# Botify Agent: HTML Question

**ID:** `html_question`

Ask any question about an HTML Page.


    Ask about a page's semantic structure, HTML elements, and technical aspects.
    Inquire about HTML tags, DOM structure, meta information, or how to access elements with CSS selectors.
    This agent can also extract and analyze structured data (e.g., JSON-LD, microdata, RDFa), understand semantic hierarchy, find specific attributes or values, and provide insights about a page's technical implementation.
    

## Authentication

All endpoints require a **Bearer token** in the `Authorization` header.

```
Authorization: Bearer <your-token>
```

## Calling this agent

This agent supports the following processing modes:

| Mode | Type | Description |
|------|------|-------------|
| **Process** | Synchronous | Single-item processing. Best for real-time requests with immediate response. |
| **Batch Process** | Synchronous | Process multiple items in a single request for efficiency. |
| **Async Process** | Asynchronous | Single-item processing for long-running tasks that exceed timeout limits. |
| **Async Batch Process** | Asynchronous | Large-scale batch jobs with background processing. |

# Synchronous Processing

Synchronous calls block until the result is ready. Use these for quick operations where you need immediate results.

## Single Item Processing

Process a single input and receive the result immediately.

```
POST https://agents.botify.com/{org}/{project}/html_question/process
```

### Request body

```json
{
  "item": {
    "url": "<url>",
    "question": "<question>"
  }
}
```

### Response

Returns a single processed item (HTTP 200).

### cURL example

```bash
curl -X POST "https://agents.botify.com/{org}/{project}/html_question/process" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "item": {
    "url": "<url>",
    "question": "<question>"
  }
}'
```

## Batch Processing

Process multiple inputs in a single synchronous request. More efficient than making individual calls. Items are processed concurrently on the server.

```
POST https://agents.botify.com/{org}/{project}/html_question/batch_process
```

### Request body

```json
{
  "items": [
    {
      "url": "<url>",
      "question": "<question>"
    }
  ]
}
```

### Response

Returns an array of results. Each element is either a successful processed item (`"status": "success"`) or an error (`"status": "error"`).

### cURL example

```bash
curl -X POST "https://agents.botify.com/{org}/{project}/html_question/batch_process" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "items": [
    {
      "url": "<url>",
      "question": "<question>"
    }
  ]
}'
```

### When to use synchronous calls

- Processing completes within timeout limits (typically 30 seconds)
- You need immediate results for user-facing features
- Small to medium batch sizes (up to ~100 items)

# Asynchronous Processing

Asynchronous calls return immediately with a batch ID. You then poll for results using the `async_batches/` endpoints.

### Async processing flow

1. **Submit job** -- `POST` to `async_process` or `async_batch_process`
2. **Receive batch ID** -- response contains `batch_id`
3. **Poll status** -- `HEAD` request to check readiness (lightweight, no body)
4. **Get results** -- `GET` request to retrieve processed results

## Async Single Item

Submit a single item for background processing. Use the `/single` endpoint to retrieve the result.

```
POST https://agents.botify.com/{org}/{project}/html_question/async_process
```

### Request body

```json
{
  "item": {
    "url": "<url>",
    "question": "<question>"
  }
}
```

### cURL example

```bash
# Step 1: Submit the job
curl -X POST "https://agents.botify.com/{org}/{project}/html_question/async_process" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "item": {
    "url": "<url>",
    "question": "<question>"
  }
}'

# Response: { "batch_id": "abc123" }

# Step 2: Check if batch is ready (HEAD request -- lightweight check)
curl -I -X HEAD "https://agents.botify.com/{org}/{project}/html_question/async_batches/abc123" \
  -H "Authorization: Bearer $TOKEN"
# Returns 200 if ready, 204 if still processing

# Step 3: Get the result (for single-item async)
curl -X GET "https://agents.botify.com/{org}/{project}/html_question/async_batches/abc123/single" \
  -H "Authorization: Bearer $TOKEN"
# Returns 200 with result, 202 if still processing, 404 if batch not found
```

## Async Batch Processing

Submit multiple items for background processing. The request body uses **JSONL** (newline-delimited JSON) format.

```
POST https://agents.botify.com/{org}/{project}/html_question/async_batch_process
```

### Request body (JSONL, `Content-Type: text/plain`)

The first line contains `config` and `batch_config`. Each subsequent line is an item with a unique `id`.

```
{"config": {}, "batch_config": {}}
{"id": "item_1", "item": {"url": "<url>", "question": "<question>"}}
```

### Response

Returns a JSON object with `batch_id`, `status`, and a `Location` header.

