Overview
By default, LILT comes with MinIO enabled. However, if an environment has access to S3 directly, this is the recommended approach. This document covers configuring LILT to use S3 instead of MinIO—it does not cover how to transition an existing MinIO deployment to S3. Please work with your program manager to facilitate this process. There are two options for authentication with s3 depending on the type of cluster, managed or unmanaged:- Unmanaged: Identity and Access Management (IAM) that utilizes a AWS access and secret key
- Managed (EKS): IAM Roles for Service Accounts (IRSA) that attaches a service account to a pod
Uninstall MinIO
There is currently no mechanism in LILT to automatically remove MinIO from a deployment. This is a feature we are working to implement by the end of 2025. In the mean time, MinIO may be removed directly by:Copy
Ask AI
helm uninstall minio
Configure LILT
Update Secrets
LILT ships with a default AWS credential. This needs to be removed. Editlilt/environments/lilt/secrets.yaml
and remove the following line:
Copy
Ask AI
front:
onpremValues:
config:
front_secret_values:
s3secretkey: testsecretkey # Only remove this line
Option 1: Unmanaged IAM
Update Values
First, collect the following information for your bucket:Copy
Ask AI
AWS_ACCESS_KEY: <AWS_ACCESS_KEY>
AWS_SECRET_KEY: <AWS_SECRET_KEY>
AWS_BUCKET: <AWS_BUCKET>
AWS_REGION: <AWS_REGION>
AWS_S3_ENDPOINT_URL: <AWS_S3_ENDPOINT_URL>
AWS_S3_ENDPOINT_URL_SSL: <AWS_S3_ENDPOINT_URL_SSL>
Copy
Ask AI
AWS_S3_ENDPOINT_URL: http://s3.us-east-1.amazonaws.com
AWS_S3_ENDPOINT_URL_SSL: https://s3.us-east-1.amazonaws.com
lilt/environments/lilt/values.yaml
.
Add all of the following values, replacing values within <>
with the values documented from above:
Copy
Ask AI
AWS_ACCESS_KEY: <AWS_ACCESS_KEY>
AWS_SECRET_KEY: <AWS_SECRET_KEY>
AWS_BUCKET: <AWS_BUCKET>
AWS_REGION: <AWS_REGION>
AWS_S3_ENDPOINT_URL: <AWS_S3_ENDPOINT_URL>
AWS_S3_ENDPOINT_URL_SSL: <AWS_S3_ENDPOINT_URL_SSL>
front:
onpremValues:
env:
UPLOADER_EVENT_SOURCE_TYPE: s3
MM_BUCKET: <AWS_BUCKET>
config:
front_secret_values:
awsSecretAccessKey: <AWS_SECRET_KEY>
s3secretkey: <AWS_SECRET_KEY>
front_configmap_values:
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
s3-region: <AWS_REGION>
awsRegion: <AWS_REGION>
s3accesskey: <AWS_ACCESS_KEY>
awsS3Bucket: <AWS_BUCKET>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
awsS3EndpointUrlPublic: <AWS_S3_ENDPOINT_URL_SSL>
lexicon:
onpremValues:
app:
bucketname: <AWS_BUCKET>
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
s3-region: <AWS_REGION>
init:
filePaths: "s3://<AWS_BUCKET>/lexicon-data/panlex/panlex-20220201-json_compiled.scored-rev-filter.json.gz,s3://<AWS_BUCKET>/lexicon-data/ranking/linguee_en_de_es_fr_pt_nl_it_zh_esfr_itfr_da_sv_no_pl_ru_fi_20170513_fixes.csv,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_da.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_de.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_en.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_es.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_fr.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_it.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_nl.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_no.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_pl.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_pt.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_sv.json"
extraInitContainer:
outputPath: "s3://<AWS_BUCKET>/lexicon-data/"
converter:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
