swarmauri_tool_textlength 0.11.0.dev1

NLTK-powered Swarmauri text-analysis tool for counting characters, words, and sentences.

Swarmauri Tool Text Length

swarmauri_tool_textlength is a Swarmauri text-analysis tool that measures characters, words, and sentences using NLTK tokenization. It is useful for content QA, moderation gates, prompt-budget checks, readability workflows, and agentic text analytics.

Why Use Swarmauri Tool Text Length

• Measure content size with a Swarmauri-native tool interface.
• Track character, word, and sentence counts from a single call.
• Add length checks to moderation, documentation, or editorial pipelines.
• Reuse the same tool in agents, notebooks, scripts, and backend workflows.

FAQ

What does the tool return?
A dictionary with num_characters, num_words, and num_sentences.

Are spaces included in the character count?
No. The current implementation excludes space characters.

What tokenizer does it use?
It uses NLTK sentence and word tokenizers and downloads punkt_tab at import time if needed.

Is it English-specific?
The default tokenization behavior is best suited to English text unless you swap in different tokenization logic.

Features

• Swarmauri ToolBase implementation registered as TextLengthTool.
• Character, word, and sentence counts in one structured response.
• NLTK-based tokenization for more useful word and sentence splitting.
• Works well in content governance, prompt analytics, and editorial checks.
• Supports Python 3.10, 3.11, 3.12, 3.13, and 3.14.

Installation

uv add swarmauri_tool_textlength

pip install swarmauri_tool_textlength

Usage

from swarmauri_tool_textlength import TextLengthTool

tool = TextLengthTool()
metrics = tool("This is a simple test sentence.")

print(metrics)

Examples

Measure prompt length before model submission

from swarmauri_tool_textlength import TextLengthTool

tool = TextLengthTool()
metrics = tool("Summarize the following release notes for an executive audience.")

print(metrics["num_words"])

Check documentation size in a content pipeline

from pathlib import Path
from swarmauri_tool_textlength import TextLengthTool

tool = TextLengthTool()

for path in Path("docs").rglob("*.md"):
    metrics = tool(path.read_text(encoding="utf-8"))
    print(path, metrics)

Register the tool inside a Swarmauri tool registry

from swarmauri_standard.tools.ToolCollection import ToolCollection
from swarmauri_tool_textlength import TextLengthTool

tools = ToolCollection(tools=[TextLengthTool()])
print(tools)

Related Packages

• swarmauri_tool_searchword
• swarmauri_tool_lexicaldensity
• swarmauri_tool_sentencecomplexity
• swarmauri_tool_smogindex
• swarmauri_tool_dalechallreadability

Swarmauri Foundations

• swarmauri
• swarmauri_core
• swarmauri_base
• swarmauri_standard

More Documentation

• NLTK documentation
• Swarmauri SDK repository

Best Practices

• Pre-download punkt_tab for offline or containerized deployments.
• Treat counts as language-sensitive when processing non-English corpora.
• Pair text-length checks with readability tools when enforcing content style.
• If you need whitespace-inclusive counts, extend the character-count logic downstream.

License

This project is licensed under the Apache-2.0 License.