### cURL example

```bash
# Step 1: Submit the batch job
curl -X POST "https://agents.botify.com/{org}/{project}/html_question/async_batch_process" \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: text/plain" \
  -d '{"config": {}, "batch_config": {}}\n{"id": "item_1", "item": {"url": "<url>", "question": "<question>"}}'

# Response: { "batch_id": "xyz789" }

# Step 2: Check if batch is ready (HEAD request)
curl -I -X HEAD "https://agents.botify.com/{org}/{project}/html_question/async_batches/xyz789" \
  -H "Authorization: Bearer $TOKEN"
# Returns 200 if ready, 204 if still processing

# Step 3: Get all results
curl -X GET "https://agents.botify.com/{org}/{project}/html_question/async_batches/xyz789" \
  -H "Authorization: Bearer $TOKEN"
```

## Checking Batch Status

Use a lightweight `HEAD` request to check if your batch is ready without transferring data.

```
HEAD https://agents.botify.com/{org}/{project}/html_question/async_batches/{batch_id}
```

```bash
curl -I -X HEAD "https://agents.botify.com/{org}/{project}/html_question/async_batches/{batch_id}" \
  -H "Authorization: Bearer $TOKEN"

# Response headers indicate status:
# HTTP/1.1 200 OK        -> Batch is complete, results ready
# HTTP/1.1 204 No Content -> Still processing
# HTTP/1.1 404 Not Found -> Batch does not exist
```

## Retrieving Results

Once the batch is ready, fetch results using the appropriate endpoint.

```bash
# For async_process (single item) -- use /single endpoint
curl -X GET "https://agents.botify.com/{org}/{project}/html_question/async_batches/{batch_id}/single" \
  -H "Authorization: Bearer $TOKEN"

# For async_batch_process (multiple items) -- use base endpoint
curl -X GET "https://agents.botify.com/{org}/{project}/html_question/async_batches/{batch_id}" \
  -H "Authorization: Bearer $TOKEN"
# Returns streaming JSONL where each line is a processed item or error
```

### Async response codes

| Code | Endpoint | Meaning | Action |
|------|----------|---------|--------|
| 200 | `HEAD` / `GET` | Batch complete, results ready | Read results from response body |
| 204 | `HEAD` | Still processing | Continue polling |
| 202 | `GET /single` | Still processing | Continue polling |
| 400 | `GET /single` | All items failed (client error) | Check error in response body |
| 404 | `HEAD` / `GET` | Batch does not exist | Verify `batch_id` is correct |

> **HEAD vs GET:** Use `HEAD` requests for lightweight status checks (no response body). Use `GET` only when ready to retrieve results to minimize bandwidth.

### When to use asynchronous calls

- Processing takes longer than 30 seconds
- Large batch sizes (100+ items)
- Background processing where immediate results aren't required
- Integration with job queues or workflow systems

