Files
anything-llm/cloud-deployments/helm/charts/anythingllm/README.md.gotmpl
2026-04-22 15:15:59 -07:00

103 lines
3.8 KiB
Go Template

{{ template "chart.header" . }}
{{ template "chart.deprecationWarning" . }}
{{ template "chart.badgesSection" . }}
![AnythingLLM](https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/master/images/wordmark.png)
[AnythingLLM](https://github.com/Mintplex-Labs/anything-llm)
{{ template "chart.description" . }}
{{ template "chart.homepageLine" . }}
{{ template "chart.maintainersSection" . }}
{{ template "chart.sourcesSection" . }}
{{ template "chart.requirementsSection" . }}
**Configuration & Usage**
- **Config vs Secrets:** This chart exposes application configuration via two mechanisms:
- `config` (in `values.yaml`) — rendered into a `ConfigMap` and injected using `envFrom` in the pod. Do NOT place sensitive values (API keys, secrets) in `config` because `ConfigMap`s are not encrypted.
- `env` / `envFrom` — the preferred way to inject secrets. Use Kubernetes `Secret` objects and reference them from `env` (with `valueFrom.secretKeyRef`) or `envFrom.secretRef`.
- **Storage & STORAGE_DIR mapping:** The chart creates (or mounts) a `PersistentVolumeClaim` using the `persistentVolume.*` settings. The container mount path is set from `persistentVolume.mountPath`. Ensure the container `STORAGE_DIR` config key matches that path (defaults are set in `values.yaml`).
**Providing API keys & secrets (recommended)**
Use Kubernetes Secrets. Below are example workflows and `values.yaml` snippets.
1) Create a Kubernetes Secret with API keys:
```
kubectl create secret generic openai-secret --from-literal=OPENAI_KEY="sk-..."
# or from a file
# kubectl create secret generic openai-secret --from-file=OPENAI_KEY=/path/to/keyfile
```
2) Reference the Secret from `values.yaml` using `envFrom` (recommended when your secret contains multiple env keys):
```yaml
envFrom:
- secretRef:
name: openai-secret
```
This will inject all key/value pairs from the `openai-secret` Secret as environment variables in the container.
3) Or reference a single secret key via `env` (explicit mapping):
```yaml
env:
- name: OPENAI_KEY
valueFrom:
secretKeyRef:
name: openai-secret
key: OPENAI_KEY
```
Notes:
- Avoid placing secret values into `config:` (the chart's `ConfigMap`) — `ConfigMap`s are visible to anyone who can read the namespace. Use `Secret` objects for any credentials/tokens.
- If you use a GitOps workflow, consider integrating an external secret operator (ExternalSecrets, SealedSecrets, etc.) so you don't store raw secrets in Git.
**Example `values-secret.yaml` to pass during `helm install`**
```yaml
image:
repository: mintplexlabs/anythingllm
tag: "1.12.1"
service:
type: ClusterIP
port: 3001
# Reference secret containing API keys
envFrom:
- secretRef:
name: openai-secret
# Optionally override other values
persistentVolume:
size: 16Gi
mountPath: /storage
```
Install with:
```
helm install my-anythingllm ./anythingllm -f values-secret.yaml
```
**Best practices & tips**
- Use `envFrom` for convenience when many environment variables are stored in a single `Secret` and use `env`/`valueFrom` for explicit single-key mappings.
- Use `kubectl create secret generic` or your secrets management solution. If you need to reference multiple different provider keys (OpenAI, Anthropic, etc.), create a single `Secret` with multiple keys or multiple Secrets and add multiple `envFrom` entries.
- Keep probe paths and `service.port` aligned. If your probes fail after deployment, check that the probe `port` matches the container port (or named port `http`) and that the `path` is valid.
- For storage, if you have a pre-existing PVC set `persistentVolume.existingClaim` to the PVC name; the chart will mount that claim (and will not attempt to create a new PVC).
- For production, provide resource `requests` and `limits` in `values.yaml` to prevent scheduler starvation and to control cost.
{{ template "chart.valuesSection" . }}