Feature × Audience

How should enterprise architects design RAG on Plugsky?

RAG for enterprise architects is a topology decision: which corpora, which data plane, which retrieval mode and which model serves the answer. Plugsky provides managed collections with keyword, vector and hybrid retrieval plus optional reranking, returns chunks with source attribution, and runs hosted, in your VPC, on-prem or air-gapped — with access to 30+ models and per-collection encryption at rest.

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

  • Treat each corpus as a product with an owner, freshness target and access rule.
  • One OpenAI-compatible plane covers ingestion, retrieval and generation.
  • Route cheap classification to small models and pin stronger models for sensitive answers.
  • Choose the data plane per corpus: region-locked, VPC, on-prem or air-gapped.
  • Keep the embedding interface stable so vector stores remain swappable.

How it works, step by step

  1. Inventory corpora, owners, refresh cadence and sensitivity classification.
  2. Map each corpus to an allowed deployment plane and a collection boundary.
  3. Decide retrieval mode per corpus: keyword, vector or hybrid with reranking.
  4. Define model routing rules: default, escalation and pinned versions for regulated answers.
  5. Specify key custody, audit fields, retention and SIEM export with security.
  6. Prove retrieval quality on one corpus with a shared evaluation set.
  7. Standardise an ingestion contract and open the service to further teams.
1Inventory corpora,owners, refreshcadence and2Map each corpus toan alloweddeployment plane3Decide retrievalmode per corpus:keyword, vector or4Define modelrouting rules:default, escalation5Specify keycustody, auditfields, retention6Prove retrievalquality on onecorpus with a

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 RAG architecture builder →

Why enterprise architects need RAG grounded in their own content

Architects are asked to place RAG on a diagram and defend it. Four questions decide the shape: where each corpus lives and who owns it, whether retrieval quality needs vector or hybrid search, which data plane is allowed for each corpus, and which model is permitted to answer. Get those wrong and every later change is a migration.

Treat corpora as products with owners, refresh cadences and access rules. A collection per bounded domain — HR policy, product documentation, regulatory notices — keeps retrieval precise, permissions clean and evaluation practical.

The Plugsky RAG stack: embeddings, collections, queries

The retrieval pipeline is three calls: embed, collect, query. POST /v1/embeddings converts text to vectors using plugsky-embed-v1 (1536 dimensions, OpenAI-ada compatible) or plugsky-embed-large (3072 dimensions); POST /v1/rag/collections stores and indexes documents with per-collection encryption at rest; POST /v1/rag/query returns ranked chunks with source attribution. Keyword, vector and hybrid retrieval are all available, with optional cross-encoder reranking when precision matters more than raw recall. For architects the decision is which layer to own: managed collections shorten delivery, while standalone embeddings let you keep an existing vector store without changing the model interface.

The controls enterprise architects should configure first

A defensible reference topology puts ingestion, retrieval and generation in one OpenAI-compatible plane: documents are chunked and embedded into collections, queries return ranked chunks with citations, and any chat model composes the answer. Model routing across 30+ models lets you send cheap classification to a small model and sensitive answers to a pinned, stronger one.

Residency, keys and audit complete the picture: region-locked planes, VPC, on-prem or air-gapped deployment; BYOK via AWS KMS, Azure Key Vault, HashiCorp Vault or an on-prem HSM; per-request logs with SIEM export and retention up to 7 years. Review model versions at the same cadence as your other dependencies.

A practical pilot path

Phase the rollout: prove retrieval on one corpus, then standardise the ingestion contract, then open the service to more teams through scoped keys and quotas. Keep the embeddings interface stable even if you change vector stores later, and hold the evaluation set as a shared asset so changes are measured, not argued. Prototype on the free plan and use the 14-day full-access trial for a wider evaluation. 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

How many collections should we create?

One per bounded domain with a clear owner. Separate collections keep retrieval precise, make per-collection encryption and access rules meaningful, and let teams evaluate independently.

How does model routing fit a RAG design?

Retrieval returns chunks independent of the model; routing decides which model composes the answer, so you can send routine work to efficient models and pin stronger models where answers need 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.