Kubernetes Pod Resources

Component	Instances	CPU req	CPU limit	RAM req (GB)	RAM limit (GB)
Automate	2	-	-	-	-
admin	2	2	4	6	6
dialogs	2	2	4	12	12
nlu-pipeline	2	1	2	2	2
nlu-facade	2	1	2	5	5
gateway	2	2	4	2	2
analytics	2	1	2	2	2
cron-orchestrator	2	1	2	2	2
web-chat	2	1	2	2	2
storage	1	1	2	2	2
sso-server	2	1	2	2	2
channels-connector	2	1	2	2	2
thread-coordinator	2	1	2	2	2
bot-integration	2	1	2	2	2
refinery	2	1	2	8	8
uploader	2	1	2	2	2

Listen&React*	2
new-web	2	1	2	4	4
analyser	2	1	2	7	7
html-converter	2	0.2	2	8	8
redis (single)	2	0.2	2	2	2
hooks-server	2	1	2	2	2

Infrastructure	2	-	-	-	-
ElasticSearch*	3	1	2	16	16
RabbitMQ*	3	1	2	6	6
PostgreSQL*	3	1	2	6	6
Kubernetes - master node	3	4	4	8	8
NFS	3	1	2	2	2
Redis AI	1	12	24	24	24

Voice systems*	2	-	-	-	-
Voice Gateway	2	16	16	32	32

NLU	2	-	-	-	-
duckling	2	2	2	1	1
inferrer	2	1	2	1	1
intentizer-multi	2	2	2	0.1	0.1
intentizer-fitter	2	2	16	16	16
intentizer-llm	2	0.1	2	1	1
keywords	2	1	2	0.25	0.25
name-service	2	0.5	1	0.25	0.25
ner-pl	2	4	8	2	2
pattern	2	2	2	2	2
pcre	2	1	2	0.2	0.2
sentiduck	2	2	4	1	1
tokenizer-pl	2	2	4	2	2
tagger-de	2	1	2	2	2
tagger-en	2	1	2	2	2
tagger-multi	2	1	2	2	2
ner-multi	2	2	6	6	6
nlu-data-migrator	1	1	1	6	6

Resources summary

Component	Instances	CPU req	CPU limit	RAM req (GB)	RAM limit (GB)
Automate	2	36	72	106	106
Listen&React*	2	6.8	20	46	46
Infrastructure	3	36	60	138	138
Voice systems*	2	32	32	64	64
NLU	2	59.2	142	86.7	86.7
	TOTAL	170	326	440.7	440.7

Recommended VM configuration

	qty.	NVMe [GB]	vCPU	RAM [GB]
Kubernetes Master	3	75	4	8
Kubernetes Worker	5	200	40	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 simple models. If more active NLU models are needed please calculate 0.8GB per 1 NLU simple model. If complex models are used, calculate 4GB per 1 model - more information about complex models in Comparison of available intentizer types