## Python Example

A complete Python example showing both synchronous and asynchronous patterns.

```python
import requests
import time

API_TOKEN = "your_api_token"
BASE_URL = "https://agents.botify.com/{organization}/{project}"
AGENT = "html_question"

headers = {
    "Authorization": f"Bearer {API_TOKEN}",
    "Content-Type": "application/json"
}

single_payload = {
  "item": {
    "url": "<url>",
    "question": "<question>"
  }
}


def process_sync(payload: dict) -> dict:
    """Synchronous single-item processing."""
    response = requests.post(
        f"{BASE_URL}/{AGENT}/process",
        headers=headers,
        json=payload
    )
    response.raise_for_status()
    return response.json()


def process_async(
    payload: dict,
    poll_interval: int = 5,
    max_retries: int = 60
) -> dict:
    """Asynchronous single-item processing with polling."""
    # Submit job
    response = requests.post(
        f"{BASE_URL}/{AGENT}/async_process",
        headers=headers,
        json=payload
    )
    batch_id = response.json()["batch_id"]

    # Poll for results using HEAD (lightweight check)
    for _ in range(max_retries):
        status = requests.head(
            f"{BASE_URL}/{AGENT}/async_batches/{batch_id}",
            headers=headers
        )

        if status.status_code == 200:
            result = requests.get(
                f"{BASE_URL}/{AGENT}/async_batches/{batch_id}/single",
                headers=headers
            )
            return result.json()
        elif status.status_code == 204:
            time.sleep(poll_interval)
        else:
            raise Exception(f"Unexpected status: {status.status_code}")

    raise Exception("Max retries exceeded")


def process_async_batch(
    items: list,
    config: dict | None = None,
    poll_interval: int = 5
) -> dict:
    """Asynchronous batch processing with polling."""
    import json as _json

    # Build JSONL payload: first line is config, subsequent lines are items
    lines = [_json.dumps({"config": config or {}, "batch_config": {}})]
    for i, item in enumerate(items):
        lines.append(_json.dumps({"id": f"item_{i}", "item": item}))
    body = "\n".join(lines)

    # Submit batch (JSONL, text/plain)
    response = requests.post(
        f"{BASE_URL}/{AGENT}/async_batch_process",
        headers={**headers, "Content-Type": "text/plain"},
        data=body
    )
    batch_id = response.json()["batch_id"]

    # Poll until ready
    while True:
        status = requests.head(
            f"{BASE_URL}/{AGENT}/async_batches/{batch_id}",
            headers=headers
        )

        if status.status_code == 200:
            results = requests.get(
                f"{BASE_URL}/{AGENT}/async_batches/{batch_id}",
                headers=headers
            )
            return results.json()

        time.sleep(poll_interval)


# Example usage
# result = process_sync(single_payload)
# result = process_async(single_payload)
# results = process_async_batch([{"input": "item1"}, {"input": "item2"}])
```

## Billing

Fixed cost per question asked. The rest follows the page: content read scales with how much of the page the question needs and the answer written with how long an answer you ask for, and nothing caps either. Point it at a page already in your SiteCrawler crawl and no fetch is billed; otherwise the page is fetched live. Leaving response_lang on auto adds one small extra model call to detect the page's language, and only for pages that do not declare it themselves.

These usage SKUs can be charged on a call, including SKUs from tools this one may call.

| SKU | Credits | Description | Used by |
| --- | ------- | ----------- | ------- |
| Tool call | 1 per request | Charged once per successful item, on top of any usage below. | This tool |
| Gemini 3 Flash (flex), input | 250 per million tokens | Tokens the model reads from the prompt you send. | HTML Lang (`html_lang`) |
| Gemini 3 Flash (flex), output | 1,500 per million tokens | Tokens the model writes in its answer. | HTML Lang (`html_lang`) |
| Gemini 3 Flash (flex), read from cache | 50 per million tokens | Tokens the model reads from a cached prompt. Cheaper than a fresh read. | HTML Lang (`html_lang`) |
| Gemini 3 Flash (standard), input | 500 per million tokens | Tokens the model reads from the prompt you send. | HTML Lang (`html_lang`) |
| Gemini 3 Flash (standard), output | 3,000 per million tokens | Tokens the model writes in its answer. | HTML Lang (`html_lang`) |
| Gemini 3 Flash (standard), read from cache | 50 per million tokens | Tokens the model reads from a cached prompt. Cheaper than a fresh read. | HTML Lang (`html_lang`) |
| Gemini 3.1 Flash Lite (flex), input | 125 per million tokens | Tokens the model reads from the prompt you send. | This tool |
| Gemini 3.1 Flash Lite (flex), output | 750 per million tokens | Tokens the model writes in its answer. | This tool |
| Gemini 3.1 Flash Lite (flex), read from cache | 12.5 per million tokens | Tokens the model reads from a cached prompt. Cheaper than a fresh read. | This tool |
| Gemini 3.1 Flash Lite (standard), input | 250 per million tokens | Tokens the model reads from the prompt you send. | This tool |
| Gemini 3.1 Flash Lite (standard), output | 1,500 per million tokens | Tokens the model writes in its answer. | This tool |
| Gemini 3.1 Flash Lite (standard), read from cache | 25 per million tokens | Tokens the model reads from a cached prompt. Cheaper than a fresh read. | This tool |
| Live page fetch | 495 per 1,000 page | Fetches a page from the live web as an ordinary visitor would. | HTML Fetch (`html_fetch`) |
| Live page fetch, hard-blocked page | 7,425 per 1,000 page | A page that refused every gentler attempt. Charged on top of them, so a hard-blocked page costs the whole sequence. | HTML Fetch (`html_fetch`) |
| Live page fetch, protected page | 2,475 per 1,000 page | A page that refused an ordinary fetch and had to be retried. Charged on top of the ordinary attempt, not instead of it. | HTML Fetch (`html_fetch`) |


