Add Process and Data entity types to LLM extraction system

• Add Process and Data to default types
• Update env.example configuration
• Add translations for new entities
• Support 5 languages (en/zh/fr/ar/tw)
This commit is contained in:
yangdx 2025-09-14 01:14:47 +08:00
parent 2686fc526e
commit 7060cf17f0
7 changed files with 33 additions and 1 deletions

View file

@ -125,7 +125,7 @@ ENABLE_LLM_CACHE_FOR_EXTRACT=true
SUMMARY_LANGUAGE=English
### Entity types that the LLM will attempt to recognize
# ENTITY_TYPES='["Person", "Organization", "Location", "Event", "Concept", "Content", "Artifact", "NaturalObject"]'
# ENTITY_TYPES='["Person", "Organization", "Location", "Event", "Concept", "Process", "Content", "Data", "Artifact", "NaturalObject"]'
### Chunk size for document splitting, 500~1500 is recommended
# CHUNK_SIZE=1200

View file

@ -29,7 +29,9 @@ DEFAULT_ENTITY_TYPES = [
"Location",
"Event",
"Concept",
"Process",
"Content",
"Data",
"Artifact",
"NaturalObject",
]

View file

@ -190,6 +190,12 @@
"technology": "العلوم",
"product": "منتج",
"document": "وثيقة",
"content": "محتوى",
"data": "بيانات",
"artifact": "قطعة أثرية",
"concept": "مفهوم",
"naturalobject": "كائن طبيعي",
"process": "عملية",
"other": "أخرى"
},
"sideBar": {

View file

@ -190,6 +190,12 @@
"technology": "Technology",
"product": "Product",
"document": "Document",
"content": "Content",
"data": "Data",
"artifact": "Artifact",
"concept": "Concept",
"naturalobject": "Natural Object",
"process": "Process",
"other": "Other"
},
"sideBar": {

View file

@ -190,6 +190,12 @@
"technology": "Technologie",
"product": "Produit",
"document": "Document",
"content": "Contenu",
"data": "Données",
"artifact": "Artefact",
"concept": "Concept",
"naturalobject": "Objet naturel",
"process": "Processus",
"other": "Autre"
},
"sideBar": {

View file

@ -190,6 +190,12 @@
"technology": "技术",
"product": "产品",
"document": "文档",
"content": "内容",
"data": "数据",
"artifact": "人工制品",
"concept": "抽象概念",
"naturalobject": "自然对象",
"process": "过程方法",
"other": "其他"
},
"sideBar": {

View file

@ -190,6 +190,12 @@
"technology": "技術",
"product": "產品",
"document": "文檔",
"content": "內容",
"data": "資料",
"artifact": "人工製品",
"concept": "抽象概念",
"naturalobject": "自然物件",
"process": "過程方法",
"other": "其他"
},
"sideBar": {