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.

SCACHE.THRESHOLD

Last updated 
SCACHE.THRESHOLD namespace similarity
Group
Semantic cache
Complexity
O(1)
Arity
3 (exactly, counting the command name)
Flags
write, fast
Keys
first 1, last 1, step 1
HotKV Cloud
Performance and Scale
On-Premise
requires the semantic-cache license feature

The semantic cache returns a cached LLM response when a new query embedding is similar enough to one you stored, so paraphrased requests can hit. Your application computes the embeddings. SCACHE.THRESHOLD sets the minimum similarity, from 0.0 to 1.0, that SCACHE.GET needs for a hit. It applies to the next lookup. A higher value gives fewer but closer matches.

Return value

Section titled “Return value”
Case RESP2 RESP3
Threshold changed Simple string OK Same

Errors:

  • ERR threshold must be 0.0-1.0 if the value is out of range or not a number.
  • ERR namespace not found if the namespace does not exist.
  • ERR wrong number of arguments for 'scache.threshold' command if the argument count is wrong.
  • NOLICENSE semantic-cache requires a HotKV license. Contact sales@hotkv.com if your license does not include the semantic-cache feature.

Examples

Section titled “Examples”
127.0.0.1:6379> SCACHE.THRESHOLD llm_cache 0.95
OK
127.0.0.1:6379> SCACHE.THRESHOLD llm_cache 1.5
(error) ERR threshold must be 0.0-1.0

Compatibility

Section titled “Compatibility”

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

See also

Section titled “See also”

SCACHE.CREATE, SCACHE.SET, SCACHE.GET, SCACHE.STATS, SCACHE.FLUSH, SCACHE.DROP, SCACHE.LIST, AI features guide