s3-privatekey: <AWS_SECRET_KEY>
s3-accesskey: <AWS_ACCESS_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
app:
bucketname: <AWS_BUCKET>
args:
s3-endpoint: <AWS_S3_ENDPOINT_URL_SSL>
s3-region: <AWS_REGION>
bucket: <AWS_BUCKET>
assignment:
onpremValues:
app:
bucketname: <AWS_BUCKET>
auditlog:
onpremValues:
app:
bucketname: <AWS_BUCKET>
batch-tb:
onpremValues:
app:
bucketname: <AWS_BUCKET>
tb:
onpremValues:
app:
bucketname: <AWS_BUCKET>
tm:
onpremValues:
app:
bucketname: <AWS_BUCKET>
args:
s3-endpoint: <AWS_S3_ENDPOINT_URL_SSL>
s3-region: <AWS_REGION>
bucket: <AWS_BUCKET>
indexer:
onpremValues:
app:
bucketname: <AWS_BUCKET>
linguist:
onpremValues:
app:
bucketname: <AWS_BUCKET>
memory:
onpremValues:
app:
bucketname: <AWS_BUCKET>
qa:
onpremValues:
app:
bucketname: <AWS_BUCKET>
search:
onpremValues:
app:
bucketname: <AWS_BUCKET>
segment:
onpremValues:
app:
bucketname: <AWS_BUCKET>
tag:
onpremValues:
app:
bucketname: <AWS_BUCKET>
watchdog:
onpremValues:
app:
bucketname: <AWS_BUCKET>
job:
onpremValues:
app:
bucketname: <AWS_BUCKET>
args:
s3-endpoint: <AWS_S3_ENDPOINT_URL_SSL>
s3-region: <AWS_REGION>
bucket: <AWS_BUCKET>
workflow:
onpremValues:
app:
bucketname: <AWS_BUCKET>
args:
s3-endpoint: <AWS_S3_ENDPOINT_URL_SSL>
s3-region: <AWS_REGION>
bucket: <AWS_BUCKET>
file-translation:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
s3-privatekey: <AWS_SECRET_KEY>
s3-accesskey: <AWS_ACCESS_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
app:
bucketname: <AWS_BUCKET>
args:
s3-endpoint: <AWS_S3_ENDPOINT_URL_SSL>
s3-region: <AWS_REGION>
bucket: <AWS_BUCKET>
s3-accesskey: <AWS_ACCESS_KEY>
s3-privatekey: <AWS_SECRET_KEY>
file-job:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
s3-privatekey: <AWS_SECRET_KEY>
s3-accesskey: <AWS_ACCESS_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
init:
filePaths: "s3://<AWS_BUCKET>/tesseract/eng.traineddata,s3://<AWS_BUCKET>/tesseract/deu.traineddata,s3://<AWS_BUCKET>/tesseract/fra.traineddata,s3://<AWS_BUCKET>/tesseract/spa.traineddata,s3://<AWS_BUCKET>/tesseract/ara.traineddata,s3://<AWS_BUCKET>/tesseract/nor.traineddata,s3://<AWS_BUCKET>/tesseract/ind.traineddata,s3://<AWS_BUCKET>/tesseract/chi_tra.traineddata,s3://<AWS_BUCKET>/tesseract/chi_sim.traineddata,s3://<AWS_BUCKET>/tesseract/por.traineddata,s3://<AWS_BUCKET>/tesseract/nld.traineddata,s3://<AWS_BUCKET>/tesseract/ita.traineddata,s3://<AWS_BUCKET>/tesseract/dan.traineddata,s3://<AWS_BUCKET>/tesseract/swe.traineddata,s3://<AWS_BUCKET>/tesseract/pol.traineddata,s3://<AWS_BUCKET>/tesseract/rus.traineddata,s3://<AWS_BUCKET>/tesseract/fin.traineddata,s3://<AWS_BUCKET>/tesseract/jpn.traineddata,s3://<AWS_BUCKET>/tesseract/kor.traineddata,s3://<AWS_BUCKET>/tesseract/ukr.traineddata,s3://<AWS_BUCKET>/tesseract/ron.traineddata,s3://<AWS_BUCKET>/tesseract/heb.traineddata,s3://<AWS_BUCKET>/tesseract/tha.traineddata,s3://<AWS_BUCKET>/tesseract/hin.traineddata,s3://<AWS_BUCKET>/tesseract/tur.traineddata,s3://<AWS_BUCKET>/tesseract/vie.traineddata,s3://<AWS_BUCKET>/tesseract/ell.traineddata,s3://<AWS_BUCKET>/tesseract/afr.traineddata,s3://<AWS_BUCKET>/tesseract/ces.traineddata,s3://<AWS_BUCKET>/tesseract/slk.traineddata,s3://<AWS_BUCKET>/tesseract/hun.traineddata,s3://<AWS_BUCKET>/tesseract/fas.traineddata,s3://<AWS_BUCKET>/tesseract/jav.traineddata,s3://<AWS_BUCKET>/tesseract/pus.traineddata,s3://<AWS_BUCKET>/tesseract/urd.traineddata,s3://<AWS_BUCKET>/tesseract/fas.traineddata,s3://<AWS_BUCKET>/tesseract/ben.traineddata,s3://<AWS_BUCKET>/tesseract/hrv.traineddata,s3://<AWS_BUCKET>/tesseract/swa.traineddata,s3://<AWS_BUCKET>/tesseract/slv.traineddata,s3://<AWS_BUCKET>/tesseract/bul.traineddata,s3://<AWS_BUCKET>/tesseract/fil.traineddata,s3://<AWS_BUCKET>/tesseract/kan.traineddata,s3://<AWS_BUCKET>/tesseract/guj.traineddata,s3://<AWS_BUCKET>/tesseract/pan.traineddata,s3://<AWS_BUCKET>/tesseract/mal.traineddata,s3://<AWS_BUCKET>/tesseract/mar.traineddata,s3://<AWS_BUCKET>/tesseract/tam.traineddata,s3://<AWS_BUCKET>/tesseract/tel.traineddata,s3://<AWS_BUCKET>/tesseract/sqi.traineddata"
