Innovation & Tech

Perplexity's New Guide Makes the Case for Handing RAG to Outside Providers

Perplexity's November 19, 2026 guide lays out RAG as a service: three deployment models, a build-versus-buy test, and a seven-vendor list including AWS, OpenAI, Azure, Pinecone and Vectara.

By Amara Osei

4 min read

Perplexity Publishes Guide to Managed RAG for Enterprise AI
Perplexity Publishes Guide to Managed RAG for Enterprise AIgregroose / pixabay

What's News

  • Perplexity published its managed RAG guide on November 19, 2026.
  • The guide names seven providers: Perplexity, AWS, OpenAI, Microsoft Azure, Pinecone, LlamaIndex and Vectara.
  • Perplexity says more than 50,000 organizations trust Perplexity Enterprise, and Computer draws on 20 advanced models.
  • Listed enterprise controls include SOC 2 Type II certification, SSO, SCIM and audit logs.
  • The guide says self-hosting may avoid token and storage charges, but hardware and maintenance can offset those savings.

Perplexity published a guide on November 19, 2026, laying out how companies can outsource retrieval-augmented generation — the machinery that lets enterprise AI systems reach information beyond a model's training data — through a managed service it calls RAG as a service, or RaaS.

The term covers arrangements where outside providers handle most or all RAG components. Responsibility for vector databases, embedding models and retrievers shifts to the provider, which can also run ingestion, storage, security and ongoing optimization. Depending on the package, the vendor supplies the language model and user interface, or connects its retrieval service to the customer's existing AI system.

How does managed retrieval actually work?

The guide frames the choice with three deployment models. Local RAG puts ingestion, retrieval and storage on the user's own servers, potentially alongside locally run embedding and language models. A self-built cloud system uses APIs to reach hosted databases and third-party models, but internal administrators manage the connections and orchestration. With RaaS, the provider manages all or most of the system, and the enterprise supplies access to its database or cloud storage.

In the guide's knowledge-management example, the provider receives knowledge-base access through an API. After cleaning the text, it turns passages into vector embeddings and places them in a vector database on its own servers. The provider adds newly available documentation and connects its retriever API to the customer's orchestrator — the software that coordinates user inputs and sends augmented prompts to the language model.

When a user queries the company chatbot, the orchestrator passes the query text to the vendor, which embeds it and searches the database. The orchestrator adds the returned information to the input context and sends it to the language model, whose answer is delivered through the chatbot. Supplying information absent from training parameters improves the accuracy and completeness of generated outputs, the guide says.

Where do enterprises deploy it?

The principal applications the guide identifies:

  • Internal knowledge management, searching documentation in services such as Google Drive, SharePoint and Confluence
  • Customer support
  • Sales assistance, drawing on support tickets, competitor research and call recordings
  • Customer-data access for subscription management, returns and changes to personal details
  • Customer-facing product chatbots connected to backend databases for discovery and technical questions

Perplexity lists faster deployment, reduced maintenance, scalability, automatic content synchronization and enterprise-platform integration as advantages of managed RAG, while noting that service and package-tier limits still apply.

What does the build-versus-buy math look like?

The framework centers on cost, scale and complexity. Self-hosting suits clearly bounded usage and may avoid token and storage charges when every component runs on internal servers — though hardware and maintenance can offset those savings, the guide warns.

Advanced architectures can add multimodal and hybrid retrieval, along with reranking, and the guide says specialized vendors typically offer the most economical access to that expertise. Because most RAG systems already rely on some vendor services, the real decision is how much of the overall system a provider will build and manage.

Who are the providers?

The guide splits the market into general AI platforms with built-in RAG — ready-to-use products with integrations — and managed backend infrastructure vendors for tailored setups. Its seven-provider editorial selection comprises Perplexity, AWS, OpenAI, Microsoft Azure, Pinecone, LlamaIndex and Vectara.

Perplexity Enterprise appears in that selection as a suite of agentic tools with internal and project-level knowledge bases, web search, access to multiple generative models, a proprietary embedding model, external-data integrations, security and employee permissions.

On its separate Enterprise page, Perplexity says more than 50,000 organizations trust Perplexity Enterprise, and describes Computer as drawing on 20 advanced models, with the broader platform connecting company files and tools for internal knowledge, research and complex projects. The same page states that Perplexity does not train its large language models on enterprise customer data. Listed controls include SOC 2 Type II certification, configurable file retention, user management, SSO and SCIM, and audit logs for tracking user activity.

Is outsourcing all-or-nothing?

No. Companies can build straightforward systems themselves and use a provider for advanced applications. The practical consequence, per the guide: outsourcing need not be enterprise-wide — each deployment can place a different share of retrieval complexity, expense and maintenance with the provider, while the enterprise retains responsibility for whatever it keeps internal. That granularity gives buyers a middle path between full self-hosting and full delegation.

Source: unite.ai

Share this article:

More from Amara Osei

Amara Osei

Show full bio

Senior reporter covering companies, deals and strategy in entrepreneurship, startups and venture funding at Business Bearings.

2,370 articles

Related articles

« Previous article