# Reference config for `mtrag_federated`: IBM MTRAG ClapNQ, partitioned by
# article title into four collections, scored on retrieval only.
#
# Build the partition and emit the config that searches exactly it:
#   uv run python -m evaluations.datasets.mtrag_federated \
#       --config configs/mtrag_federated.yaml --n 4 --out ~/configs/fed-n4.yaml
#   evaluations run mtrag_federated --config ~/configs/fed-n4.yaml \
#       --skip-db --skip-qa
#
# The databases below are the canonical n=4 partition at seed 20260831. Sweep
# configs for other collection counts live outside the repo, because a config
# here must be named after a registered dataset.
#
# No reranking block on purpose: this eval measures the reciprocal-rank fusion
# path, where retrieval depth per collection is `limit // n`. Adding a reranker
# is the comparison arm, not the baseline.
# base_url uses the `vllm` host serving each model over an OpenAI-compatible API.

environment: development

storage:
  auto_vacuum: false

lancedb:
  # Declaration order is load-bearing: fusion resolves equal ranks to this
  # order, so permuting these four keys is an arm.
  databases:
    clapnq_0: ${HOME}/.local/share/haiku.rag/evaluations/dbs/mtrag_federated_s20260831_n4_0.lancedb
    clapnq_1: ${HOME}/.local/share/haiku.rag/evaluations/dbs/mtrag_federated_s20260831_n4_1.lancedb
    clapnq_2: ${HOME}/.local/share/haiku.rag/evaluations/dbs/mtrag_federated_s20260831_n4_2.lancedb
    clapnq_3: ${HOME}/.local/share/haiku.rag/evaluations/dbs/mtrag_federated_s20260831_n4_3.lancedb

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