> ## Documentation Index > Fetch the complete documentation index at: https://docs.context.dev/llms.txt > Use this file to discover all available pages before exploring further. # Query website data using AI > Use AI to extract specific data points from a brand's website. The AI will crawl the website and extract the requested information based on the provided data points. 10 Credits ## OpenAPI ````yaml https://app.stainless.com/api/spec/documented/context.dev/openapi.documented.yml post /brand/ai/query openapi: 3.0.0 info: title: Context API description: API for retrieving context data from any website version: 1.0.0 servers: - url: https://api.context.dev/v1 security: [] paths: /brand/ai/query: post: tags: - Web Extraction summary: Query website data using AI description: >- Use AI to extract specific data points from a brand's website. The AI will crawl the website and extract the requested information based on the provided data points. requestBody: required: true content: application/json: schema: type: object required: - domain - data_to_extract properties: domain: type: string description: The domain name to analyze specific_pages: type: object description: Optional object specifying which pages to analyze properties: home_page: type: boolean description: Whether to analyze the home page blog: type: boolean description: Whether to analyze the blog terms_and_conditions: type: boolean description: Whether to analyze the terms and conditions page privacy_policy: type: boolean description: Whether to analyze the privacy policy page about_us: type: boolean description: Whether to analyze the about us page contact_us: type: boolean description: Whether to analyze the contact us page careers: type: boolean description: Whether to analyze the careers page faq: type: boolean description: Whether to analyze the FAQ page pricing: type: boolean description: Whether to analyze the pricing page data_to_extract: type: array description: Array of data points to extract from the website items: type: object required: - datapoint_name - datapoint_type - datapoint_description - datapoint_example properties: datapoint_name: type: string description: Name of the data point to extract datapoint_type: type: string enum: - text - number - date - boolean - list - url description: Type of the data point datapoint_list_type: type: string enum: - string - text - number - date - boolean - list - url - object default: string description: >- Type of items in the list when datapoint_type is 'list'. Defaults to 'string'. Use 'object' to extract an array of objects matching a schema. datapoint_object_schema: type: object description: >- Schema definition for objects when datapoint_list_type is 'object'. Provide a map of field names to their scalar types. additionalProperties: type: string enum: - string - number - date - boolean minProperties: 1 example: testimonial_text: string testimonial_author: string datapoint_description: type: string description: Description of what to extract datapoint_example: type: string description: Example of the expected value timeoutMS: $ref: '#/components/schemas/TimeoutMS' responses: '200': description: Successful response content: application/json: schema: type: object properties: status: type: string description: Status of the response, e.g., 'ok' domain: type: string description: The domain that was analyzed urls_analyzed: type: array description: List of URLs that were analyzed items: type: string data_extracted: type: array description: Array of extracted data points items: type: object properties: datapoint_name: type: string description: Name of the extracted data point datapoint_value: oneOf: - type: string - type: number - type: boolean - type: array items: type: string - type: array items: type: number - type: array items: type: object description: >- Value of the extracted data point. Can be a primitive type, an array of primitives, or an array of objects when datapoint_list_type is 'object'. '400': description: Bad Request - validation error content: application/json: schema: type: object properties: message: type: string description: Error message error_code: type: string enum: - INTERNAL_ERROR - VALID - NOT_FOUND - FORBIDDEN - USAGE_EXCEEDED - RATE_LIMITED - UNAUTHORIZED - DISABLED - INSUFFICIENT_PERMISSIONS - TIMEOUT_EXCEEDS_MAXIMUM - WEBSITE_ACCESS_ERROR - INPUT_VALIDATION_ERROR description: Error code indicating the type of error '401': description: Unauthorized content: application/json: schema: type: object properties: error_code: type: string enum: - INTERNAL_ERROR - VALID - NOT_FOUND - FORBIDDEN - USAGE_EXCEEDED - RATE_LIMITED - UNAUTHORIZED - DISABLED - INSUFFICIENT_PERMISSIONS - TIMEOUT_EXCEEDS_MAXIMUM - WEBSITE_ACCESS_ERROR - INPUT_VALIDATION_ERROR description: Error code indicating the type of error '408': description: Request Timeout content: application/json: schema: type: object properties: message: type: string description: Timeout error message error_code: type: string enum: - REQUEST_TIMEOUT description: Error code indicating request timeout '500': description: Internal server error content: application/json: schema: type: object properties: message: type: string description: Error message error_code: type: string enum: - INTERNAL_ERROR description: Error code indicating internal server error security: - bearerAuth: [] x-codeSamples: - lang: JavaScript source: |- import ContextDev from 'context.dev'; const client = new ContextDev({ apiKey: process.env['CONTEXT_DEV_API_KEY'], // This is the default and can be omitted }); const response = await client.ai.aiQuery({ data_to_extract: [ { datapoint_description: 'datapoint_description', datapoint_example: 'datapoint_example', datapoint_name: 'datapoint_name', datapoint_type: 'text', }, ], domain: 'domain', }); console.log(response.data_extracted); - lang: Python source: |- import os from context.dev import ContextDev client = ContextDev( api_key=os.environ.get("CONTEXT_DEV_API_KEY"), # This is the default and can be omitted ) response = client.ai.ai_query( data_to_extract=[{ "datapoint_description": "datapoint_description", "datapoint_example": "datapoint_example", "datapoint_name": "datapoint_name", "datapoint_type": "text", }], domain="domain", ) print(response.data_extracted) - lang: Ruby source: |- require "context_dev" context_dev = ContextDev::Client.new(api_key: "My API Key") response = context_dev.ai.ai_query( data_to_extract: [ { datapoint_description: "datapoint_description", datapoint_example: "datapoint_example", datapoint_name: "datapoint_name", datapoint_type: :text } ], domain: "domain" ) puts(response) components: schemas: TimeoutMS: type: integer minimum: 1000 maximum: 300000 description: >- Optional timeout in milliseconds for the request. If the request takes longer than this value, it will be aborted with a 408 status code. Maximum allowed value is 300000ms (5 minutes). securitySchemes: bearerAuth: type: http scheme: bearer ````