#!/usr/bin/env bash
# Loads data/memory.md and data/claude-legacy-memory.md into the LiteLLM
# knowledgebase (the "memory-and-notes" vector store, see litellm-config.yaml)
# via litellm-pgvector's batch-embeddings endpoint.
#
# ponytail: one chunk per non-empty, non-heading line — both source files are
# already one fact/paragraph per line (no hard-wrapping), so this needs no
# real chunking logic. Re-run after editing either file; there's no dedup, so
# this appends duplicates on a second run against unchanged content — clear
# the store first (DELETE the vector_store_id's rows) if you need a clean
# reload.
set -euo pipefail
cd "$(dirname "$0")/.."

[ -f .env ] && set -a && . ./.env && set +a

: "${LITELLM_PGVECTOR_API_KEY:?Set LITELLM_PGVECTOR_API_KEY in .env first}"
LITELLM_PGVECTOR_URL="${LITELLM_PGVECTOR_URL:-http://localhost:8000}"
VECTOR_STORE_ID="memory-and-notes"

# Must match litellm-config.yaml's vector_store_registry entry — the
# registry just points at a store the backend must already know about.
# Ignores failure if it already exists (no documented idempotency check).
curl -sf -X POST "${LITELLM_PGVECTOR_URL}/v1/vector_stores" \
  -H "Authorization: Bearer ${LITELLM_PGVECTOR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{\"name\": \"${VECTOR_STORE_ID}\"}" > /dev/null 2>&1 || true

ingest_file() {
  local file="$1" section=""
  local batch="[]"
  while IFS= read -r line; do
    case "$line" in
      "#"*) section="${line#\# }"; section="${section#\#\# }"; continue ;;
      ""|"---") continue ;;
    esac
    batch=$(jq --arg content "$line" --arg source "$file" --arg section "$section" \
      '. += [{"content": $content, "metadata": {"source": $source, "section": $section}}]' <<<"$batch")
  done < "$file"

  echo "Ingesting $(jq 'length' <<<"$batch") chunks from $file..."
  curl -sf -X POST "${LITELLM_PGVECTOR_URL}/v1/vector_stores/${VECTOR_STORE_ID}/embeddings/batch" \
    -H "Authorization: Bearer ${LITELLM_PGVECTOR_API_KEY}" \
    -H "Content-Type: application/json" \
    -d "$batch" > /dev/null
}

ingest_file data/memory.md
ingest_file data/claude-legacy-memory.md
echo "Done."