Keyword Extractor

Overview

Extracts keyword candidates using single-document term-frequency (TF) analysis with stopword filtering. This is TF only — NOT TF-IDF: there is no reference corpus or inverse-document-frequency weighting, so common-but-uninformative terms are down-weighted only by the stopword list. Deterministic, no LLM. Stable sort by frequency desc, first occurrence, then lexical order. Accepts file input via file_ref — no need to extract file content first.

Word-frequency ranking is statistical, not semantic — we give you deterministic TF-based keywords so tagging and indexing stay reproducible without LLM overhead.

When to use it

Scope

Non-goals

• Does not perform semantic or contextual analysis — purely statistical
• Does not use LLM-based extraction or embeddings
• Does not perform topic modeling or clustering

Properties

Capabilities

Cost & billing

Flat rate per invocation

File handling

File limits

Constraints this skill applies to your input and generated files. The “Limited by” column shows the static source of each cap; none of these can be raised by upgrading your plan.

How we handle your data

Input schema

Output schema

API contract

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"text.extract_keywords","input":{"text":"Cloud computing infrastructure enables scalable resources.","maxKeywords":10}}'

import { Squillify } from "@squillify/sdk";

const sq = new Squillify({ apiKey: process.env.SQUILLIFY_API_KEY });

const { output } = await sq.execute("text.extract_keywords", {"maxKeywords":5,"text":"Cloud computing infrastructure enables organizations to scale their computing resources on demand. Modern cloud platforms provide computing power, storage, and networking as managed services. Infrastructure as code automates cloud resource provisioning."});

Errors

Other limits

Limitations

• Does not perform semantic or contextual analysis — purely statistical
• Does not use LLM-based extraction or embeddings
• Does not perform topic modeling or clustering
• Semantic analysis requiring contextual understanding
• Topic modeling or document clustering
• Named entity recognition (use text.extract_entities_regex instead)

How to call

POST /v1/execute (requires authentication)

{
  "skillKey": "text.extract_keywords",
  "input": {
    "maxKeywords": 5,
    "text": "Cloud computing infrastructure enables organizations to scale their computing resources on demand. Modern cloud platforms provide computing power, storage, and networking as managed services. Infrastructure as code automates cloud resource provisioning."
  }
}

Examples

{
  "maxKeywords": 5,
  "text": "Cloud computing infrastructure enables organizations to scale their computing resources on demand. Modern cloud platforms provide computing power, storage, and networking as managed services. Infrastructure as code automates cloud resource provisioning."
}

{
  "returned": 5,
  "stopwordsVersion": "english-v1",
  "keywords": [
    {
      "keyword": "cloud",
      "score": 0.12,
      "count": 3
    },
    {
      "keyword": "computing",
      "score": 0.12,
      "count": 3
    },
    {
      "keyword": "infrastructure",
      "score": 0.08,
      "count": 2
    },
    {
      "keyword": "enables",
      "score": 0.04,
      "count": 1
    },
    {
      "keyword": "organizations",
      "score": 0.04,
      "count": 1
    }
  ],
  "truncated": true,
  "method": "tf",
  "totalCandidates": 20
}

{
  "text": "Cloud computing infrastructure enables organizations to scale their computing resources on demand.",
  "maxKeywords": 3,
  "stopwords": [
    "cloud",
    "computing"
  ]
}

{
  "returned": 3,
  "stopwordsVersion": "english-v1",
  "keywords": [
    {
      "keyword": "infrastructure",
      "score": 0.1111,
      "count": 1
    },
    {
      "keyword": "enables",
      "score": 0.1111,
      "count": 1
    },
    {
      "keyword": "organizations",
      "score": 0.1111,
      "count": 1
    }
  ],
  "truncated": true,
  "method": "tf",
  "totalCandidates": 9
}

Recommended use cases

• Generate content tags for articles or documents
• Build search indexes from document collections
• Identify dominant terms for content classification

Avoid for

• Semantic analysis requiring contextual understanding
• Topic modeling or document clustering
• Named entity recognition (use text.extract_entities_regex instead)

Related skills

Composable with

Safety & privacy

• Runs without calling any external service.
• Your payloads are never stored permanently.
• Telemetry captures metadata only — never your payload contents.
• We never train models on your payloads.
• No human reviews your payloads.

Tags