Kubernetes Pod Resources

Up to 50 concurrent conversations, no HA - suitable for testing environments

Component	Instances	CPU req	CPU limit	RAM req (GB)	RAM limit (GB)
Automate	1	-	-	-	-
admin	1	0.5	2	2	2
dialogs	1	0.5	2	6	6
nlu-pipeline	1	1	1	2	2
nlu-facade	1	1	1	2	2
gateway	1	0.5	2	2	2
analytics	1	1	2	2	2
cron-orchestrator	1	0.2	1	2	2
web-chat	1	1	2	2	2
sso-server*	1	0.2	1	2	2
channels-connector*	1	0.2	1	2	2
thread-coordinator*	1	0.2	1	2	2
bot-integration	1	0.2	1	2	2
refinery	1	0.2	1	8	8
uploader	1	0.2	1	2	2

Listen&React*	1
new-web	1	0.2	1	4	4
analyser	1	0.2	1	7	7

Infrastructure	1	-	-	-	-
ElasticSearch	1	0.2	1	8	8
RabbitMQ	1	0.2	1	6	6
PostgreSQL	1	0.2	1	4	4
Kubernetes - master node	1	0.2	1	4	4
NFS	1	0.2	1	2	2
Redis AI	1	6	12	20	20

Voice systems*	1	-	-	-	-
Voice Gateway	1	6	6	96	96

NLU	1	-	-	-	-
duckling	1	2	2	1	1
inferrer	1	0.1	2	1	1
intentizer-multi	1	0.2	1	0.1	0.1
intentizer-multi-fitter	1	2	16	16	16
keywords	1	0.2	1	0.25	0.25
name-service	1	0.1	1	0.25	0.25
ner-pl	1	2	4	2	2
pattern	1	0.1	2	1	1
pcre	1	0.2	1	0.25	0.25
sentiduck	1	1	2	1	1
tokenizer-pl	1	1	2	2	2
tagger-de	1	1	1	1	1
tagger-en	1	1	1	1	1
tagger-multi	1	1	1	1	1
ner-multi	1	1	2	6	6

Resources summary

Component	Instances	CPU req	CPU limit	RAM req (GB)	RAM limit (GB)
Automate	1	6.9	19	38	38
Listen&React*	1	0.4	2	11	11
Infrastructure	1	7	17	36	36
Voice systems*	1	6	6	96	96
NLU	1	12.9	39	33.85	33.85
	TOTAL	33.2	83	214.85	214.85

	qty.	HDD [GB]	vCPU	RAM [GB]
Kubernetes Master	1	75	1	4
Kubernetes Worker	2	100	20	64
Voice Gateway*	1	50	6	96

* - Optional applications

⚠️ When planning deployment please take into account requirements described in Deployment Assumptions and contact us for further details.

ℹ️ RedisAI assumes 35 active NLU models. If more active NLU models are needed please calculate 0.8GB per 1 NLU model.