Qdrant — an open-source vector database and similarity-search engine for embeddings, powering semantic search and RAG. Deployed as a host-networked Nomad service with a persistent volume; pairs with the ollama pack for a self-hosted AI stack.
Save as values.hcl, edit, then run:
# The name of the Nomad job.
job_name = "qdrant"
# The Nomad namespace to deploy into.
namespace = "default"
# The datacenters to deploy to.
datacenters = ["*"]
# The Qdrant container image. Pin a tag in production.
image = "qdrant/qdrant:latest"
# Host port for the REST API + web dashboard (/dashboard).
http_port = 6333
# Host port for the gRPC API.
grpc_port = 6334
# Optional API key. Empty = open (no auth). Set it to require an api-key header on all requests.
api_key = ""
# Docker named volume for /qdrant/storage (collections + vectors). Qdrant runs as root, so a fresh volume is writable. Back it up.
data_volume = "qdrant_data"
# Placement constraints — pin to one node so the local volume stays put. On a nomploy cluster: attribute = "$${meta.nomploy_control_plane}", operator = "=", value = "true".
constraints = []
# The task resources. Raise memory for large collections (vectors are held in RAM by default).
resources = {
cpu = 500
memory = 512
}
| Name | Type | Default | Description |
|---|---|---|---|
| job_name | string | "qdrant" | The name of the Nomad job. |
| namespace | string | "default" | The Nomad namespace to deploy into. |
| datacenters | list | ["*"] | The datacenters to deploy to. |
| image | string | "qdrant/qdrant:latest" | The Qdrant container image. Pin a tag in production. |
| http_port | number | 6333 | Host port for the REST API + web dashboard (/dashboard). |
| grpc_port | number | 6334 | Host port for the gRPC API. |
| api_key key | string | "" | Optional API key. Empty = open (no auth). Set it to require an api-key header on all requests. |
| data_volume | string | "qdrant_data" | Docker named volume for /qdrant/storage (collections + vectors). Qdrant runs as root, so a fresh volume is writable. Back it up. |
| constraints | list | [] | Placement constraints — pin to one node so the local volume stays put. On a nomploy cluster: attribute = "$${meta.nomploy_control_plane}", operator = "=", value = "true". |
| resources | object | {
cpu = 500
memory = 512
} | The task resources. Raise memory for large collections (vectors are held in RAM by default). |
No variables match.
Qdrant — an open-source vector database and similarity-search
engine for embeddings: the storage/retrieval layer for semantic search and RAG. Host-networked
Nomad service with a persistent volume. Pairs with the ollama pack for a self-hosted AI stack.
nomad-pack registry add nomploy github.com/Nomploy/nomad-packs
nomad-pack run qdrant --registry nomploy
In nomploy: create a Compose service, type Nomad Pack, pack qdrant, custom registry
github.com/Nomploy/nomad-packs, then Deploy. Dashboard at http://<node-ip>:6333/dashboard.
| Variable | Default | Notes |
|---|---|---|
image |
qdrant/qdrant:latest |
Pin a tag in production. |
http_port / grpc_port |
6333 / 6334 |
REST/dashboard + gRPC. |
api_key |
"" |
Empty = open; set to require an api-key header. |
data_volume |
qdrant_data |
Collections + vectors. Back it up. |
constraints |
[] |
Pin to a node so the local volume stays put. |
resources |
cpu 500 / mem 512 |
Raise memory for large collections. |
count is fixed to 1 (local volume). Pin with constraints.api_key and front with TLS before exposing it beyond a trusted network.