# Reference config for the `hotpotqa` pre-built evaluation database.
# HotpotQA (distractor validation split) multi-hop QA over wiki paragraphs.
# Run: evaluations run hotpotqa --config configs/hotpotqa.yaml
# base_url uses the `vllm` host serving each model over an OpenAI-compatible API.

environment: development

storage:
  auto_vacuum: false

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

qa:
  model:
    provider: openai
    name: gemma4-26b
    base_url: http://vllm:11432/v1
    max_tokens: 49152

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