QQIOI
deploy

package qioi show deepfryr

package metadata● managed

DeepFryr

Private RAG with citations and provenance.

package:deepfryr

category:knowledge & rag

version:pinned · channels: stable

min resources:8 gb ram

backups:daily

regions:canada (central) · us east

domain:qioi.app subdomain + custom domain · ssl included

model costs:external model api usage billed by your provider, not qioi

deployment:automated deployment — includes vector store provisioning

from:$89/mo

description

The trusted-knowledge engine from the QIOI ecosystem. DeepFryr ingests difficult source material — manuals, regulations, permits, internal documents — and answers with citations, confidence levels, and source provenance. Deployed and operated by QIOI.

technical documentation teamsregulated industriesinternal knowledge assistants

scope — where qioi's responsibility ends

+ managed by qioi

  • +Dedicated server resources on a tested plan
  • +Automated application deployment from a pinned template
  • +SSL certificate and qioi.app subdomain
  • +Health monitoring with automatic restarts
  • +Scheduled encrypted backups
  • +Managed upgrade path with rollback support
  • +QIOI dashboard: logs, metrics, backups, domains
  • +Vector storage (Qdrant) provisioned and managed
  • +Source-backed answers with citation tracking
  • +Confidence scoring and conflict detection

- not included

  • -Third-party model API usage (billed by your model provider)
  • -Custom application or workflow development
  • -Data preparation beyond package limits
  • -Unlimited technical consulting
  • -Document cleanup or manual ingestion beyond package limits

depends — recommended plans

planvcpuramstorageprice
M48 gb160 gb$69/mo
L816 gb320 gb$119/mo
XL1632 gb640 gb$219/mo

prices include hosting + management · model api usage billed separately by your provider

notes

q: how are answers sourced?

Every answer links back to the ingested source documents with version tracking. Low-confidence answers are flagged for human review rather than presented as fact.

q: what formats can deepfryr ingest?

PDFs, Office documents, HTML, plain text, and structured data. Large or unusual corpora can be scoped as an onboarding service.

$ cd ../catalog