---
updatedAt: 2026-08-24T18:17:32.000Z
agentTools:
  projectIndex: https://docs.datastreamer.io/llms.txt
---

# Gemini Prompt: Category

```text Prompt Text
Analyze the given text assign one of the following labels and provide confidence:
["Politics & World Events", "Hobbies & Relaxation", "Family & Relationships", "Fashion & Lifestyle", "Food & Beverages", "Technology & Manufacturing", "Sports & Entertainment", "Travel & Adventure", "Personal Finance & Careers", "Health & Wellness", "Weather & Environment", "Education & Learning", "Other"]

Definitions:
- Politics & World Events: "Local, regional, national, and international exercise of power, political struggle for power, politics and the relationships between governing bodies and states. Establishment, statement, and analysis of rules, policies, international relations, and significant global events that influence the structure and conduct of society."
- Hobbies & Relaxation: "Activities pursued for enjoyment and relaxation, including creative pursuits, board game, outdoor recreational sports, and leisure activities."
- Family & Relationships: "Matters related to family life, parenting, romantic relationships, friendships, and social connections."
- Fashion & Lifestyle: "The design of clothing, accessories, and personal style, as well as lifestyle choices and trends in society."
- Food & Beverages: "Culinary practices, recipes, food industries, beverages, and all matters related to food production and consumption."
- Technology & Manufacturing: "Advancements and innovations in technology, market research, marketing,business and industrial processes involved in the production of goods and services."
- Sports & Entertainment: "Activities and events related to sports, games, and entertainment, including music, sport, movies, television, and other forms of entertainment."
- Travel & Adventure: "Information and experiences related to travel destinations, exploration, and adventurous activities."
- Personal Finance & Careers: "Advice and information on managing personal finances, career development, and professional growth."
- Health & Wellness: "Physical and mental health topics, including fitness, nutrition, medical treatments, and overall well-being."
- Weather & Environment: "Information on weather conditions, natural disasters, climate change, and environmental conservation."
- Education & Learning: "All forms of learning and education, including formal schooling, skill development, and personal enrichment."

Return one JSON object per input in the same order as the inputs. Each object must contain `label` and `confidence`.
```

```json Response JSON Format
{
  "type": "array",
  "items": {
    "type": "object",
    "required": ["label", "confidence"],
    "properties": {
      "label": {
        "type": "string",
        "enum": [
          "Politics & World Events",
          "Hobbies & Relaxation",
          "Family & Relationships",
          "Fashion & Lifestyle",
          "Food & Beverages",
          "Technology & Manufacturing",
          "Sports & Entertainment",
          "Travel & Adventure",
          "Personal Finance & Careers",
          "Health & Wellness",
          "Weather & Environment",
          "Education & Learning",
          "Other"
        ]
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "additionalProperties": false
  }
}
```

# Component Configuration

<!-- text@1-2 -->

Use this prompt with the Gemini Text Generation component.

- Source Path: `content.body`
- Destination Path: `enrichment.category`
- Suggested Model: `gemini-3.1-flash-lite`

Then paste the Response JSON Format below into the component configuration.

# Response JSON Format

<!-- json@1-33 -->

Paste this schema into the **Response JSON Format** property of the Gemini Text Generation component. Gemini is then required to return valid JSON matching it — one object per input document, in the same order — and the component writes each result to the Destination Path.

# Category Definitions

<!-- text@4-16 -->

The model classifies each input into one of the predefined categories, using the definitions to disambiguate overlapping topics.

# Output Format

<!-- text@18 -->

One JSON object per input, in the same order, containing only the `label` and `confidence` fields.