ac7467f0b4
- Added comprehensive AI Assistant system (aiassist/ directory): * Vector search and embedding capabilities * Typebot proxy integration * Elastic search functionality * Message classification and chat history * MCP proxy for external integrations - Implemented Court Status API (GetCourtStatus.php): * Real-time court document status checking * Integration with external court systems * Comprehensive error handling and logging - Enhanced S3 integration: * Improved file backup system with metadata * Batch processing capabilities * Enhanced error logging and recovery * Copy operations with URL fixing - Added Telegram contact creation API - Improved error logging across all modules - Enhanced callback system for AI responses - Extensive backup file storage with timestamps - Updated documentation and README files - File storage improvements: * Thousands of backup files with proper metadata * Fix operations for broken file references * Project-specific backup and recovery systems * Comprehensive file integrity checking Total: 26,461+ files added/modified including AWS SDK, vendor dependencies, and extensive backup system.
35 lines
1.4 KiB
Python
35 lines
1.4 KiB
Python
#!/var/www/laws/legal/bin/python3
|
|
|
|
from sentence_transformers import SentenceTransformer
|
|
from natasha import Doc, Segmenter, MorphVocab, NamesExtractor
|
|
|
|
# Инициализация моделей
|
|
#sbert_model = SentenceTransformer("paraphrase-MiniLM-L6-v2", device="cpu")
|
|
sbert_model = SentenceTransformer("/var/www/laws/models/paraphrase-MiniLM-L6-v2", device="cpu")
|
|
segmenter = Segmenter()
|
|
morph_vocab = MorphVocab()
|
|
|
|
import sys
|
|
import json
|
|
import sys
|
|
|
|
# Добавляем нужный путь для установки зависимостей, если требуется
|
|
sys.path.append('/var/www/laws/legal/bin/python3.11/site-packages')
|
|
|
|
from sentence_transformers import SentenceTransformer
|
|
|
|
def get_embedding(text):
|
|
# Инициализируем модель на CPU
|
|
sbert_model = SentenceTransformer("paraphrase-MiniLM-L6-v2", device="cpu")
|
|
# Получаем эмбеддинг (модель возвращает numpy-массив)
|
|
embedding = sbert_model.encode(text, show_progress_bar=False)
|
|
# Преобразуем в список и возвращаем
|
|
return embedding.tolist()
|
|
|
|
if __name__ == '__main__':
|
|
# Считываем текст из аргументов командной строки
|
|
input_text = sys.argv[1] if len(sys.argv) > 1 else ""
|
|
vector = get_embedding(input_text)
|
|
# Выводим результат в формате JSON
|
|
print(json.dumps(vector))
|