> ## Documentation Index
> Fetch the complete documentation index at: https://docs.andiai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Response format
> Structure of the Andi AI Search API response, including result types and instant answers.
All responses are JSON objects. The `format=context` option returns markdown text instead — see [query parameters](/features/query-parameters) for details.
The `results_type` field tells you the shape of the response. Use it to determine which arrays and objects are present — for example, `results_type: "weather"` means a `weather` object is included.
## Top-level fields
| Field | Type | Always present | Description |
| ------------------ | ------ | -------------- | ------------------------------------------------------------------- |
| `results_type` | string | Yes | Category of results (e.g., `search`, `news`, `images`) |
| `answer` | string | Yes | Generated answer for the query (may be empty) |
| `type` | string | Yes | Same as `results_type` |
| `title` | string | Yes | Title summarizing the search results |
| `results` | array | Yes | Search results |
| `metrics` | object | Yes | Search performance metrics |
| `correctedQuery` | string | No | Spell-corrected query (deep search only, when a correction is made) |
| `related_searches` | array | No | Related search suggestions |
| `topics` | array | No | Related topics |
### Type-specific arrays
Depending on the query intent, the response may include additional arrays alongside `results`:
| Field | Present when |
| ----------- | ------------------------- |
| `videos` | Video intent queries |
| `images` | Image intent queries |
| `news` | News intent queries |
| `places` | Location/business queries |
| `profiles` | People-related queries |
| `socials` | Social media queries |
| `academics` | Scholarly queries |
## Search results
Each result in the `results` array has this structure:
| Field | Type | Always present | Description |
| ------------- | ------ | -------------- | ------------------------------------------------------------------ |
| `title` | string | Yes | Page title |
| `link` | string | Yes | Page URL (returned as `url` when `linkFormat=url`) |
| `desc` | string | Yes | Page description or summary |
| `source` | string | Yes | Domain name |
| `type` | string | Yes | Result type (see [result types](#result-types)) |
| `date` | string | No | Publication date |
| `image` | string | No | Preview image URL |
| `snippet` | string | No | Query-relevant text excerpt (distinct from `desc`) |
| `answer` | string | No | Inline answer for instant answer results |
| `extracts` | array | No | Text extracts from the page, when available (when `extracts=true`) |
| `contentType` | string | No | Content type (when `metadata=full`) |
| `reader` | object | No | Extracted page content (when `metadata=full`) |
### Accessing key fields
```python theme={null}
data = response.json()
for result in data["results"]:
# Always present
print(result["title"], result["link"], result["source"])
# Optional fields — check before accessing
if result.get("snippet"):
print(f"Snippet: {result['snippet']}")
if result.get("extracts"):
print(f"Extract: {result['extracts'][0][:200]}")
if result.get("date"):
print(f"Published: {result['date']}")
```
## Result types
The `type` field indicates the kind of result:
| Type | Description |
| ---------------- | -------------------------------- |
| `website` | Standard web page |
| `news` | News article |
| `video` | Video content |
| `image` | Image content |
| `place` | Business or place |
| `profile` | Person or entity profile |
| `social` | Social media content |
| `academic` | Scholarly or research content |
| `calculation` | Math computation result |
| `weather` | Weather data |
| `computation` | Computed answer |
| `instant answer` | Direct answer to a factual query |
## Instant answers
Some queries trigger instant answers alongside regular results.
### Weather
Queries about weather return a `weather` object:
```json theme={null}
{
"results_type": "weather",
"answer": "",
"type": "weather",
"title": "Weather in San Francisco",
"results": [],
"weather": {
"location": {
"name": "San Francisco",
"country": "US",
"coordinates": {
"latitude": 37.7749,
"longitude": -122.4194
}
},
"temperature": 62,
"feelsLike": 59,
"units": "imperial",
"description": "Partly Cloudy",
"humidity": 72,
"windSpeed": 12,
"windDirection": 270,
"pressure": 1013,
"icon": "partly-cloudy",
"cloudiness": 40,
"visibility": 10000,
"timestamp": "2025-03-15T14:00:00Z"
},
"metrics": {
"query": "weather san francisco",
"intent": "WeatherIntent",
"timestamp": "2025-03-15T14:00:01Z",
"duration": 850,
"queries_executed": 1,
"api_requests_count": 2,
"results_returned": 0,
"total_results_found": 0
}
}
```
Use the `units` parameter to get results in `metric` or `imperial`. The default is auto-detected from the `country` parameter.
### Calculation
Mathematical queries return a `calculation` object:
```json theme={null}
{
"results_type": "computation",
"answer": "",
"type": "computation",
"title": "150 * 1.08",
"results": [],
"calculation": {
"expression": "150 * 1.08",
"result": "162"
},
"metrics": { ... }
}
```
Image queries return an `images` array with thumbnail and dimension data:
```json theme={null}
{
"results_type": "images",
"answer": "",
"type": "images",
"title": "Mountain landscape images",
"results": [],
"images": [
{
"title": "Mountain landscape",
"link": "https://example.com/photo",
"image": "https://example.com/photo.jpg",
"source": "example.com",
"type": "image",
"thumbnail": "https://example.com/photo_thumb.jpg",
"width": "1920",
"height": "1080"
}
],
"metrics": { ... }
}
```
Image results include `thumbnail` (thumbnail URL), `width`, and `height` as string values.
## Parsing tips
* **Check `results_type` first** to know the response shape before accessing type-specific fields
* **`results` is always an array** but may be empty for instant answers (weather, calculations)
* **`desc` vs `snippet`**: `desc` is the page's general description; `snippet` is a query-relevant excerpt (when available)
* **`answer` at top level** is a generated answer string (may be empty); `answer` on individual results is an inline answer for instant answer result types
* **Optional fields** (`date`, `image`, `snippet`, `extracts`) may not be present on every result — always check before accessing
## Search intents
The `results_type` and `type` fields reflect what kind of search was performed. You can force an intent with the `intent` parameter, or let the API auto-detect it.
Common intent aliases:
| Alias | Intent | Extra fields |
| ----------- | ------------------- | ------------- |
| `search` | General web search | — |
| `news` | News articles | `news` |
| `video` | Video content | `videos` |
| `images` | Image search | `images` |
| `weather` | Weather queries | `weather` |
| `calculate` | Math expressions | `calculation` |
| `wiki` | Wikipedia/knowledge | — |
| `code` | Programming queries | — |
| `recipe` | Recipe search | — |
| `place` | Business search | `places` |
| `time` | Time queries | — |
See [query parameters](/features/query-parameters#intent-values) for the full list of intent aliases.
## Metrics
The response always includes a `metrics` object with search performance data:
```json theme={null}
{
"results": [...],
"metrics": {
"query": "machine learning",
"intent": "FallbackSearchIntent",
"timestamp": "2025-03-15T14:00:01Z",
"duration": 234,
"queries_executed": 1,
"api_requests_count": 3,
"results_returned": 10,
"total_results_found": 42
}
}
```
| Field | Type | Description |
| --------------------- | ------- | ------------------------------------------------------------ |
| `query` | string | The query as processed |
| `intent` | string | Detected or forced search intent |
| `timestamp` | string | Timestamp of the request |
| `duration` | number | Total request time in milliseconds |
| `queries_executed` | integer | Number of queries executed |
| `api_requests_count` | integer | Number of API requests made |
| `results_returned` | integer | Results returned in this response |
| `total_results_found` | integer | Total results found across sources |
| `cached` | boolean | Whether response was from cache (only present on cache hits) |
## Next steps
Full parameter reference.
Use search results as LLM context.