KiviDB as a Vector Database

Vector search for AI apps: 59,300 searches a second at recall 0.943 on glove-25-angular, the highest recall at every setting, 1.4 to 1.9x Redis's query engine.

Vector search · HNSW and FLAT · Redis Stack commands

KiviDB as a vector database

Vector, full-text and hybrid search in the engine that already holds your cache. FT.CREATE and FT.SEARCH work as they do in Redis Stack, and HNSW graphs are saved in snapshots, so a restart reloads the index instead of rebuilding it.

  • Retrieval for RAG
  • Semantic search
  • Hybrid text and vector
  • Recommendations
  • LLM response caching
Start freeVector benchmarks 59,300 searches a second at ef 64 0.943 recall@10 on glove-25-angular 1.4–1.9× Redis 8.10’s query engine running shoes marathon trainers trail sneakers track spikes race-day socks running belt espresso machine burr grinder milk frother pour-over kettle cold brew jar single-origin beans noise-cancelling headphones wireless earbuds travel ear cushions in-flight adapter headphone case studio monitors reset your password locked out of account two-factor setup account recovery change login email session timeouts two-person tent sleeping bag trekking poles camp stove headlamp water filter Query “shoes for a 10k race” Query “café-style coffee at home” Query “quiet headphones for flights” Query “I can’t sign in” Query “gear for an overnight hike” FT.SEARCH idx "*=>[KNN 5 @vec $q]" PARAMS 2 q <embedding>

Every point is an embedding. Things that mean the same thing sit close together, so the nearest points to a query are its best matches, even when they share no words.

59,300 Searches a second ef 64, recall 0.943, 100 clients 1.9x Against Redis 8.10 (query engine) ef 64, at higher recall 0.998 Highest recall measured ef 512, recall@10 31 s 1.18M vectors loaded and indexed 38 s on Redis, 13 s on Dragonfly

What teams build

The memory behind an AI application

An embedding is a list of numbers that stands for meaning. Store them, and a search can find what is alike rather than what matches word for word.

RAG

Retrieval for generation

Find the passages closest to a question and hand them to the model, with tag and number filters to keep the answer to what the reader may see.

SEARCH

Semantic and hybrid search

Rank by meaning, by keyword, or by both in one query with FT.HYBRID.

RECOMMEND

Recommendations

Start from an item and ask for the ones nearest to it. New items are searchable the moment they are written.

CACHE

Answers you have already paid for

Keep a model's reply under the embedding of its question, and serve the next question that means the same from memory.

What you get

An index that keeps up with writes

01

Searchable when the write returns

A vector is indexed as part of the write. There is no background indexing phase to wait out before a new record can be found.

02

Recall you choose per query

HNSW with M, EF_CONSTRUCTION and a per-query EF_RUNTIME, or FLAT for exact search over small sets. L2, cosine and inner product.

03

Filters and vectors in one query

Tag, numeric and text filters run before the nearest-neighbour step, and FT.HYBRID combines text and vector scores.

04

The commands you already use

FT.CREATE, FT.SEARCH and FT.AGGREGATE over hashes and JSON, from any Redis client. No new SDK and no second service.

05

Next to the rest of your data

Sessions, caches, counters and embeddings in one database, behind one connection and one set of credentials.

06

Anywhere KiviDB runs

The same binary on your laptop, in Docker, on Kubernetes or as a managed database on KiviDB Cloud.

In practice

An index, a write, a filtered search

Create the index once. Writes to matching keys are indexed as they land, and a search can narrow by tag or number before it looks for neighbours.

The full syntax is in the command reference.

Vector search
FT.CREATE docs ON HASH PREFIX 1 doc: SCHEMA category TAG embedding VECTOR HNSW 6 TYPE FLOAT32 DIM 768 DISTANCE_METRIC COSINE HSET doc:1 category guide embedding <768 float32 bytes> FT.SEARCH docs "(@category:{guide})=>[KNN 10 @embedding $vec AS score]" PARAMS 2 vec <query bytes> DIALECT 2

Measured

The highest recall at every setting

Raising ef trades speed for recall in every engine. KiviDB returned the most accurate results at each setting and the most searches a second at ef 64 and 128; at ef 256 and 512 Dragonfly answered more.

SettingEngineRecall@10Searches a second
ef 64 KiviDB 1.1.00.943 59,300
Dragonfly 2.0.20.912 41,300
Redis 8.10 (query engine)0.912 31,800
ef 128 KiviDB 1.1.00.961 50,700
Dragonfly 2.0.20.937 40,300
Redis 8.10 (query engine)0.937 28,900
ef 256 KiviDB 1.1.00.989 31,500
Dragonfly 2.0.20.979 36,200
Redis 8.10 (query engine)0.979 21,100
ef 512 KiviDB 1.1.00.998 18,700
Dragonfly 2.0.20.995 29,800
Redis 8.10 (query engine)0.995 13,700

Recall is the share of the true ten nearest neighbours returned. 100 parallel clients.

Loading

1.18 million vectors, searchable as they land

Indexing happens in the write, so the load is finished when the last write returns. KiviDB loaded and indexed the dataset in 31 seconds, Redis in 38; Dragonfly was fastest, at 13. Afterwards KiviDB held 1.66 GB, against 1.13 GB and 1.07 GB.

KiviDB 1.1.0 31 s Dragonfly 2.0.2 13 s Redis 8.10 (query engine) 38 s

Time to load and index the dataset. Shorter is better.

Method

How it was run

One engine at a time on the same server, driven from a second machine, with a public tool and a public dataset. The numbers are in the KiviDB repository.

The numbers on GitHub
Tool
redis/vector-db-benchmark, the harness Redis maintains
Dataset
glove-25-angular: 1.18 million vectors, 25 dimensions, cosine distance
Index
HNSW, M=16, EF_CONSTRUCTION=256
Load
100 clients, batches of 64
Search
100 parallel clients at ef 64, 128, 256 and 512
Compared with
Dragonfly 2.0.2 and Redis 8.10 (query engine)
Machines
AWS Graviton3 bare metal: the server on a c7gn.metal confined to 32 cores, the load generator on a second c7gn.metal in the same placement group, one engine at a time.
Date
October 2026

Try it on your own embeddings

Start a free database on KiviDB Cloud, or download the binary and run it yourself. Key-value throughput and latency are on the benchmarks page.

Start freeDownload KiviDB