registry.json

{
  "version": "0.1.0",
  "roles": [
    {
      "role": "embedding",
      "recommended_for": [
        "paper retrieval",
        "dataset retrieval",
        "protocol retrieval"
      ],
      "candidates": [
        {
          "repo_id": "BAAI/bge-m3",
          "status": "benchmark",
          "notes": "Multilingual retrieval candidate with long-context support."
        }
      ]
    },
    {
      "role": "reranker",
      "recommended_for": [
        "top-k reranking",
        "evidence ordering"
      ],
      "candidates": [
        {
          "repo_id": "BAAI/bge-reranker-v2-m3",
          "status": "benchmark",
          "notes": "Multilingual reranker candidate for biomedical search refinement."
        }
      ]
    },
    {
      "role": "instruct_small",
      "recommended_for": [
        "structured extraction",
        "research summarization",
        "non-clinical reasoning"
      ],
      "candidates": [
        {
          "repo_id": "google/gemma-3-4b-it",
          "status": "benchmark",
          "notes": "Smaller instruction-tuned candidate for cost-sensitive workflows."
        }
      ]
    },
    {
      "role": "instruct_medium",
      "recommended_for": [
        "higher-complexity synthesis",
        "longer-context research assistance"
      ],
      "candidates": [
        {
          "repo_id": "google/gemma-3-12b-it",
          "status": "benchmark",
          "notes": "Medium-size reasoning candidate; benchmark before adoption."
        }
      ]
    }
  ]
}