Full-fidelity recall at any scale. A native on-disk graph that scales without giving up accuracy — and the same REST shape your team already uses, so migration is a URL swap, not a rewrite.
Full-fidelity recall, on disk, at any scale — no shortcuts, no accuracy trade-offs. A drop-in replacement for your existing vector store, with the same REST shape you already know.
No shortcuts, no trade-offs. A native on-disk graph that scales without giving up accuracy. Cosine, and Euclidean metrics supported.
POST /v1/vector/indexes/my-idx/query
{
"vector": [0.12, 0.43, ...],
"top_k": 10,
"metric": "cosine"
}Familiar index primitives: create, list, describe, delete. Pick your dimension and metric at creation; per-index quotas enforced at the engine level.
POST /v1/vector/indexes
{ "name": "products", "dimension": 1536, "metric": "cosine" }Upsert thousands of vectors per call. Query, fetch by ID, delete in bulk, and scroll through entire indexes — everything you need to run a production vector store.
POST /v1/vector/indexes/my-idx/vectors
{
"vectors": [
{ "id": "doc-1", "values": [...], "metadata": { "category": "ai" } },
{ "id": "doc-2", "values": [...], "metadata": { "category": "db" } }
]
}Store arbitrary JSON payload per vector; filter at query time with operators like $eq, $lt, $gt, $in. Filtered queries stay fast — filters fuse with the search itself.
{
"vector": [...],
"top_k": 10,
"filter": {
"category": { "$eq": "electronics" },
"price": { "$lt": 500 }
}
}Each tenant's indexes are fully isolated at the engine level — no cross-tenant leakage, even under collision. Hard tier caps and real-time quota enforcement.
Reach for REST when you want quick integration, or native gRPC for throughput-sensitive workloads. The HTTP shape is a drop-in replacement for your existing vector store — most clients work with minimal changes.
Most vector databases quietly trade accuracy for speed. Ours doesn't — the graph is built once, lives on disk, and serves full-fidelity results from the first query onward.
Same familiar API shape, better recall, smaller bill. Migration is a URL swap — not a rewrite.
Embed your docs, store the vectors, retrieve the right ones. 100% recall means the relevant chunk is always in the top-k — no "why did the LLM miss that?" moments.
Content-based or collaborative filtering with millisecond latency. Payload filters let you scope by availability, price, or cohort without a second query.
"Find me items like this one." Drop in your embeddings, pick your metric (cosine / dot / Euclidean), and get scored top-k results with metadata attached.
Find the paraphrased post, the almost-identical image, the copy-pasted commit message. 100% recall keeps the near-misses from slipping through.
Every query returns exact nearest neighbors — not approximations. Predictable monthly pricing with no surprise fees.
For prototypes & learning
For side projects & early RAG
For teams running production
For regulated orgs, self-hosted
Need more vectors, indexes, or ops? All paid plans support flexible add-ons. Save up to 18% with a Memory + Vector bundle. See full pricing →
Join the private beta. Get early access to GitDB, Memory, and Vector services.