mnemon_vector_quantize
Configure pgvector HNSW-PQ vector quantization and disk-spill indexing to enable billion-scale similarity search while conserving RAM and lowering query latency.
Instructions
Configure pgvector + HNSW-PQ vector quantization with disk-spill indexing for sub-10ms billion-vector search.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"tenant_id": "<tenant_id>",
"table": "<table>",
"column": "<column>"
},
"name": "mnemon_vector_quantize"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| table | Yes | Target vector table | |
| column | Yes | Target vector embedding column | |
| tenant_id | Yes | Database tenant identifier | |
| dimensions | No | Vector dimensions (default: 1536) | |
| disk_spill | No | Enable disk-spill indexing for RAM conservation | |
| quantization_type | No | Quantization algorithm (default: PQ) |