LLM Prompt Redaction

Introduction

In this guide, you'll learn how to use Private AI to perform prompt redaction and re-hydration. The guide is centred around handling personally identifiable data: you'll deidentify user prompts, send them to OpenAI's ChatGPT, and then re-identify the responses. This ensures confidential information remains safe while interacting with AI models. The process looks like this:

Overview of PrivateGPT workflow

In addition to this guide, you might find the following notebooks and code examples useful.

Title	LLM Provider	Format
Safely work with Company Confidential Information with Private AI	OpenAI	Notebook
SEC Filing: Document Summarization and Question Answering	Cohere	Notebook
SEC Filing: Document Summarization and Question Answering	Google	Notebook
Secure Prompting with Private AI	OpenAI, Google or Cohere	Python Script
Secure Prompting with Private AI - Files	OpenAI, Google or Cohere	Python Script

Environment Setup and Configuration

First, we need to pull and run the Private AI Docker container, which is responsible for data deidentification and re-identification. Follow the instructions in the Quickstart Guide to set up your Docker container.

The next step is setting up the rest of your environment. You will need to install necessary Python libraries, import the required modules in your script, and configure your API keys.

Let's install the privateai_client and openai Python libraries using pip (this has been tested with Private AI Client version 1.3.2 and Open AI Client version 0.28.0):

Copy

Copied

pip install privateai_client openai

Now in your Python script, you'll need to initialize the requisite constants and client libraries:

Copy

Copied

from privateai_client import PAIClient, request_objects
import openai
import os

# Initialize the openai client
openai.api_key = os.getenv('OPENAI_KEY')

# initialize the privateai client
PRIVATEAI_SCHEME = 'http'
PRIVATEAI_HOST = 'localhost'
PRIVATEAI_PORT = '8080'
client = PAIClient(PRIVATEAI_SCHEME, PRIVATEAI_HOST, PRIVATEAI_PORT)

Remember to set a local environment variable named OPENAI_KEY with your actual OpenAI API key, and set the PRIVATEAI_SCHEME, PRIVATEAI_HOST, and PRIVATEAI_PORT variables according to where your local Docker container is running.

Creating the Redaction Function

Let's create a function that will redact personal data from user input, and generate entity mappings that will later be used to re-identify the response:

Copy

Copied

def redact_text(text):
    text_request = request_objects.process_text_obj(text=[text])
    return client.process_text(text_request)

Crafting the Reidentification Function

Next, we'll define a function that does the opposite of the redaction function, enabling the re-identification of redacted entities in the text:

Copy

Copied

def reidentify_text(text, entities):
    entity_mappings = list(map(map_entity, entities))
    reid_request = request_objects.reidentify_text_obj(processed_text=[text], entities=entity_mappings)
    reid_text = client.reidentify_text(reid_request)
    return reid_text.response.json()[0]

We don't need all of the data in the response from the redaction service, so let's create a little mapping function to get just what we need:

Copy

Copied

def map_entity(entity):
    return {
        'processed_text': entity['processed_text'],
        'text': entity['text']
    }

Function for Calling OpenAI

We'll also need a function for generating responses from OpenAI's GPT-3.5-turbo chat model. Here's a simple illustration of how to accomplish this:

Copy

Copied

def prompt_chat_gpt(text):
    completion = openai.ChatCompletion.create(
        model = "gpt-3.5-turbo",
        messages = [
            {
                "role": "user",
                "content": text
            }
        ]
    )
    return completion.choices[0].message['content']

Bringing it All Together

We're now ready to put all the components together to form our final solution. This is how we redact a prompt, dispatch it to the GPT model, and reidentify the response:

Copy

Copied

def prompt_private_gpt(prompt):
    print("******* ORIGINAL TEXT *******")
    print(prompt)

    redacted_object = redact_text(prompt)
    print("\n******* REDACTED TEXT **********")
    print(redacted_object.processed_text)

    chatgpt_response = prompt_chat_gpt(redacted_object.processed_text[0])
    print("\n******* OPEN AI RESPONSE WITH REDACTIONS ********")
    print(chatgpt_response)

    reidentified_text = reidentify_text(chatgpt_response, redacted_object.entities[0])
    print("\n******* OPEN AI RESPONSE REIDENTIFIED ********")
    print(reidentified_text)

    return reidentified_text

Done

There you have it - enjoy chatting while preserving your privacy!

Copy

Copied

openai_response = prompt_private_gpt("Hey! Im Joe, a developer at Private AI!")

The entire code is below for you to copy-paste 😉

Copy

Copied

from privateai_client import PAIClient, request_objects
import openai
import os

# Initialize the openai client
openai.api_key = os.getenv('OPENAI_KEY')

# initialize the privateai client
PRIVATEAI_SCHEME = 'http'
PRIVATEAI_HOST = 'localhost'
PRIVATEAI_PORT = '8080'
client = PAIClient(PRIVATEAI_SCHEME, PRIVATEAI_HOST, PRIVATEAI_PORT)

def redact_text(text):
    text_request = request_objects.process_text_obj(text=[text])
    return client.process_text(text_request)


def reidentify_text(text, entities):
    entity_mappings = list(map(map_entity, entities))
    reid_request = request_objects.reidentify_text_obj(processed_text=[text], entities=entity_mappings)
    reid_text = client.reidentify_text(reid_request)
    return reid_text.response.json()[0]


def map_entity(entity):
    return {
        'processed_text': entity['processed_text'],
        'text': entity['text']
    }


def prompt_chat_gpt(text):
    completion = openai.ChatCompletion.create(
        model = "gpt-3.5-turbo",
        messages = [
            {
                "role": "user",
                "content": text
            }
        ]
    )
    return completion.choices[0].message['content']


def prompt_private_gpt(prompt):
    print("******* ORIGINAL TEXT *******")
    print(prompt)

    redacted_object = redact_text(prompt)
    print("\n******* REDACTED TEXT **********")
    print(redacted_object.processed_text)

    chatgpt_response = prompt_chat_gpt(redacted_object.processed_text[0])
    print("\n******* OPEN AI RESPONSE WITH REDACTIONS ********")
    print(chatgpt_response)

    reidentified_text = reidentify_text(chatgpt_response, redacted_object.entities[0])
    print("\n******* OPEN AI RESPONSE REIDENTIFIED ********")
    print(reidentified_text)

    return reidentified_text


openai_response = prompt_private_gpt("Hey! Im Joe, a developer at Private AI!")