extraInitContainer:
outputPath: "s3://<AWS_BUCKET>/tesseract/"
BUCKETNAME: <AWS_BUCKET>
app:
bucketname: <AWS_BUCKET>
args:
s3-endpoint: <AWS_S3_ENDPOINT_URL_SSL>
s3-region: <AWS_REGION>
bucket: <AWS_BUCKET>
dataflow:
onpremValues:
env:
MINIO_ENDPOINT: s3://<AWS_BUCKET>
MINIO_ACCESS_KEY: <AWS_ACCESS_KEY>
MINIO_SECRET_KEY: <AWS_SECRET_KEY>
MINIO_REGION: <AWS_REGION>
translatev4:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
init:
bucket: <AWS_BUCKET>
outputPath: "s3://<AWS_BUCKET>/trained/"
updatev4:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
wpaDataStoreBasePath: "s3://<AWS_BUCKET>/wpa/"
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
langid:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
update-managerv4:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
routing:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
batchv4:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
batch-worker-gpuv4:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
llm-inference:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
init:
bucket: <AWS_BUCKET>
outputPath: "s3://<AWS_BUCKET>/trained/"
automqm:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
alignment:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
init:
bucket: <AWS_BUCKET>
outputPath: "s3://<AWS_BUCKET>/trained/"
tag-projection:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
init:
bucket: <AWS_BUCKET>
outputPath: "s3://<AWS_BUCKET>/trained/"
nncache:
onpremValues:
config:
awsSecretAccessKey: <AWS_SECRET_KEY>
awsAccessKeyId: <AWS_ACCESS_KEY>
bucket: <AWS_BUCKET>
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
Option 2: Managed (EKS) IRSA
Create AWS IAM Policy and Role
In the AWS console or via terraform, create IAM role and policy for accessing the s3 bucket and then attach them to each other. The following assumes that you are using OIDC provider.Copy
Ask AI
{
"Version": "2012-10-17",
"Statement": [
{
"Effect": "Allow",
"Action": [
"s3:GetObject",
"s3:PutObject",
"s3:ListBucket"
],
"Resource": [
"arn:aws:s3:::<my-bucket-name>",
"arn:aws:s3:::<my-bucket-name>/*"
]
}
]
}
Copy
Ask AI
{
"Version": "2012-10-17",
"Statement": [
{
"Effect": "Allow",
"Principal": {
"Federated": "arn:aws:iam::<ACCOUNT_ID>:oidc-provider/<OIDC_PROVIDER>"
},
"Action": "sts:AssumeRoleWithWebIdentity",
"Condition": {
"StringEquals": {
"<OIDC_PROVIDER>:sub": "system:serviceaccount:<SERVICE_ACCOUNT_NAMESPACE>:<SERVICE_ACCOUNT_NAME>"
}
}
}
]
}
Copy
Ask AI
arn:aws:iam::<ACCOUNT_ID>:role/<role_name>
Create Service Account
Either via terraform or kubectl, create a service account for use by the pods. Example using kubectl:Copy
Ask AI
kubectl create serviceaccount <service-account-name> -n <your-namespace>
kubectl annotate serviceaccount <service-account-name> \
-n <your-namespace> \
eks.amazonaws.com/role-arn=<your-arm>
Update RBAC
Pod can only reference ONE service account. This overrides any default cluster permissions so any additional requirements must be included within RBAC roles. For example,neural
requires access to pods
and deployments
.
