Key facts
| RAG endpoints | POST /v1/embeddings, POST /v1/rag/collections and POST /v1/rag/query |
| Embedding models | plugsky-embed-v1 (1536 dimensions, OpenAI-ada compatible) and plugsky-embed-large (3072 dimensions) |
| Retrieval modes | Keyword, vector and hybrid search with optional cross-encoder reranking |
| Citations | Every query returns ranked chunks with source attribution |
| Ingestion | Documents are chunked, embedded and indexed automatically per collection |
| Batch limits | Up to 2,048 inputs per embeddings request, max 8,191 tokens each |
| Data handling | Per-collection encryption at rest; API data is not used to train models |
| Deployment | Hosted, VPC, on-prem and air-gapped options; 30+ models behind one API |
TL;DR
- Turn runbooks, care scripts and catalogues into citable answers.
- Separate procedural knowledge from subscriber-adjacent records by collection.
- Region-locked, VPC, on-prem and air-gapped planes match corpus classification.
- Audit export to Splunk, Sentinel, QRadar or Datadog with retention up to 7 years.
- Pilot with NOC runbooks and measure time-to-answer, not demo quality.
How it works, step by step
- Choose a first corpus: NOC runbooks, escalation matrices or care scripts.
- Separate collections by data classification and audience.
- Ingest documents and verify chunking preserves steps, tables and references.
- Define acceptance metrics: time-to-answer and citation accuracy versus current search.
- Configure BYOK, RBAC/SSO, audit export and retention with security and compliance.
- Run the pilot inside one team and collect feedback before scaling.
- Move to VPC, on-prem or air-gapped deployment for subscriber-adjacent workloads.
Original data
Try it yourself
Open the vector database comparison →
Why telcos need RAG grounded in their own content
Telcos have an unusual amount of procedural knowledge: network runbooks, escalation matrices, product catalogues, tariff rules, care scripts and regulatory guidance. Care agents and field engineers lose time searching it, and new staff take months to learn it. Retrieval over that corpus pays back quickly, especially when answers carry citations.
Subscriber data changes the calculus. Keep care knowledge and subscriber-adjacent records in separate collections with separate access, and choose a deployment plane that matches the classification of each corpus rather than applying one setting to everything.
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 telcos the retrieval layer runs region-locked, on-prem or air-gapped, so runbooks and care knowledge stay inside the operator perimeter while the API stays familiar.
The controls telcos should configure first
Operator review focuses on residency, keys and attribution. Region-locked planes keep processing in a published geography; VPC, on-prem and air-gapped deployments cover workloads that cannot leave the operator's perimeter. BYOK through AWS KMS, Azure Key Vault, HashiCorp Vault or an on-prem HSM keeps encryption keys with the operator.
Per-request audit logs record model, tokens, latency, user and region and export to Splunk, Sentinel, QRadar or Datadog with retention up to 7 years. RBAC with workspace, role and resource-level permissions plus SAML/OIDC SSO and SCIM govern who can query what. Compliance evidence covers SOC 2 Type II under NDA, ISO 27001/27017/27018 and HIPAA with a BAA; FedRAMP Moderate is in process.
A practical pilot path
Pilot on network runbooks for NOC staff or care scripts for a single product line, and measure time-to-answer and citation accuracy against the current search tool. Prototype on the free plan with plugsky-micro and plugsky-lite, then move the workload to the required data plane before real subscriber context is involved. See the live pricing page for current plans.
Honest comparison
| Capability | Plugsky | Assembling your own stack | Keyword search only |
|---|---|---|---|
| Retrieval | Keyword, vector and hybrid with optional reranking | You integrate and tune each component | Keyword matching, no semantics |
| Citations | Ranked chunks with source attribution | You build attribution yourself | Document links, not passages |
| Embeddings | plugsky-embed-v1 (1536d) and plugsky-embed-large (3072d) | Model choice spread across vendors | Not applicable |
| Deployment | Hosted, VPC, on-prem and air-gapped | Depends on every component | Usually on-prem already |
| Data handling | Per-collection encryption; API data not used to train models | You audit every vendor | Existing controls apply |
| Time to first answer | One collection and a query call | Weeks of integration work | Days, with lower answer quality |
Frequently asked questions
Can NOC knowledge stay on-premises?
Yes. On-prem and fully air-gapped deployments run the same OpenAI-compatible API with a local model registry and offline update channels, so runbooks never leave the operator perimeter.
How does this fit our existing search tools?
Retrieval returns chunks with citations that you can route through your own UI or gateway; the API is OpenAI-compatible, so integration is an endpoint call rather than a platform replacement.
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.