# Reference config for `mtrag_pooled`: all four MTRAG domains (clapnq, cloud,
# fiqa, govt) pooled and partitioned across `n` collections, scored on retrieval
# only.
#
# This is the heterogeneous corpus. `mtrag_federated` partitions one domain by
# article title, which is round-robin fusion's friendliest case: no collection is
# ever off-topic for a query, so the guaranteed-slot waste is never exercised.
# Here a query belongs to one domain and the others are genuinely off-topic.
#
# Build the partition and emit the config that searches exactly it:
#   uv run python -m evaluations.datasets.mtrag_federated \
#       --config configs/mtrag_pooled.yaml --pooled --n 4 --alpha 0 \
#       --out ~/configs/pooled-n4-a0.yaml
#   evaluations run mtrag_pooled --config ~/configs/pooled-n4-a0.yaml \
#       --skip-db --skip-qa
#
# alpha 0 keeps each collection to one domain; alpha 1 shards titles across all
# of them, which is the degenerate sharding endpoint rather than a rival design.
# The operator emits the databases, so none are listed here.

environment: development

storage:
  auto_vacuum: false

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

search:
  # Matches the spec's retrieval_limit and the product default.
  limit: 5

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