Athina home page
Search...
⌘K
Ask AI
AI Hub
Website
Sign-up
Sign-up
Search...
Navigation
Safety
PII Detection
Docs
API / SDK Reference
Guides
FAQs
Documentation
Open-Source Evals
Blog
Email us
Book a call
Logging
Overview
POST
Logging Attributes
Logging LLM Inferences
Updating Logs
Datasets
List All Datasets
Create a Dataset
Add Rows to Dataset
Get Dataset
Delete Dataset
Update Cells in a Dataset
Evals
Running Evals via SDK
Loading Data for Evals
Preset Evals
Overview
RAG Evals
Safety
PII Detection
Prompt Injection
OpenAI Content Moderation
Guardrails
JSON Evals
Summarization QA
Function Evals
Grounded Evals
Conversation Evaluators
Custom Evals
GraphQL API
Overview
Getting Started
Sample GraphQL Queries
Curl and Python Examples
Deprecated
OpenAI Completion 0.x
OpenAI Completion 1.x
On this page
Example
How does it work?
Notes
Safety
PII Detection
Fails if the text contains Personal Identifiable Information (PII).
Inputs:
text
Type:
boolean
Metrics:
passed
(0 or 1)
Example
With PII
Query
:
“Sam Altman’s Ethereum address is 0x2390jd24jJD3m29kd20kd02k30rk02.”
Result
:
Failed
Without PII
Query
:
“What is the capital of France?”
Result
:
Passed
How does it work?
This evaluator uses an open-source
Hugging Face library
to detect PII in the text.
The model is a fine-tuned version of Microsoft’s Deberta V3.
Notes
The model is not perfect and might not detect all PII.
You can use Athina as real time guardrails, but the PII detection eval can take a few seconds to complete, so it is not recommended for chat apps. (
Example Notebook
)
RAGAS
Prompt Injection
Assistant
Responses are generated using AI and may contain mistakes.