Search & Retrieval
Hybrid search with vector similarity, full-text search, and reranking — find the most relevant memories.
MemoryKit search returns ranked results using hybrid retrieval that combines vector similarity, full-text search, and reranking in a single call.
Search
Returns ranked memory chunks with relevance scores. Use for building custom UIs, feeding your own LLM, or powering any retrieval workflow.
Hybrid search
Combines vector similarity and full-text search with automatic reranking for the best results.
Query parameters
Use query parameters to narrow results by tags, type, date range, and precision.
| Parameter | Type | Description |
|---|---|---|
query | string | Search query (required) |
precision | string | low, medium (default), or high — higher precision returns fewer but more relevant results |
limit | number | Max results, 1–100 (default: 10) |
user_id | string | Scope to a specific user |
type | string | Filter by memory type |
tags | string | Comma-separated tags (e.g. finance,reports) |
created_after | string | ISO 8601 timestamp — only memories created after this date |
created_before | string | ISO 8601 timestamp — only memories created before this date |
include_graph | boolean | Include knowledge graph connections |
User-scoped search
Pass userId to only retrieve memories belonging to that user. This is essential for multi-tenant apps where each user has their own knowledge base.
Common patterns
| Use case | Approach |
|---|---|
| Build a custom search UI with results | search with limit and tags |
| Feed context into your own LLM prompt | search to retrieve, then pass results to your LLM |
| Scope to a single user | search with userId |
| Need full control over the LLM | search + your own LLM |
| Time-scoped results | search with created_after / created_before |
| High-accuracy retrieval | search with precision: "high" |