## Schemas

### Item

```json
{
  "type": "object",
  "properties": {
    "url": {
      "description": "Source URL to ask question about",
      "title": "Url",
      "type": "string"
    },
    "question": {
      "description": "Question to ask",
      "title": "Question",
      "type": "string"
    }
  },
  "required": [
    "url",
    "question"
  ]
}
```

### Config

```json
{
  "type": "object",
  "properties": {
    "tone_of_voice": {
      "default": "",
      "description": "IA tone of voice",
      "title": "Tone Of Voice",
      "type": "string"
    },
    "response_lang": {
      "default": "auto",
      "description": "Language of the response (must be a BCP47 lang code or 'auto' (default) to use the HTML page language)",
      "title": "Response Lang",
      "type": "string"
    },
    "country_code": {
      "default": "us",
      "description": "Country code to use for real-time fetches (2 letters lowercase)",
      "title": "Country Code",
      "type": "string"
    },
    "remove_tags": {
      "description": "List of HTML tags to remove from the page before processing",
      "items": {
        "type": "string"
      },
      "title": "Remove Tags",
      "type": "array"
    },
    "only_text": {
      "default": true,
      "description": "If set to True, extract the text before the LLM",
      "title": "Only Text",
      "type": "boolean"
    },
    "fallback_real_time_fetch": {
      "default": true,
      "description": "Fall back to real-time ScrapingBee fetch when URL not in SiteCrawler",
      "title": "Fallback Real Time Fetch",
      "type": "boolean"
    }
  },
  "required": []
}
```

### Response

```json
{
  "properties": {
    "url_found": {
      "description": "Whether the URL was found and the HTML was fetched",
      "title": "Url Found",
      "type": "boolean"
    },
    "answer": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Answer to given question (if the URL was found)",
      "title": "Answer"
    },
    "confidence_score": {
      "anyOf": [
        {
          "maximum": 100,
          "minimum": 0,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "A score between 0 (lowest confidence) and 100 (best confidence) representing the confidence that the answer was accurately and completely extracted",
      "title": "Confidence Score"
    },
    "url": {
      "description": "Source URL used to answer the question",
      "title": "Url",
      "type": "string"
    },
    "question": {
      "description": "Question that was asked",
      "title": "Question",
      "type": "string"
    },
    "iframe_allowed": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Whether iframes are allowed in the answer",
      "title": "Iframe Allowed"
    }
  },
  "required": [
    "url_found",
    "answer",
    "confidence_score",
    "url",
    "question"
  ],
  "title": "HTMLQuestionProcessedItem",
  "type": "object"
}
```

## Best Practices

**Use exponential backoff for polling.** Start with short intervals (1-2 seconds) and increase the delay between polls to reduce API load.

**Set reasonable timeouts.** For synchronous calls, configure your HTTP client with appropriate timeout values (30-60 seconds).

**Handle rate limits gracefully.** Implement retry logic with backoff when you receive 429 (Too Many Requests) responses.

**Batch when possible.** Use batch endpoints to reduce the number of API calls and improve throughput.