Skip to main content
Nowledge MemNowledge Mem

Reindex Search Index

POST
/search-index/reindex

Refresh the search projection from authoritative storage.

Most calls perform a full semantic rebuild of:

  • All memories (with search embeddings)
  • All thread messages
  • All Library sources and source chunks
  • All communities
  • All entities

If the only pending marker is the 0.8.4 Content Store thread-message migration and semantic index metadata already matches the active embedding backend, this endpoint only copies/verifies messages, rebuilds the FTS-only messages_index, and skips embedding initialization.

The embedding model is platform-specific:

  • macOS Apple Silicon: Qwen3-Embedding via mlx-embeddings
  • non-Apple-Silicon (Windows/Linux/macOS Intel): BGE-M3 via FastEmbed/ONNX

This is a heavy operation and should only be triggered:

  • After first downloading the search embedding model
  • After a data migration
  • When explicitly requested by the user

Response Body

application/json

curl -X POST "https://example.com/search-index/reindex"
{  "communities": 0,  "entities": 0,  "errors": [    "string"  ],  "memories": 0,  "message": "",  "messages": 0,  "restart_recommended": false,  "source_chunks": 0,  "sources": 0,  "success": true}