RAG.STATS

A RAG pipeline splits your documents into chunks, keeps each chunk with the embedding you computed for it, and answers searches that combine keyword (BM25) relevance with vector similarity, all inside HotKV. RAG.STATS describes one pipeline.

Return value

The reply is a flat array of alternating field names and values in both RESP2 and RESP3 (it is not sent as a RESP3 map). The fields, in order:

Field	Type	Meaning
name	Bulk string	Pipeline name.
dimensions	Integer	Embedding dimensions.
totalDocs	Integer	Documents currently stored.
totalChunks	Integer	Chunks currently stored.
totalIngested	Integer	Ingest calls that stored chunks, re-ingests included.
totalQueries	Integer	Searches run.
chunkSize	Integer	Chunk size in characters.
chunkStrategy	Bulk string	fixed_size, sentence or paragraph.
chunkOverlap	Integer	Chunk overlap in characters.

Errors:

• ERR pipeline not found if the pipeline does not exist.
• ERR wrong number of arguments for 'rag.stats' command if the argument count is wrong.
• NOLICENSE rag-pipeline requires a HotKV license. Contact sales@hotkv.com if your license does not include the rag-pipeline feature.

Examples

127.0.0.1:6379> RAG.STATS faq
 1) "name"
 2) "faq"
 3) "dimensions"
 4) (integer) 3
 5) "totalDocs"
 6) (integer) 1
 7) "totalChunks"
 8) (integer) 2
 9) "totalIngested"
10) (integer) 1
11) "totalQueries"
12) (integer) 1
13) "chunkSize"
14) (integer) 512
15) "chunkStrategy"
16) "paragraph"
17) "chunkOverlap"
18) (integer) 64

Compatibility

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

See also

RAG.CREATE, RAG.INGEST, RAG.SEARCH, RAG.DROP, RAG.LIST, AI features guide