Upload 4 files

app.py

@@ -0,0 +1,131 @@
+# Necessary imports
+import warnings
+
+warnings.filterwarnings("ignore")
+
+import gradio as gr
+from ner import pii_ner
+
+
+# Examples to display in the interface
+examples = [
+    [
+        "Hi support, I can't log in! My account username is 'johndoe88'. Every time I try, it says 'invalid credentials'. Please reset my password. You can reach me at (555) 123-4567 or johnd@example.com",
+        "email, phone_number, user_name",
+        0.3,
+        False,
+        False,
+    ],
+    [
+        "Patient John Doe, MRN 123456, diagnosed with diabetes.",
+        "name, medical record number, condition",
+        0.3,
+        False,
+        False,
+    ],
+    [
+        "Client Jane Doe vs. Corporation ABC, case #2024-CV-001",
+        "name, organization, case number",
+        0.3,
+        False,
+        False,
+    ],
+]
+
+
+# Launch the gradio UI
+with gr.Blocks(title="GLiNER-PII", theme=gr.themes.Soft()) as demo:
+    gr.Markdown(
+        """
+        # GLiNER-PII
+        GLiNER-PII is a successor to the Gretel GLiNER PII/PHI models. Built on the GLiNER bi-large base, it detects and classifies a broad range of Personally Identifiable Information (PII) and Protected Health Information (PHI) in structured and unstructured text. It is non-generative and produces span-level entity annotations with confidence scores across 55+ categories. This model was developed by NVIDIA.
+        
+        ## Links
+        * Model: https://huggingface.co/nvidia/gliner-pii
+        * Training dataset: https://huggingface.co/datasets/nvidia/nemotron-pii
+        * GLiNER library: https://pypi.org/project/gliner/
+        """
+    )
+
+    # Text input
+    input_text = gr.Textbox(
+        value=examples[0][0], label="Text input", placeholder="Enter your text here"
+    )
+
+    # Labels, threshold, nested NER
+    with gr.Row() as row:
+        labels = gr.Textbox(
+            value=examples[0][1],
+            label="Labels",
+            placeholder="Enter your PII/PHI labels here (comma separated)",
+            scale=2,
+        )
+        threshold = gr.Slider(
+            0,
+            1,
+            value=0.5,
+            step=0.01,
+            label="Threshold",
+            info="Lower the threshold to increase how many entities get predicted.",
+            scale=1,
+        )
+        nested_ner = gr.Checkbox(
+            value=False,
+            label="Nested NER",
+            info="Allow for nested NER?",
+            scale=0,
+        )
+        multi_label = gr.Checkbox(
+            value=False,
+            label="Multi-label",
+            info="Allow for multi-label?",
+            scale=0,
+        )
+
+    # Output
+    output = gr.HighlightedText(label="Predicted Entities")
+
+    # Submit button
+    submit_btn = gr.Button("Submit")
+    examples = gr.Examples(
+        examples,
+        fn=pii_ner,
+        inputs=[input_text, labels, threshold, nested_ner, multi_label],
+        outputs=output,
+        cache_examples=True,
+        cache_mode="lazy",
+    )
+
+    # Events when submitting
+    input_text.submit(
+        fn=pii_ner,
+        inputs=[input_text, labels, threshold, nested_ner, multi_label],
+        outputs=output,
+    )
+    labels.submit(
+        fn=pii_ner,
+        inputs=[input_text, labels, threshold, nested_ner, multi_label],
+        outputs=output,
+    )
+    threshold.release(
+        fn=pii_ner,
+        inputs=[input_text, labels, threshold, nested_ner, multi_label],
+        outputs=output,
+    )
+    submit_btn.click(
+        fn=pii_ner,
+        inputs=[input_text, labels, threshold, nested_ner, multi_label],
+        outputs=output,
+    )
+    nested_ner.change(
+        fn=pii_ner,
+        inputs=[input_text, labels, threshold, nested_ner, multi_label],
+        outputs=output,
+    )
+    multi_label.change(
+        fn=pii_ner,
+        inputs=[input_text, labels, threshold, nested_ner, multi_label],
+        outputs=output,
+    )
+
+demo.launch(debug=False)

exception.py

@@ -0,0 +1,50 @@
+"""
+This module defines a custom exception handling class and a function to get error message with details of the error.
+"""
+
+# Standard Library
+import sys
+
+# Local imports
+from logger import logging
+
+
+# Function Definition to get error message with details of the error (file name and line number) when an error occurs in the program
+def get_error_message(error, error_detail: sys):
+    """
+    Get error message with details of the error.
+
+    Args:
+        - error (Exception): The error that occurred.
+        - error_detail (sys): The details of the error.
+
+    Returns:
+        str: A string containing the error message along with the file name and line number where the error occurred.
+    """
+    _, _, exc_tb = error_detail.exc_info()
+
+    # Get error details
+    file_name = exc_tb.tb_frame.f_code.co_filename
+    return "Error occured in python script name [{0}] line number [{1}] error message[{2}]".format(
+        file_name, exc_tb.tb_lineno, str(error)
+    )
+
+
+# Custom Exception Handling Class Definition
+class CustomExceptionHandling(Exception):
+    """
+    Custom Exception Handling:
+        This class defines a custom exception that can be raised when an error occurs in the program.
+        It takes an error message and an error detail as input and returns a formatted error message when the exception is raised.
+    """
+
+    # Constructor
+    def __init__(self, error_message, error_detail: sys):
+        """Initialize the exception"""
+        super().__init__(error_message)
+
+        self.error_message = get_error_message(error_message, error_detail=error_detail)
+
+    def __str__(self):
+        """String representation of the exception"""
+        return self.error_message

logger.py

@@ -0,0 +1,21 @@
+# Importing the required modules
+import os
+import logging
+from datetime import datetime
+
+# Creating a log file with the current date and time as the name of the file
+LOG_FILE = f"{datetime.now().strftime('%m_%d_%Y_%H_%M_%S')}.log"
+
+# Creating a logs folder if it does not exist
+logs_path = os.path.join(os.getcwd(), "logs")
+os.makedirs(logs_path, exist_ok=True)
+
+# Setting the log file path and the log level
+LOG_FILE_PATH = os.path.join(logs_path, LOG_FILE)
+
+# Configuring the logger
+logging.basicConfig(
+    filename=LOG_FILE_PATH,
+    format="[ %(asctime)s ] %(lineno)d %(name)s - %(levelname)s - %(message)s",
+    level=logging.INFO,
+)

ner.py

@@ -0,0 +1,38 @@
+import sys
+from typing import Dict, Union
+from exception import CustomExceptionHandling
+from logger import logging
+from gliner import GLiNER
+
+# Load the model
+model = GLiNER.from_pretrained("nvidia/gliner-PII")
+
+
+def pii_ner(
+    text, labels: str, threshold: float, nested_ner: bool, multi_label: bool
+) -> Dict[str, Union[str, int, float]]:
+    """Perform PII detection on the given text."""
+    try:
+        labels = labels.split(",")
+        logging.info("PII detection completed successfully")
+        return {
+            "text": text,
+            "entities": [
+                {
+                    "entity": entity["label"],
+                    "word": entity["text"],
+                    "start": entity["start"],
+                    "end": entity["end"],
+                    "score": 0,
+                }
+                for entity in model.predict_entities(
+                    text,
+                    labels,
+                    flat_ner=not nested_ner,
+                    threshold=threshold,
+                    multi_label=multi_label,
+                )
+            ],
+        }
+    except Exception as e:
+        raise CustomExceptionHandling(e, sys) from e