7758315632
Services: - api: FastAPI gateway with JWT auth, async endpoints, WebSocket - worker-gpu: CUDA sentence-transformers, FAISS IVFFlat, Ollama LLM - worker-indexer: Winnowing+MinHash plagiarism detection, PDF/DOCX extraction - worker-notifier: SMTP email notifications - worker-gost: GOST 7.1-2003 and GOST R 7.0.5-2008 formatting Infrastructure: - docker-compose.yml (production) + docker-compose.dev.yml (hot reload) - Nginx reverse proxy + WebSocket support - PostgreSQL 16 with Alembic migrations - Elasticsearch 8 with Russian/English analyzers - MinIO, RabbitMQ, Redis, Ollama Frontend: - React 18 + Vite + TypeScript + TailwindCSS + Zustand + React Query v5 - 9 pages: Home, Search, Cabinet, Task, Check, Bibliography, Pricing, Login, Register Scripts: - Parser stubs: OpenAlex, КиберЛенинка, arXiv (Phase 0 - to be filled) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
76 lines
2.1 KiB
JSON
76 lines
2.1 KiB
JSON
{
|
|
"settings": {
|
|
"number_of_shards": 1,
|
|
"number_of_replicas": 0,
|
|
"analysis": {
|
|
"analyzer": {
|
|
"russian_analyzer": {
|
|
"type": "custom",
|
|
"tokenizer": "standard",
|
|
"filter": ["lowercase", "russian_stop", "russian_stemmer"]
|
|
},
|
|
"english_analyzer": {
|
|
"type": "custom",
|
|
"tokenizer": "standard",
|
|
"filter": ["lowercase", "english_stop", "english_stemmer"]
|
|
},
|
|
"multilingual_analyzer": {
|
|
"type": "custom",
|
|
"tokenizer": "standard",
|
|
"filter": ["lowercase", "russian_stop", "russian_stemmer", "english_stop"]
|
|
}
|
|
},
|
|
"filter": {
|
|
"russian_stop": {
|
|
"type": "stop",
|
|
"stopwords": "_russian_"
|
|
},
|
|
"russian_stemmer": {
|
|
"type": "stemmer",
|
|
"language": "russian"
|
|
},
|
|
"english_stop": {
|
|
"type": "stop",
|
|
"stopwords": "_english_"
|
|
},
|
|
"english_stemmer": {
|
|
"type": "stemmer",
|
|
"language": "english"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"mappings": {
|
|
"properties": {
|
|
"doc_id": {"type": "long"},
|
|
"source": {"type": "keyword"},
|
|
"title": {
|
|
"type": "text",
|
|
"analyzer": "multilingual_analyzer",
|
|
"fields": {
|
|
"keyword": {"type": "keyword", "ignore_above": 512},
|
|
"ru": {"type": "text", "analyzer": "russian_analyzer"},
|
|
"en": {"type": "text", "analyzer": "english_analyzer"}
|
|
}
|
|
},
|
|
"abstract": {
|
|
"type": "text",
|
|
"analyzer": "multilingual_analyzer",
|
|
"fields": {
|
|
"ru": {"type": "text", "analyzer": "russian_analyzer"},
|
|
"en": {"type": "text", "analyzer": "english_analyzer"}
|
|
}
|
|
},
|
|
"authors": {
|
|
"type": "text",
|
|
"analyzer": "multilingual_analyzer"
|
|
},
|
|
"year": {"type": "integer"},
|
|
"lang": {"type": "keyword"},
|
|
"journal": {"type": "keyword", "ignore_above": 512},
|
|
"doi": {"type": "keyword"},
|
|
"url": {"type": "keyword", "index": false}
|
|
}
|
|
}
|
|
}
|