search_memories_similarity
Find related memories by comparing embedding vector similarities on the AGI MCP Server, enabling AI systems to retrieve relevant past experiences based on a defined threshold and limit.
Instructions
Search memories by vector similarity
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| embedding | Yes | Query embedding vector | |
| limit | No | Maximum number of results | |
| threshold | No | Minimum similarity threshold |
Input Schema (JSON Schema)
{
"properties": {
"embedding": {
"description": "Query embedding vector",
"items": {
"type": "number"
},
"type": "array"
},
"limit": {
"default": 10,
"description": "Maximum number of results",
"type": "integer"
},
"threshold": {
"default": 0.7,
"description": "Minimum similarity threshold",
"type": "number"
}
},
"required": [
"embedding"
],
"type": "object"
}