Create role yaml and apply to cluster:
Copy
Ask AI
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
name: <role-name>
namespace: <your-namespace>
rules:
- apiGroups: [""]
resources: ["deployments", "deployments/scale", "jobs", "pods", "pods/status", "pods/log", "configmaps", "secrets"]
verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
- apiGroups: ["apps"]
resources: ["deployments/scale"]
verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
Copy
Ask AI
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: <bind-role-name>
namespace: <your-namespace>
subjects:
- kind: ServiceAccount
name: <service-account-name>
namespace: <your-namespace>
roleRef:
kind: Role
name: <role-name>
apiGroup: rbac.authorization.k8s.io
Update Values
First, collect the following information for your bucket:Copy
Ask AI
AWS_BUCKET: <AWS_BUCKET>
AWS_REGION: <AWS_REGION>
AWS_S3_ENDPOINT_URL: <AWS_S3_ENDPOINT_URL>
AWS_S3_ENDPOINT_URL_SSL: <AWS_S3_ENDPOINT_URL_SSL>
STORAGETYPE : s3
Copy
Ask AI
AWS_S3_ENDPOINT_URL: http://s3.us-east-1.amazonaws.com
AWS_S3_ENDPOINT_URL_SSL: https://s3.us-east-1.amazonaws.com
Copy
Ask AI
<SERVICE_ACCOUNT>: <service-account-name>
lilt/environments/lilt/values.yaml
.
Add all of the following values, and replacing values within <>
with the values documented from above:
Copy
Ask AI
front:
enabled: true
env:
MM_BUCKET: <AWS_BUCKET>
UPLOADER_EVENT_SOURCE_TYPE: <STORAGETYPE>
UPLOADER_STORAGETYPE: <STORAGETYPE>
config:
front_configmap_values:
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
awsS3EndpointUrlPublic: <AWS_S3_ENDPOINT_URL>
awsS3Bucket: <AWS_BUCKET>
s3accesskey: ""
front_secret_values:
awsSecretAccessKey: ""
s3secretkey: ""
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
converter:
enabled: true
onpremValues:
config:
app:
bucketname: <AWS_BUCKET>
args:
s3SslVerificationMode: NONE
storagetype: <STORAGETYPE>
bucket: <AWS_BUCKET>
s3-endpoint: <AWS_S3_ENDPOINT_URL>
s3-region: <AWS_REGION>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
qa:
enabled: true
onpremValues:
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
linguist:
enabled: true
onpremValues:
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
search:
enabled: true
onpremValues:
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
tm:
enabled: true
onpremValues:
app:
bucketname: <AWS_BUCKET>
args:
storagetype: <STORAGETYPE>
bucket: <AWS_BUCKET>
s3-endpoint: <AWS_S3_ENDPOINT_URL>
s3-region: <AWS_REGION>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
tb:
enabled: true
onpremValues:
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
batch-tb:
enabled: true
onpremValues:
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
indexer:
enabled: true
onpremValues:
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
lexicon:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsRegion: <AWS_REGION>
app:
bucketname: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
init:
