# Reference config for the `mtrag_clapnq` pre-built evaluation database.
# IBM MTRAG, ClapNQ (Wikipedia) domain: multi-turn retrieval and QA over
# 183,408 passages. Also serves mtrag_clapnq_rewrite, mtrag_clapnq_live and
# mtrag_clapnq_live_uncompacted.
# Run: evaluations run mtrag_clapnq --config configs/mtrag_clapnq.yaml
# base_url uses the `vllm` host serving each model over an OpenAI-compatible API.
# The corpus is text-only: no multimodal embedder, no vision paths. This eval
# cannot exercise image or vision turn-boundary behavior.

environment: development

storage:
  auto_vacuum: false

embeddings:
  model:
    provider: openai
    name: qwen3-embedding-4b
    vector_dim: 2560
    base_url: http://vllm:11431/v1

reranking:
  model:
    provider: vllm
    name: Qwen/Qwen3-Reranker-4B
    base_url: http://vllm:11455

qa:
  model:
    provider: openai
    name: RedHatAI/Muse-Glimmer-30B-NVFP4
    base_url: http://vllm:11450/v1
    # vLLM enforces input + max_tokens <= max_model_len, so a large output
    # budget silently shrinks the input budget. MTRAG answers are sentences.
    max_tokens: 8192
    extra_body:
      chat_template_kwargs:
        # Part of the measured baseline. vLLM's reasoning parser consumes
        # enable_thinking before the chat template sees it; reasoning_strength
        # is the knob Muse Glimmer templates honour, and a template that
        # defaults it to low silently changes search behavior.
        reasoning_strength: high

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