---
id: "turbopuffer"
type: "component"
kind: "vector-database"
provider: "default"
category: "data"
docs: "https://turbopuffer.com/docs/schema"
url: "https://localhost:3000/catalogue/components/turbopuffer"
---

# turbopuffer

Managed vector and full-text search engine storing namespaces on object storage with an NVMe cache.

| | |
|---|---|
| Provider | [default](https://localhost:3000/catalogue?provider=default) |
| Kind | [Vector database](https://localhost:3000/catalogue/kinds/vector-database) |
| Category | Data |
| Official docs | [https://turbopuffer.com/docs/schema](https://turbopuffer.com/docs/schema) |

## Properties

| property | type | values | required | kind default | this component |
|---|---|---|---|---|---|
| `deployment` | enum | `multi-tenant`, `single-tenant`, `byoc` | no | "multi-tenant" | inherited |
| `dimensions` | integer | — | no | — | inherited |
| `distanceFunction` | enum | `cosine-distance`, `euclidean-squared` | no | — | inherited |
| `distanceMetric` | enum | `cosine`, `euclidean`, `dot-product` | no | — | inherited |
| `hybridSearch` | boolean | — | no | false | **true** |
| `indexType` | enum | `flat`, `hnsw`, `ivf`, `disk-ann`, `lsh` | no | — | inherited |
| `managed` | boolean | — | no | false | **true** |
| `metadataFiltering` | boolean | — | no | false | **true** |
| `namespaces` | boolean | — | no | false | **true** |
| `quantization` | enum | `none`, `scalar`, `product`, `binary` | no | "none" | inherited |
| `replicas` | integer | — | no | — | inherited |
| `storageBackend` | enum | `object-storage` | no | "object-storage" | inherited |

Bold values are the ones this component pins.

## Rules that apply · 0

No rule selects this kind or its category.

## Other products of the same kind · 23

- [Alibaba Cloud Milvus](https://localhost:3000/catalogue/components/alibaba-milvus.md) `alibaba-milvus` — alibabacloud
- [Amazon S3 Vectors](https://localhost:3000/catalogue/components/aws-s3-vectors.md) `aws-s3-vectors` — aws
- [Agent Memory](https://localhost:3000/catalogue/components/cloudflare-agent-memory.md) `cloudflare-agent-memory` — cloudflare
- [Cloudflare Vectorize](https://localhost:3000/catalogue/components/cloudflare-vectorize.md) `cloudflare-vectorize` — cloudflare
- [Chroma](https://localhost:3000/catalogue/components/chroma.md) `chroma` — default
- [Deep Lake](https://localhost:3000/catalogue/components/deeplake.md) `deeplake` — default
- [Epsilla](https://localhost:3000/catalogue/components/epsilla.md) `epsilla` — default
- [KDB.AI](https://localhost:3000/catalogue/components/kdb-ai.md) `kdb-ai` — default
- [LanceDB](https://localhost:3000/catalogue/components/lancedb.md) `lancedb` — default
- [Marqo](https://localhost:3000/catalogue/components/marqo.md) `marqo` — default
- [Milvus](https://localhost:3000/catalogue/components/milvus.md) `milvus` — default
- [MyScale](https://localhost:3000/catalogue/components/myscale.md) `myscale` — default
- [pgvector](https://localhost:3000/catalogue/components/pgvector.md) `pgvector` — default
- [pgvectorscale](https://localhost:3000/catalogue/components/pgvectorscale.md) `pgvectorscale` — default
- [Pinecone](https://localhost:3000/catalogue/components/pinecone.md) `pinecone` — default
- [Qdrant](https://localhost:3000/catalogue/components/qdrant.md) `qdrant` — default
- [Vald](https://localhost:3000/catalogue/components/vald.md) `vald` — default
- [Generic vector database](https://localhost:3000/catalogue/components/vector-database.md) `vector-database` — default
- [Vespa Cloud](https://localhost:3000/catalogue/components/vespa-cloud.md) `vespa-cloud` — default
- [Weaviate](https://localhost:3000/catalogue/components/weaviate.md) `weaviate` — default
- [Zilliz Cloud](https://localhost:3000/catalogue/components/zilliz-cloud.md) `zilliz-cloud` — default
- [DigitalOcean Vector Databases](https://localhost:3000/catalogue/components/digitalocean-vector-database.md) `digitalocean-vector-database` — digitalocean
- [Vertex AI Vector Search](https://localhost:3000/catalogue/components/google-vertex-ai-vector-search.md) `google-vertex-ai-vector-search` — gcp

## Use it in a design

```yaml
nodes:
  - { id: "turbopuffer", component: "turbopuffer" }
```

## Source (`component` YAML, verbatim)

```yaml
# yaml-language-server: $schema=../../schema/component.schema.json
# turbopuffer: managed search engine keeping state in object storage with an NVMe and memory cache.
# Docs: namespaces are created implicitly on first write, filters run against an inverted index and
# BM25 full-text search combines with vector queries; multi-tenant is the default deployment.
schemaVersion: "1"
type: "component"
id: "turbopuffer"
kind: "vector-database"
provider: "default"
docs: "https://turbopuffer.com/docs/schema"
defaults:
  metadataFiltering: true
  hybridSearch: true
  namespaces: true
  managed: true
properties:
  deployment:
    type: "enum"
    values: ["multi-tenant", "single-tenant", "byoc"]
    default: "multi-tenant"
  storageBackend:
    type: "enum"
    values: ["object-storage"]
    default: "object-storage"
  distanceFunction:
    type: "enum"
    values: ["cosine-distance", "euclidean-squared"]
```

Human page: https://localhost:3000/catalogue/components/turbopuffer