Install Bge M3

Download and install the search embedding model for hybrid search.

The model downloaded is platform-specific:

• macOS Apple Silicon: Qwen3-Embedding (~400MB, 4-bit quantized)
• Windows/Linux: BGE-M3 (~542MB, INT8 quantized)

This also deletes the old E5 embedding model to save space. After installation, run /search-index/reindex to build the index.

curl -X POST "http://127.0.0.1:14242/models/bge-m3/install" \  -H "Content-Type: application/json" \  -d '{}'

{
  "success": true,
  "message": "string",
  "reindex_required": true
}

{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string",
      "input": null,
      "ctx": {}
    }
  ]
}