Feature × Audience

How does government build RAG with Plugsky's architecture?

RAG for government grounds answers in policy, legislation and case files while keeping sensitive content inside a controlled or air-gapped environment. Plugsky runs embeddings, collections and queries as OpenAI-compatible endpoints, returns citations for review, and supports region-locked, VPC, on-prem and air-gapped deployment with BYOK key custody and per-request audit logs exported to your SIEM.

Key facts

RAG endpointsPOST /v1/embeddings, POST /v1/rag/collections and POST /v1/rag/query
Embedding modelsplugsky-embed-v1 (1536 dimensions, OpenAI-ada compatible) and plugsky-embed-large (3072 dimensions)
Retrieval modesKeyword, vector and hybrid search with optional cross-encoder reranking
CitationsEvery query returns ranked chunks with source attribution
IngestionDocuments are chunked, embedded and indexed automatically per collection
Batch limitsUp to 2,048 inputs per embeddings request, max 8,191 tokens each
Data handlingPer-collection encryption at rest; API data is not used to train models
DeploymentHosted, VPC, on-prem and air-gapped options; 30+ models behind one API

TL;DR

  • Citations make every answer traceable to an authoritative source.
  • Air-gapped deployment removes internet egress for classified programmes.
  • BYOK and SIEM export support records and audit obligations.
  • Pilot on unclassified corpora, then move to the required data plane.
  • Keep human review for citizen-facing output.

How it works, step by step

  1. Classify corpora by sensitivity and decide which deployment plane each one allows.
  2. Choose a first pilot corpus with high re-use and low classification risk.
  3. Create collections and ingest documents; verify chunking preserves structure and references.
  4. Define acceptance in retrieval terms: correct source retrieved and cited on every answer.
  5. Configure BYOK, audit fields, SIEM export and retention with your security team.
  6. Review output with subject-matter experts before any citizen-facing use.
  7. Move to air-gapped or on-prem deployment as classification requires.
1Classify corpora bysensitivity anddecide which2Choose a firstpilot corpus withhigh re-use and low3Create collectionsand ingestdocuments; verify4Define acceptancein retrieval terms:correct source5Configure BYOK,audit fields, SIEMexport and6Review output withsubject-matterexperts before any

Original data

POST /v1/embedRAG endpointsplugsky-embed-Embedding modelsUp to 2,048 inBatch limitsHosted, VPC, oDeploymentSource: Plugsky facts table · updated 2026-09-26

Try it yourself

Open the local RAG stack generator →

Why government need RAG grounded in their own content

Public-sector knowledge work is document-heavy and accountability-heavy: legislation, circulars, procedures, case files and correspondence. Staff need fast answers, but the answer must be traceable to an authoritative source and the processing must satisfy records, privacy and classification rules. A citation-first RAG service fits both requirements: it retrieves from approved corpora and shows where every statement came from.

Start by separating corpora that can be hosted from those that cannot. An air-gapped deployment removes internet egress entirely, with a local model registry and offline update channels for the most sensitive programmes.

The Plugsky RAG stack: embeddings, collections, queries

You do not have to assemble a vector database, an embedder, a retriever and a reranker separately. Documents are chunked, embedded and indexed automatically per collection, retrieval supports keyword, vector and hybrid modes, and every query returns ranked chunks with citations. The endpoints stay OpenAI-compatible — POST /v1/embeddings, POST /v1/rag/collections, POST /v1/rag/query — and the embeddings call also works standalone if you keep your own vector store. For government programmes the endpoint contract stays constant across cloud, VPC, on-prem and air-gapped deployments, which keeps application code stable when the data plane changes.

The controls government should configure first

Sovereignty is delivered through deployment, not promises. Plugsky supports region-locked data planes, private VPC endpoints, on-prem and fully air-gapped installations, so the processing location matches the classification of each corpus. Keys stay under your control with BYOK through AWS KMS, Azure Key Vault, HashiCorp Vault or an on-prem HSM.

Audit logs record model, tokens, latency, user and region per request and export to your SIEM with retention up to 7 years, which supports records-management policy and freedom-of-information workflows. Compliance evidence includes SOC 2 Type II under NDA, ISO 27001/27017/27018, HIPAA with a BAA and GDPR/EU SCC coverage; FedRAMP Moderate is in process, so treat it as pending for US federal work.

A practical pilot path

Run the first pilot on an unclassified corpus with high re-use value, such as internal procedure manuals, and define acceptance in retrieval terms: correct source in the top results and a citation on every answer. Keep humans in the loop for anything citizen-facing. Prototype on the free plan, then move to the required deployment plane before real data is loaded. See the live pricing page for current plans.

Honest comparison

CapabilityPlugskyAssembling your own stackKeyword search only
RetrievalKeyword, vector and hybrid with optional rerankingYou integrate and tune each componentKeyword matching, no semantics
CitationsRanked chunks with source attributionYou build attribution yourselfDocument links, not passages
Embeddingsplugsky-embed-v1 (1536d) and plugsky-embed-large (3072d)Model choice spread across vendorsNot applicable
DeploymentHosted, VPC, on-prem and air-gappedDepends on every componentUsually on-prem already
Data handlingPer-collection encryption; API data not used to train modelsYou audit every vendorExisting controls apply
Time to first answerOne collection and a query callWeeks of integration workDays, with lower answer quality

Frequently asked questions

Can RAG run air-gapped?

Yes. Air-gapped deployments run with no internet egress, a local model registry and offline update channels, which suits defence, government and critical-infrastructure programmes.

How do we keep answers accountable?

Every query returns ranked chunks with source attribution, and per-request audit logs tie each answer to a user, model, time and region for later review.

Do we have to change our application code?

No. The RAG endpoints are OpenAI-compatible, so existing SDKs, prompts and evaluation harnesses keep working when you point the base URL at Plugsky.

Is there a free plan?

Yes — plugsky-micro and plugsky-lite with 2 API keys and no credit card. A 14-day full-access trial is also available.

How is pricing structured?

Self-serve plans are flat monthly with unlimited fair-use usage and no per-token charges or overage fees. See the live pricing page for current plans.

Does Plugsky train on our data?

Plugsky states that API data is not used to train models, and collections are encrypted at rest; on Enterprise you can keep everything inside your own VPC.