Route Mode

Route mode sends requests containing PII to a local LLM. Requests without PII go to OpenAI or Anthropic.

How It Works

Request with PII

Routed to Local LLM (Ollama, vLLM, llama.cpp, etc.)PII stays on your network.

Request without PII

Routed to OpenAI or AnthropicFull performance.

When to Use

Have local GPU resources
Need complete data isolation for sensitive requests
Must prevent any PII from leaving your network

Configuration

mode: route

providers:
  openai:
    base_url: https://api.openai.com/v1

local:
  type: ollama
  base_url: http://localhost:11434
  model: llama3.2

In route mode:

No PII detected → Request goes to OpenAI or Anthropic
PII detected → Request goes to local LLM

For Anthropic requests, the local LLM must support the Anthropic Messages API (e.g., Ollama with Anthropic API compatibility).

Local LLM Setup

Ollama

local:
  type: ollama
  base_url: http://localhost:11434
  model: llama3.2

vLLM

local:
  type: openai
  base_url: http://localhost:8000/v1
  model: meta-llama/Llama-2-7b-chat-hf

llama.cpp

local:
  type: openai
  base_url: http://localhost:8080/v1
  model: local

LocalAI

local:
  type: openai
  base_url: http://localhost:8080/v1
  model: your-model-name
  api_key: ${LOCAL_API_KEY}  # if required

Response Headers

Route mode sets these headers on responses: When a request is routed to local:

X-PasteGuard-Mode: route
X-PasteGuard-Provider: local
X-PasteGuard-PII-Detected: true

When routed to OpenAI or Anthropic:

X-PasteGuard-Mode: route
X-PasteGuard-Provider: openai
X-PasteGuard-PII-Detected: false

Getting Started

Use Cases

Concepts

API Reference

Configuration

How It Works

Request with PII

Request without PII

When to Use

Configuration

Local LLM Setup

Ollama

vLLM

llama.cpp

LocalAI

Response Headers

​How It Works

Request with PII

Request without PII

​When to Use

​Configuration

​Local LLM Setup

​Ollama

​vLLM

​llama.cpp

​LocalAI

​Response Headers

How It Works

When to Use

Configuration

Local LLM Setup

Ollama

vLLM

llama.cpp

LocalAI

Response Headers