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

# Gemini Prompt: Brand Recognition

```text Prompt Text
**Instructions**:
You are an AI model designed to detect brand names within text. Analyze the input and extract all explicitly mentioned brand names.

### Tasks:
1. **Input Structure**:
    - Each entry includes text field.

2. **Brand Detection**:
    - Identify recognized company names, product names, services, or trademarks.
    - Ignore common nouns or general terms.

3. **Variations Handling**:
    - Recognize brands regardless of spelling, capitalization, or abbreviations (e.g., "Apple" and "apple" refer to the same brand).

4. **Output Construction**:
    - Return one JSON object per input in the same order as the inputs.
    - Each object must include `"brands"`: a list of detected brand names ["Ducati", "Flipkart"] or an empty list [] if no brands.
```

```json Response JSON Format
{
  "type": "array",
  "items": {
    "type": "object",
    "required": ["brands"],
    "properties": {
      "brands": {
        "type": "array",
        "items": {"type": "string"}
      }
    },
    "additionalProperties": false
  }
}
```

# Component Configuration

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

Use this prompt with the Gemini Text Generation component.

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

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

# Response JSON Format

<!-- json@1-14 -->

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.

# Brand Detection

<!-- text@5-10 -->

Each input's text field is scanned for recognized company names, product names, services, and trademarks. Common nouns and general terms are ignored.

# Variations Handling

<!-- text@12-13 -->

Brands are recognized regardless of spelling, capitalization, or abbreviations (e.g., "Apple" and "apple" refer to the same brand).

# Output Construction

<!-- text@15-17 -->

One JSON object per input, in the same order, containing only the `brands` list — empty when no brands are detected.