regex_enricher()

Simple regex-based enrichment (no LLM required).

Usage

Source

regex_enricher(
    title,
    content,
)

Extracts entities using common patterns (capitalized phrases, hashtags, @-mentions) and assigns basic topics from keywords. Useful as a fallback or for testing.

Parameters

title: str

Document title.

content: str

Document content.

Returns

EnrichmentResult

Extracted entities and topics.

Examples

import talk_box as tb

result = tb.regex_enricher("Meeting Notes", "Talked to Sarah Chen about Python.")
result.entity_names  # ["Sarah Chen"]
result.topics        # []