filePaths: "s3://<AWS_BUCKET>/lexicon-data/panlex/panlex-20220201-json_compiled.scored-rev-filter.json.gz,s3://<AWS_BUCKET>/lexicon-data/ranking/linguee_en_de_es_fr_pt_nl_it_zh_esfr_itfr_da_sv_no_pl_ru_fi_20170513_fixes.csv,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_da.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_de.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_en.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_es.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_fr.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_it.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_nl.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_no.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_pl.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_pt.json,s3://<AWS_BUCKET>/lexicon-data/morphology/morph_sv.json"
extraInitContainer:
outputPath: "s3://<AWS_BUCKET>/lexicon-data/"
segment:
enabled: true
onpremValues:
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
file-translation:
enabled: true
onpremValues:
app:
bucketname: <AWS_BUCKET>
args:
s3-accesskey: ""
s3-privatekey: ""
storagetype: <STORAGETYPE>
bucket: <AWS_BUCKET>
s3-endpoint: <AWS_S3_ENDPOINT_URL>
s3-region: <AWS_REGION>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
job:
enabled: true
onpremValues:
env:
BUCKETNAME: <AWS_BUCKET>
app:
bucketname: <AWS_BUCKET>
args:
storagetype: <STORAGETYPE>
bucket: <AWS_BUCKET>
s3-endpoint: <AWS_S3_ENDPOINT_URL>
s3-region: <AWS_REGION>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
tag:
enabled: true
onpremValues:
env:
BUCKETNAME: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
auditlog:
enabled: true
onpremValues:
env:
BUCKETNAME: <AWS_BUCKET>
assignment:
enabled: true
onpremValues:
env:
BUCKETNAME: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
workflow:
enabled: true
onpremValues:
env:
BUCKETNAME: <AWS_BUCKET>
app:
bucketname: <AWS_BUCKET>
args:
storagetype: <STORAGETYPE>
bucket: <AWS_BUCKET>
s3-endpoint: <AWS_S3_ENDPOINT_URL>
s3-region: <AWS_REGION>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
dataflow:
enabled: true
onpremValues:
env:
MINIO_ENDPOINT: <AWS_S3_ENDPOINT_URL>
MINIO_ACCESS_KEY: ""
MINIO_SECRET_KEY: ""
MINIO_REGION: <AWS_REGION>
MINIO_SSL_CERT_FILE: ""
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
file-job:
enabled: true
onpremValues:
config:
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsRegion: <AWS_REGION>
awsSecretAccessKey: ""
awsAccessKeyId: ""
env:
BUCKETNAME: <AWS_BUCKET>
app:
bucketname: <AWS_BUCKET>
args:
storagetype: <STORAGETYPE>
bucket: <AWS_BUCKET>
s3-endpoint: <AWS_S3_ENDPOINT_URL>
s3-region: <AWS_REGION>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
init:
filePaths: "s3://<AWS_BUCKET>/tesseract/eng.traineddata,s3://<AWS_BUCKET>/tesseract/deu.traineddata,s3://<AWS_BUCKET>/tesseract/fra.traineddata,s3://<AWS_BUCKET>/tesseract/spa.traineddata,s3://<AWS_BUCKET>/tesseract/ara.traineddata,s3://<AWS_BUCKET>/tesseract/nor.traineddata,s3://<AWS_BUCKET>/tesseract/ind.traineddata,s3://<AWS_BUCKET>/tesseract/chi_tra.traineddata,s3://<AWS_BUCKET>/tesseract/chi_sim.traineddata,s3://<AWS_BUCKET>/tesseract/por.traineddata,s3://<AWS_BUCKET>/tesseract/nld.traineddata,s3://<AWS_BUCKET>/tesseract/ita.traineddata,s3://<AWS_BUCKET>/tesseract/dan.traineddata,s3://<AWS_BUCKET>/tesseract/swe.traineddata,s3://<AWS_BUCKET>/tesseract/pol.traineddata,s3://<AWS_BUCKET>/tesseract/rus.traineddata,s3://<AWS_BUCKET>/tesseract/fin.traineddata,s3://<AWS_BUCKET>/tesseract/jpn.traineddata,s3://<AWS_BUCKET>/tesseract/kor.traineddata,s3://<AWS_BUCKET>/tesseract/ukr.traineddata,s3://<AWS_BUCKET>/tesseract/ron.traineddata,s3://<AWS_BUCKET>/tesseract/heb.traineddata,s3://<AWS_BUCKET>/tesseract/tha.traineddata,s3://<AWS_BUCKET>/tesseract/hin.traineddata,s3://<AWS_BUCKET>/tesseract/tur.traineddata,s3://<AWS_BUCKET>/tesseract/vie.traineddata,s3://<AWS_BUCKET>/tesseract/ell.traineddata,s3://<AWS_BUCKET>/tesseract/afr.traineddata,s3://<AWS_BUCKET>/tesseract/ces.traineddata,s3://<AWS_BUCKET>/tesseract/slk.traineddata,s3://<AWS_BUCKET>/tesseract/hun.traineddata,s3://<AWS_BUCKET>/tesseract/fas.traineddata,s3://<AWS_BUCKET>/tesseract/jav.traineddata,s3://<AWS_BUCKET>/tesseract/pus.traineddata,s3://<AWS_BUCKET>/tesseract/urd.traineddata,s3://<AWS_BUCKET>/tesseract/fas.traineddata,s3://<AWS_BUCKET>/tesseract/ben.traineddata,s3://<AWS_BUCKET>/tesseract/hrv.traineddata,s3://<AWS_BUCKET>/tesseract/swa.traineddata,s3://<AWS_BUCKET>/tesseract/slv.traineddata,s3://<AWS_BUCKET>/tesseract/bul.traineddata,s3://<AWS_BUCKET>/tesseract/fil.traineddata,s3://<AWS_BUCKET>/tesseract/kan.traineddata,s3://<AWS_BUCKET>/tesseract/guj.traineddata,s3://<AWS_BUCKET>/tesseract/pan.traineddata,s3://<AWS_BUCKET>/tesseract/mal.traineddata,s3://<AWS_BUCKET>/tesseract/mar.traineddata,s3://<AWS_BUCKET>/tesseract/tam.traineddata,s3://<AWS_BUCKET>/tesseract/tel.traineddata,s3://<AWS_BUCKET>/tesseract/sqi.traineddata"
extraInitContainer:
outputPath: "s3://<AWS_BUCKET>/tesseract/"
memory:
enabled: true
onpremValues:
env:
BUCKETNAME: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
notification:
enabled: true
onpremValues:
env:
BUCKETNAME: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
translatev4:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
btcJobBucket: <AWS_BUCKET>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
# Init container to copy neural trained v4 models
init:
enabled: true
outputPath: "s3://<AWS_BUCKET>/trained/"
updatev4:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
btcJobBucket: <AWS_BUCKET>
bucket: <AWS_BUCKET>
wpaDataStoreBasePath: "s3://<AWS_BUCKET>/wpa/"
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
langid:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
update-managerv4:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
routing:
enabled: true
# All messages from other teams' services go through the routing service.
# Increase the number of replicas in environments with high load.
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
batchv4:
enabled: true
onpremValues:
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
batch-worker-gpuv4:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
llm-inference:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
init:
outputPath: "s3://<AWS_BUCKET>/trained/"
automqm:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
alignment:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
init:
outputPath: "s3://<AWS_BUCKET>/trained/"
tag-projection:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>
init:
outputPath: "s3://<AWS_BUCKET>/trained/"
nncache:
enabled: true
onpremValues:
config:
awsSecretAccessKey: ""
awsAccessKeyId: ""
awsRegion: <AWS_REGION>
awsS3EndpointUrl: <AWS_S3_ENDPOINT_URL>
awsS3EndpointUrlSsl: <AWS_S3_ENDPOINT_URL_SSL>
caBundlePath: ""
storageType: <STORAGETYPE>
bucket: <AWS_BUCKET>
serviceAccount:
enabled: true
name: <SERVICE_ACCOUNT>