test_select_article_extractor.py",
"123": "Feature Specification: Deterministic Content Selection",
"124": "2. Entity Descriptions & Fields",
"125": "Implementation Plan: Deterministic Article Content Selection",
"126": "Deterministic Content Selection Checklist: End-to-End Requirements Quality",
"127": "Quickstart: Deterministic Article Content Selection",
"128": "Specification Quality Checklist: Deterministic Content Selection",
"129": "CLI Interface Contract: Deterministic Article Content Selection",
"130": "004-deterministic-content-selection/spec.md",
"131": "JSON Schema Contract: Deterministic Article Content Selection"
}