In-memory

Mon, 01 Jan 0001 00:00:00 +0000

The in-memory vector store keeps every collection in the memory of the Dapr sidecar. Use it for local development and tests that need no external vector database. It is not durable: collections and records are lost when the sidecar stops, and they aren’t shared between sidecar instances.

Component format

To set up an in-memory vector store, create a component of type vector.in-memory. See this guide on how to create and apply a vector store configuration.

Meilisearch

Mon, 01 Jan 0001 00:00:00 +0000

Component format

To set up a Meilisearch vector store, create a component of type vector.meilisearch. See this guide on how to create and apply a vector store configuration.

apiVersion: dapr.io/v1alpha1
kind: Component
metadata:
 name: <NAME>
spec:
 type: vector.meilisearch
 version: v1
 metadata:
 - name: host
 value: "http://localhost:7700"
 - name: apiKey
 value: "<API_KEY>"
 - name: timeout
 value: "10s"

Warning

The above example uses secrets as plain strings. It is recommended to use a secret store for the secrets, as described here.

Spec metadata fields

Field	Required	Details	Example
`host`	Y	The Meilisearch host URL.	`"http://localhost:7700"`
`apiKey`	N	The Meilisearch API key. Required when the Meilisearch instance is protected with a master key. Defaults to `""`.	`"masterKey"`
`timeout`	N	The HTTP client timeout for requests to Meilisearch, as a Go duration.	`"10s"`

Supported features

Feature	Supported	Details
Dense vectors	Y	Vectors are stored as user-provided embeddings.
Distance metrics	Cosine only	See distance metric and scores.
Query by ID	Y	`byId` queries use Meilisearch’s similar documents search. A `byId` that matches no record fails that query with `NOT_FOUND`.
Score threshold	Y
Metadata filtering	Y	`$regex` isn’t supported.
Batch query	Y	Each query is evaluated independently.
Queued acknowledgement	Y	Writes return `INDEX_ACK_QUEUED` when Meilisearch enqueues the task, so `INDEXING_WAIT_TIMEOUT_ACTION_CONTINUE_ASYNC` is supported.
Wait for completion	Y	See waiting for writes.

Collection settings

A collection is a Meilisearch index with a single userProvided embedder named default with the requested dimensions. Record metadata is filterable by default.

Vector component specs on Dapr Docs

In-memory

Component format

Meilisearch

Component format

Warning

Spec metadata fields

Supported features

Collection settings