Natural Language Analysis

​

What it provides

• Sentiment — overall sentiment (-1.0 very negative to +1.0 very positive) with a magnitude.
• Entity extraction — named entities (people, organizations, locations, etc.).
• Topic classification — high-level categories (requires text ≥ 20 bytes).
• Content moderation — categories like Toxic, Insult, Profanity, Derogatory, Sexual, Violent, Death, Harm & Tragedy, Firearms & Weapons, Illicit Drugs.

​

How it works

• v1 (classification, entities) for topic and entity extraction.
• v2 (sentiment, moderation) for sentiment and moderation scores.

​

Parameters

​

Outputs and metrics

{
  "language": "en",
  "sentiment": { "score": -0.78, "magnitude": 1.4 },
  "entities": [
    { "name": "OpenAI", "type": "ORGANIZATION", "salience": 0.4 }
  ],
  "topics": [{ "name": "/Computers & Electronics", "confidence": 0.91 }],
  "moderation": [
    { "category": "Toxic",     "confidence": 0.86 },
    { "category": "Profanity", "confidence": 0.71 }
  ],
  "metrics": {
    "processing_time_ms": 480.0,
    "sentiment_score": -0.78,
    "sentiment_magnitude": 1.4,
    "topic_count": 1,
    "entity_count": 1,
    "moderation_category_count": 2,
    "max_moderation_confidence": 0.86
  },
  "status": "OK"
}

​

Termination signals

​

Limits and cost

​

Typical latency

​

When to use it

• Best as a flag, not a block. Sentiment and entity counts are noisy. Use them to enrich your analysis log; reach for safety guardrails or YARA when you actually want to block.
• Use moderation as a secondary signal. It overlaps with ShieldGemma but uses a different model family; agreement between the two raises confidence on a violation.
• Disable what you do not use. If you do not need topic classification, the include_* toggles already disable sentiment, entities, and moderation; topic always runs but is fast.

​

Failure modes

• NL API error → analyzer ERROR status; surfaced in analyzer_results.
• Empty input → topic classification skipped; other sub-analyses produce empty results.

​

Next

• Combined analyzer — wiring NLP into termination rules.
• Safety & Responsible AI — the primary safety analyzer.