NVIDIA Llama 3.2 NV-RerankQA 1B v2

FORGE_API_BASE=${FORGE_API_BASE:-'https://YOUR_FORGE_HOST'}
case "${FORGE_API_KEY:-}" in
  ""|replace-with-your-forge-api-key)
    echo 'Set FORGE_API_KEY to a real Forge API key before running this snippet; browser SSO sessions are not sent to copied curl or SDK clients.' >&2
    exit 1
    ;;
esac
forge_api_url() {
  endpoint="$1"
  base="${FORGE_API_BASE%/}"
  case "$base:$endpoint" in
    */v1:/v1|*/v1:/v1/*|*/v1:/v1\?*) printf '%s%s\n' "$base" "${endpoint#/v1}" ;;
    *) printf '%s%s\n' "$base" "$endpoint" ;;
  esac
}
forge_print_response() {
  response_file="$1"
  if [ ! -s "$response_file" ]; then
    printf '%s\n' '(empty response)'
    return 0
  fi
  if command -v python3 >/dev/null 2>&1; then
    python3 -m json.tool "$response_file" 2>/dev/null || cat "$response_file"
  else
    cat "$response_file"
  fi
}
response_file="$(mktemp)"
if curl -sS --fail-with-body "$(forge_api_url '/v1/inference/nvidia-llama-3-2-nv-rerankqa-1b-v2')" \
  --max-time "${FORGE_REQUEST_TIMEOUT_SECONDS:-600}" \
  -H "Authorization: Bearer ${FORGE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nvidia-llama-3-2-nv-rerankqa-1b-v2",
  "query": {
    "text": "what is retrieval augmented generation?"
  },
  "passages": [
    {
      "text": "Retrieval augmented generation combines search over external documents with language model generation."
    },
    {
      "text": "A graphics processing unit accelerates parallel numerical workloads."
    },
    {
      "text": "Embeddings map text into vectors for semantic search."
    }
  ],
  "truncate": "END",
  "model_version": "v1"
}' \
  -o "$response_file"; then
  forge_print_response "$response_file"
  status=$?
  rm -f "$response_file"
  (exit "$status")
else
  status=$?
  cat "$response_file" >&2
  rm -f "$response_file"
  (exit "$status")
fi