PRODUCT · PYTHON SDK

AI Privacy Guard

Add a privacy layer before model calls without forcing your startup to adopt a specific AI provider. PrivoNest detects sensitive text, swaps it for scoped aliases, sends the protected prompt to the selected provider, and restores exact aliases in the application response.

Detect → Alias → Selected AI → Restore

The API does the PII detection. Your chosen LLM does the generation/reasoning.

Bring Your Own AI

The v1.0.5 SDK includes adapters for OpenAI, Anthropic/Claude, Google Gemini, Ollama, LangChain and LlamaIndex; integration-test against the exact third-party SDK versions your application uses.

PII Before the Model

The Guard calls the PrivoNest PII API before the model request so raw detected values can be replaced before leaving your application path.

Scoped Alias Restore

Temporary aliases such as [PN_NAME_1] can be restored in short-lived application-side memory after the selected AI responds.

Server-Side Keys

Keep both the PrivoNest API key and model-provider key in your backend environment, not browser JavaScript.

No OpenAI Dependency

OpenAI is one adapter. The customer chooses the AI provider; PrivoNest remains the privacy layer.

Textual Guard Boundary

Automatic provider wrapping remains focused on textual LLM inputs. Supported PDF, DOCX, XLSX, CSV, image, email, DICOM and transcript protection remains available through the PrivoNest REST /v1/hide document workflow.

01 · App prompt

Your backend receives normal text.

02 · Detect

PrivoNest identifies sensitive spans.

03 · Protected call

Your chosen model receives scoped aliases.

04 · Restore

Exact aliases are restored in the application response.