Trainer_LLM/scripts/bootstrap_qdrant_exercises.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Idempotenter Bootstrap für die Qdrant-Collection 'exercises':
- Legt fehlende Payload-Indizes an (ohne Collection zu droppen)
- Optional prüft Dimension/Distanz

Starten mit 
pip install qdrant-client --upgrade
python3 scripts/bootstrap_qdrant_exercises.py

"""

import os
from qdrant_client import QdrantClient
from qdrant_client.models import PayloadSchemaType

QDRANT_HOST = os.getenv("QDRANT_HOST", "localhost")
QDRANT_PORT = int(os.getenv("QDRANT_PORT", "6333"))
COLLECTION  = os.getenv("EXERCISE_COLLECTION", "exercises")

INDEX_SPECS = [
    ("keywords", PayloadSchemaType.KEYWORD),
    ("equipment", PayloadSchemaType.KEYWORD),
    ("discipline", PayloadSchemaType.KEYWORD),
    ("age_group", PayloadSchemaType.KEYWORD),
    ("target_group", PayloadSchemaType.KEYWORD),
    ("category", PayloadSchemaType.KEYWORD),
    ("capability_keys", PayloadSchemaType.KEYWORD),
    ("capability_ge1", PayloadSchemaType.KEYWORD),
    ("capability_ge2", PayloadSchemaType.KEYWORD),
    ("capability_ge3", PayloadSchemaType.KEYWORD),
    ("capability_ge4", PayloadSchemaType.KEYWORD),  # neu
    ("capability_ge5", PayloadSchemaType.KEYWORD),  # neu
    ("capability_eq1", PayloadSchemaType.KEYWORD),  # neu
    ("capability_eq2", PayloadSchemaType.KEYWORD),  # neu
    ("capability_eq3", PayloadSchemaType.KEYWORD),  # neu
    ("capability_eq4", PayloadSchemaType.KEYWORD),  # neu
    ("capability_eq5", PayloadSchemaType.KEYWORD),  # neu
]

def main():
    client = QdrantClient(host=QDRANT_HOST, port=QDRANT_PORT)
    # Sanity: Collection existiert?
    info = client.get_collection(COLLECTION)  # wirf Fehler, wenn nicht vorhanden
    print(f"[Bootstrap] Collection '{COLLECTION}' gefunden. Vectors={info.config.params.vectors}")

    # Indizes idempotent anlegen
    for field, schema in INDEX_SPECS:
        try:
            client.create_payload_index(collection_name=COLLECTION,
                                        field_name=field,
                                        field_schema=schema)
            print(f"[Bootstrap] Index created: {field} ({schema})")
        except Exception as e:
            # Qdrant wirft hier Exceptions, wenn der Index schon existiert – das ist ok
            print(f"[Bootstrap] Index exists or skipped: {field} -> {e}")

    print("[Bootstrap] done.")

if __name__ == "__main__":
    main()