# Reference config for the `orb_multimodal_nemotron` pre-built evaluation database.
# OpenRAG Bench with the nvidia/llama-nemotron-embed-vl-1b-v2 multimodal embedder,
# the embedder behind the published headline benchmark numbers.
# Run: evaluations run orb_multimodal_nemotron --skip-db --config configs/orb_multimodal_nemotron.yaml
# base_url uses the `vllm` host serving each model over an OpenAI-compatible API.

environment: development

storage:
  auto_vacuum: false

embeddings:
  model:
    provider: vllm
    name: nvidia/llama-nemotron-embed-vl-1b-v2
    vector_dim: 2048
    multimodal: true
    base_url: http://vllm:11438/v1

reranking:
  model: null

qa:
  model:
    provider: openai
    name: gemma4-26b
    base_url: http://vllm:11432/v1
    vision: true

evaluations:
  judge:
    provider: openai
    name: Inferact/Qwen3.8-27B-NVFP4
    base_url: http://vllm:11439/v1
    temperature: 0.6
    max_tokens: 16384
    extra_body:
      top_p: 0.95
      top_k: 20
      min_p: 0
      chat_template_kwargs:
        reasoning_effort: low