Filtering and Frequency¶

3 endpoints for content sanitization and lexical frequency analysis.

Python SDK Examples¶

Mask PII¶

from toolkitapi import TextAnalysis

text = "Contact [email protected], SSN 123-45-6789, card 4111 1111 1111 1111"

with TextAnalysis(api_key="tk_...") as ta:
    result = ta.pii_mask(
        text=text,
        mask_char="*",
        types=["email", "ssn", "credit_card"],
    )

print(result["masked_text"])
print(result["detection_count"])

Profanity detection only¶

from toolkitapi import TextAnalysis

with TextAnalysis(api_key="tk_...") as ta:
    check = ta.profanity(text="sample text", check_only=True)

print(check["is_profane"], check["profanity_count"])

Profanity cleaning¶

from toolkitapi import TextAnalysis

with TextAnalysis(api_key="tk_...") as ta:
    cleaned = ta.profanity(text="sample text", mask_char="#", check_only=False)

print(cleaned["cleaned_text"])

Word frequency¶

from toolkitapi import TextAnalysis

text = "logs logs traces alerts logs traces dashboards"

with TextAnalysis(api_key="tk_...") as ta:
    result = ta.word_frequency(
        text=text,
        top_n=10,
        min_length=3,
        exclude_stop_words=True,
    )

print(result["total_words"], result["unique_words"])
for item in result["frequencies"]:
    print(item["word"], item["count"], item["percentage"])

Request Parameters¶

POST /v1/text/pii-mask¶

POST /v1/text/profanity¶

POST /v1/text/word-frequency¶

Response Fields¶

PII mask¶

Profanity¶

Word frequency¶