#!/usr/bin/env bash
# =============================================================================
# ALPHA_PROJECT — Qdrant — Setup collections e payload indexes
# =============================================================================
# Collections già create il 2026-03-21. Script conservato per tracciabilità
# e disaster recovery (da eseguire su un'istanza Qdrant vuota).
#
# Prerequisiti:
#   sudo microk8s kubectl port-forward svc/qdrant -n persistence 6333:6333
#
# Esecuzione:
#   bash alpha/db/qdrant.sh
# =============================================================================

set -euo pipefail

QDRANT_URL="${QDRANT_URL:-http://localhost:6333}"
QDRANT_API_KEY="${QDRANT_API_KEY:-__Montecarlo00!}"

# Dimensione vettori: 1536 = text-embedding-3-small (Copilot, bootstrap phase)
# Da aggiornare a 768 alla migrazione verso nomic-embed-text su Ollama
VECTOR_SIZE=1536

header_key="api-key: ${QDRANT_API_KEY}"

echo "==> Connessione a ${QDRANT_URL}"
curl -sf "${QDRANT_URL}/" -H "${header_key}" | grep -o '"version":"[^"]*"'
echo ""

# -----------------------------------------------------------------------------
# Collections
# Architettura multi-tenant: isolamento via campo user_id nel payload.
# Valori user_id: "martin" | "shared" | <futuri utenti>
# -----------------------------------------------------------------------------
for COL in episodes knowledge preferences; do
  echo "==> Creazione collection: ${COL}"
  curl -sf -X PUT "${QDRANT_URL}/collections/${COL}" \
    -H "${header_key}" \
    -H "Content-Type: application/json" \
    -d "{
      \"vectors\": { \"size\": ${VECTOR_SIZE}, \"distance\": \"Cosine\" },
      \"optimizers_config\": { \"default_segment_number\": 2 },
      \"replication_factor\": 1
    }" | grep -o '"status":"[^"]*"'
done

echo ""

# -----------------------------------------------------------------------------
# Payload indexes (per pre-filtering efficiente prima della ricerca vettoriale)
# -----------------------------------------------------------------------------
for COL in episodes knowledge preferences; do
  echo "==> Indexes per collection: ${COL}"

  for FIELD in user_id source category; do
    printf "   %-20s (keyword) → " "${FIELD}"
    curl -sf -X PUT "${QDRANT_URL}/collections/${COL}/index" \
      -H "${header_key}" \
      -H "Content-Type: application/json" \
      -d "{\"field_name\": \"${FIELD}\", \"field_schema\": \"keyword\"}" \
      | grep -o '"status":"[^"]*"'
  done

  printf "   %-20s (datetime) → " "date"
  curl -sf -X PUT "${QDRANT_URL}/collections/${COL}/index" \
    -H "${header_key}" \
    -H "Content-Type: application/json" \
    -d '{"field_name": "date", "field_schema": "datetime"}' \
    | grep -o '"status":"[^"]*"'

  printf "   %-20s (bool) → " "action_required"
  curl -sf -X PUT "${QDRANT_URL}/collections/${COL}/index" \
    -H "${header_key}" \
    -H "Content-Type: application/json" \
    -d '{"field_name": "action_required", "field_schema": "bool"}' \
    | grep -o '"status":"[^"]*"'
done

echo ""

# -----------------------------------------------------------------------------
# Verifica finale
# -----------------------------------------------------------------------------
echo "==> Collections attive:"
curl -sf "${QDRANT_URL}/collections" -H "${header_key}" \
  | python3 -c "import sys,json; [print('   -', c['name']) for c in json.load(sys.stdin)['result']['collections']]"

echo ""
echo "✅ Setup Qdrant completato."
echo "   Collections: episodes, knowledge, preferences"
echo "   Payload indexes: user_id, source, category, date, action_required"