text-summarizer

Extractive summarization from long documents with flexible length control and batch processing. Create concise summaries from long text documents using extractive summarization. Identifies and extracts the most important sentences while preserving meaning. - Supports three algorithms (TextRank, LSA, frequency-based) with configurable language support - Control summary length by ratio, sentence count, or word count; optionally preserve original sentence order - Extract key points as bullet-point summaries alongside full-text summaries - Batch process multiple documents or entire directories with consistent parameters - Available as Python API or CLI with file input/output options - Extractive Summarization : Selects key sentences from original text - Length Control : By ratio, sentence count, or word count - Multiple Algorithms : TextRank, LSA, frequency-based - Key Points : Extract bullet-point summaries - Batch Processing : Summarize multiple documents - Preserve Structure : Maintains sentence order option - Extractive only (doesn't paraphrase or generate new text) - Works best with well-structured text (paragraphs, clear sentences) - Very short texts may not summarize well - Doesn't understand context deeply (may miss nuance)