Skip to content
HotKVDocs

Ask the HotKV docs

Answers come only from these docs and can be wrong; check the linked pages before you rely on them.

AMEM.SEARCH

Last updated 
AMEM.SEARCH agent_id k value [value ...]
Group
Agent memory
Complexity
O(log N) where N is the number of facts
Arity
-4 (at least 4 words, counting the command name)
Flags
read-only, slow
Keys
first 1, last 1, step 1
HotKV Cloud
Performance and Scale
On-Premise
requires the agent-memory license feature

Agent memory gives AI agents four kinds of memory. AMEM.SEARCH returns up to k entries closest to a query embedding, most similar first, each tagged with the memory it came from. It searches the agent’s semantic memory only, so every result has the source semantic. Note that k comes before the vector.

Return value

Section titled “Return value”
Case RESP2 RESP3
Always Array of results. Each result is a flat array: "source", the source, "key", the key, "content", the content, "similarity", the cosine similarity as a string (all bulk strings). Empty for an unknown agent or a vector of the wrong size. Same

Errors:

  • ERR invalid k if k is not a positive integer.
  • ERR invalid vector component if a vector value is not a finite number.
  • ERR empty embedding vector if no vector values are given.
  • ERR wrong number of arguments for 'amem.search' command if the argument count is wrong.
  • NOLICENSE agent-memory requires a HotKV license. Contact sales@hotkv.com if your license does not include the agent-memory feature.

Examples

Section titled “Examples”
127.0.0.1:6379> AMEM.SEARCH notes 1 0.1 0.2 0.31
1) 1) "source"
   2) "semantic"
   3) "key"
   4) "fact-1"
   5) "content"
   6) "Paris is the capital of France."
   7) "similarity"
   8) "0.99990195"

Compatibility

Section titled “Compatibility”

HotKV-only command. Redis and Valkey have no equivalent.

See also

Section titled “See also”

AMEM.SEM.CREATE, AMEM.SEM.STORE, AMEM.SEM.RECALL, AMEM.SEM.FORGET, AMEM.SEM.LIST, AI features guide