# Response Fields

## Response Fields

### **Top-Level Fields**

| Field                  | Description                                                                            | Example                                             |
| ---------------------- | -------------------------------------------------------------------------------------- | --------------------------------------------------- |
| **`traceID`**          | Unique identifier for the request. Used for debugging, support, and internal tracking. | `"traceID": "121da7f7-c8c8-42bc-980e-a1f0a07961e8"` |
| **`timestamp`**        | ISO-8601 timestamp indicating when the request was processed.                          | `"timestamp": "2026-04-13T14:16:13.543Z"`           |
| **`request_duration`** | End-to-end request duration in seconds (from request received to response returned).   | `"request_duration": 18.56`                         |
| **`process_duration`** | Total internal processing time in seconds. This includes the full request lifecycle.   | `"process_duration": 18.56`                         |
| **`scraper`**          | Scraper name by LLM Engine                                                             | `"scraper": "Gemini"`                               |

**Note**\
`request_duration` is included within `process_duration`.\
For example, if `request_duration` is `18.56` and `process_duration` is `18.56`, the overall time experienced by the client is **18.56 seconds**.

***

### **Response Object**

The main parsed output from the LLM.

***

#### `prompt`

The original prompt sent to the LLM for this request.\
This field is always returned as part of the response for traceability and debugging.

**Example**

```json
"prompt": "what are the leading SEO tips in 2026"
```

***

#### `text_markdown`

Markdown-formatted version of the response, preserving structure such as headings, lists, emphasis, and inline citations.

This field represents the **primary readable output** of the LLM, including formatting and citation markers as returned by the model.

***

**Example**

```json
"text_markdown": "In 2026, SEO has shifted from \"ranking for keywords\" to \"optimizing for visibility across the AI ecosystem.\"\n\n### 1. Generative Engine Optimization (GEO)\n* **Answer-First Formatting:** Lead your articles with a concise, 2-3 sentence direct answer.\n* **Modular Content:** Use clear headings, bulleted lists, and tables.\n* **Schema Markup Everything:** Use FAQ, HowTo, and Product schema to help AI understand your data."
```

***

#### **`text` (plain text)**

Plain-text version of the response with formatting removed.\
Useful for storage, indexing, or systems that don't support Markdown.

**Example**

```json
"text": "In 2026, SEO has shifted from ranking for keywords to optimizing for visibility across the AI ecosystem. With Google's AI Overviews and search assistants like ChatGPT and Claude siphoning up to 60% of clicks for informational queries, the strategy is no longer just about being #1—it's about being the cited source."
```

***

#### **`citations_found`**

Boolean indicating whether the model output included citations.

**Example**

```json
"citations_found": true
```

***

#### **`citations`**

Flat list of citation objects extracted from Gemini.

Each citation includes:

* `id`
* `title`
* `url`
* `description`
* `section`: `"citations"` or `"more"`

**Example**

```json
"citations": [
  {
    "id": 1,
    "url": "https://www.mandr-group.com/the-future-of-seo-how-ai-is-changing-content-strategy-in-2026/",
    "title": "The Future of SEO: How AI Is Changing Content Strategy in 2026 - M&R Marketing",
    "description": "In 2026, don't just optimize your digital presence to reach the top of Google's results page.",
    "section": "citations"
  },
  {
    "id": 2,
    "url": "https://thistle.media/how-will-googles-ai-search-sge-reshape-seo-strategies-by-2026/",
    "title": "How Will Google's AI Search (SGE) Reshape SEO Strategies by 2026? - Thistle Media",
    "description": "Visibility is no longer just about ranking first; it's about being referenced, cited, and trusted by AI systems.",
    "section": "citations"
  }
]
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://help.netnut.io/netnut-documentation/netnut-scraper-apis/llm-scraper/gemini/response-fields.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.