.Net: Example of prompt PII detection logic with Filters and Microsoft Presidio #6171
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
markwallace-microsoft
added
.NET
6 tasks
westey-m
approved these changes
May 9, 2024
SergeyMenshykh
approved these changes
May 9, 2024
markwallace-microsoft
approved these changes
May 10, 2024
LudoCorporateShark
pushed a commit
to LudoCorporateShark/semantic-kernel
that referenced
this pull request
Aug 25, 2024
…t Presidio (microsoft#6171) ### Motivation and Context <!-- Thank you for your contribution to the semantic-kernel repo! Please help reviewers and future users, providing the following information: 1. Why is this change required? 2. What problem does it solve? 3. What scenario does it contribute to? 4. If it fixes an open issue, please link to the issue here. --> This example shows how to implement Personal Identifiable Information (PII) detection logic with Filters using Microsoft Presidio service: https://github.com/microsoft/presidio. Example contains two filters: First filter is responsible for PII detection in prompt by using Presidio Text Analyzer. If PII is detected, then the prompt won't be sent to LLM and custom result will be returned after function invocation. Example output: ``` Prompt: John Smith has a card 1111 2222 3333 4444 Entity type: CREDIT_CARD. Score: 1 Entity type: PERSON. Score: 0.85 Exception: Prompt contains PII information. Operation is canceled. ``` Second filter is responsible for PII detection in prompt and updating the prompt by following specified rules before sending it to LLM. This filter uses Presidio Text Analyzer and Presidio Text Anonymizer. Example output: ``` LLM instructions: If prompt does not contain first and last name - return 'true'. Prompt before anonymization : Hello world, my name is Jane Doe. My number is: 034453334 Prompt after anonymization : Hello world, my name is ANONYMIZED. My number is: Result: true ``` ### Contribution Checklist <!-- Before submitting this PR, please make sure: --> - [x] The code builds clean without any errors or warnings - [x] The PR follows the [SK Contribution Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md) and the [pre-submission formatting script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts) raises no violations - [x] All unit tests pass, and I have added new tests where possible - [x] I didn't break anyone 😄
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation and Context
This example shows how to implement Personal Identifiable Information (PII) detection logic with Filters using Microsoft Presidio service: https://github.com/microsoft/presidio.
Example contains two filters:
First filter is responsible for PII detection in prompt by using Presidio Text Analyzer. If PII is detected, then the prompt won't be sent to LLM and custom result will be returned after function invocation.
Example output:
Second filter is responsible for PII detection in prompt and updating the prompt by following specified rules before sending it to LLM. This filter uses Presidio Text Analyzer and Presidio Text Anonymizer.
Example output:
Contribution Checklist