> ## Documentation Index
> Fetch the complete documentation index at: https://deepline.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Context.dev: Contextdev Preview Webdb
> Preview extraction (dry run). Includes SDK V2 and CLI requests, input constraints, response fields, and Deepline credit cost.
Preview extraction (dry run).
Tool ID: `contextdev_preview_webdb`
## Run this action
Use the TypeScript SDK for a single call. Put `ctx.tools.execute(...)` inside a Play when the call should be durable, scheduled, or run across a CSV.
```ts theme={null}
import { Deepline } from 'deepline';
const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
'contextdev_preview_webdb',
{
"urls": [
"https://example.com/resource"
],
"schema": {}
},
);
console.log(result.toolResponse.raw);
```
### CLI
```bash theme={null}
deepline tools execute contextdev_preview_webdb --input '{
"urls": [
"https://example.com/resource"
],
"schema": {}
}' --json
```
## Example response
The static output schema is not detailed enough to generate a reliable example. Use `deepline tools get contextdev_preview_webdb --json` for the complete live contract.
## Input reference
Tests extraction without creating a collection.
| Name | Type | Required | Default | Details |
| --------------------- | -------- | -------- | ------- | ------------------------------------------------------------------------------------------------------ |
| `payload.urls` | `array` | Yes | — | URLs to test. Maximum 5. Minimum items: 1. Maximum items: 5. |
| `payload.schema` | `object` | Yes | — | JSON Schema for the fields extracted into each row. Zod users can pass the output of z.toJSONSchema(). |
| `payload.eligibility` | `object` | No | — | Rules that decide whether a page becomes a row. |
| `payload.tags` | `array` | No | — | Optional tags for tracking usage. Up to 20 tags, each 1 to 50 characters. Maximum items: 20. |
Show raw input schema
### Input JSON Schema
```json theme={null}
{
"type": "object",
"description": "Tests extraction without creating a collection.",
"properties": {
"urls": {
"type": "array",
"description": "URLs to test. Maximum 5.",
"minItems": 1,
"maxItems": 5,
"items": {
"type": "string",
"format": "uri"
}
},
"schema": {
"type": "object",
"description": "JSON Schema for the fields extracted into each row. Zod users can pass the output of z.toJSONSchema().",
"additionalProperties": true
},
"eligibility": {
"type": "object",
"description": "Rules that decide whether a page becomes a row.",
"properties": {
"prefilter": {
"type": "object",
"description": "Fast URL and text checks.",
"properties": {
"url_match": {
"type": "array",
"description": "URL patterns a page must match. Supports exact URLs, `*`, `**`, and `:name` path values.",
"maxItems": 50,
"items": {
"type": "string"
}
},
"must_contain_any": {
"type": "array",
"description": "Text where at least one value must appear.",
"maxItems": 50,
"items": {
"type": "string"
}
},
"must_not_contain": {
"type": "array",
"description": "Text values that must not appear.",
"maxItems": 50,
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"semantic": {
"type": "object",
"description": "AI check for whether a page should become a row.",
"properties": {
"condition": {
"type": "string",
"description": "Plain-language rule a page must satisfy.",
"minLength": 1,
"maxLength": 4000
},
"min_score": {
"type": "number",
"description": "Minimum matching score from 0 to 1. Defaults to 0.7.",
"minimum": 0,
"maximum": 1
}
},
"required": [
"condition"
],
"additionalProperties": false
}
},
"additionalProperties": false
},
"tags": {
"type": "array",
"description": "Optional tags for tracking usage. Up to 20 tags, each 1 to 50 characters.",
"maxItems": 20,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 50
}
}
},
"required": [
"urls",
"schema"
],
"additionalProperties": false
}
```
## Output reference
| Name | Type | Required | Default | Details |
| ------------------------------------------------- | ---------------- | -------- | ------- | ------- |
| `result.data` | `object` | Yes | — | — |
| `result.data.results` | `array` | Yes | — | — |
| `result.data.results[].url` | `string` | Yes | — | — |
| `result.data.results[].end_url` | `string \| null` | Yes | — | — |
| `result.data.results[].eligibility` | `object \| null` | Yes | — | — |
| `result.data.results[].eligibility.eligible` | `boolean` | Yes | — | — |
| `result.data.results[].eligibility.score` | `number \| null` | Yes | — | — |
| `result.data.results[].eligibility.reason` | `string` | Yes | — | — |
| `result.data.results[].row` | `object \| null` | Yes | — | — |
| `result.data.results[].fields` | `object \| null` | Yes | — | — |
| `result.data.results[].extraction` | `object \| null` | Yes | — | — |
| `result.data.results[].extraction.confidence` | `number \| null` | Yes | — | — |
| `result.data.results[].extraction.missing_fields` | `array` | Yes | — | — |
| `result.data.results[].error` | `string \| null` | Yes | — | — |
| `result.data.key_metadata` | `object` | No | — | — |
| `result.meta` | `object` | No | — | — |
Show raw output schema
### Output JSON Schema
```json theme={null}
{
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"url": {
"type": "string"
},
"end_url": {
"type": [
"string",
"null"
]
},
"eligibility": {
"type": [
"object",
"null"
],
"properties": {
"eligible": {
"type": "boolean"
},
"score": {
"type": [
"number",
"null"
]
},
"reason": {
"type": "string"
}
},
"required": [
"eligible",
"score",
"reason"
],
"additionalProperties": false
},
"row": {
"type": [
"object",
"null"
],
"additionalProperties": {}
},
"fields": {
"type": [
"object",
"null"
],
"additionalProperties": {
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"extracted",
"missing",
"invalid",
"low_confidence"
]
},
"confidence": {
"type": [
"number",
"null"
]
}
},
"required": [
"status",
"confidence"
],
"additionalProperties": false
}
},
"extraction": {
"type": [
"object",
"null"
],
"properties": {
"confidence": {
"type": [
"number",
"null"
]
},
"missing_fields": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"confidence",
"missing_fields"
],
"additionalProperties": false
},
"error": {
"type": [
"string",
"null"
]
}
},
"required": [
"url",
"end_url",
"eligibility",
"row",
"fields",
"extraction",
"error"
],
"additionalProperties": false
}
},
"key_metadata": {
"type": "object",
"properties": {},
"required": [],
"additionalProperties": false
}
},
"required": [
"results"
],
"additionalProperties": false
},
"meta": {
"type": "object",
"additionalProperties": true
}
},
"required": [
"data"
],
"additionalProperties": false
}
```
## Deepline cost
* Pricing model: `fixed` (per call).
* Estimated Deepline credits: `0` per pricing unit.
* Provider-native pricing may still exist outside Deepline credit billing.
## Related documentation
* [Context.dev provider guide](/docs/providers/contextdev/guide)
* [SDK V2 quickstart](/docs/sdk-v2/quickstart)
* [SDK reference](/docs/sdk-v2/sdk-reference)
* [Run tools across a CSV](/docs/sdk-v2/batch-csv)