Parcha Admin - Profiler Testing API
The Admin - Profiler Testing API from Parcha — 1 operation(s) for admin - profiler testing.
OpenAPI Specification
openapi: 3.0.0
info:
title: Parcha Admin Admin - Profiler Testing API
version: 1.0.0
description: API for managing Parcha jobs and checks
servers:
- url: https://api.parcha.ai/api/v1
description: Agent Hub API server
- url: https://demo.parcha.ai/api/v1
description: Sandbox API server
- url: https://us1.parcha.ai/api/v1
description: Legacy API server
- url: http://{your-company-domain}.parcha.ai/api/v1
description: Custom Enterpris server (your company's API server)
security:
- bearerAuth: []
tags:
- name: Admin - Profiler Testing
paths:
/admin/profiler/test:
post:
tags:
- Admin - Profiler Testing
summary: Test Web Profiler
operationId: test_web_profiler_admin_profiler_test_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/WebProfilerTestRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/WebProfilerTestResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
components:
schemas:
SimpleProductsAndServices:
properties:
products_and_services_summary:
anyOf:
- type: string
- type: 'null'
title: Products And Services Summary
description: A paragraph with the products and services offered by the business. There will be a list, this should be an introduction to that list.
products_and_services_list:
anyOf:
- items:
$ref: '#/components/schemas/ProductOrServiceItem'
type: array
- type: 'null'
title: Products And Services List
description: A list of the products and services offered by the business and their descriptions
type: object
title: SimpleProductsAndServices
WebProfilerTestRequest:
properties:
business_name:
type: string
title: Business Name
description: The name of the business to profile.
official_websites:
items:
type: string
type: array
title: Official Websites
description: A list of official website URLs for the business.
job_id:
anyOf:
- type: string
- type: 'null'
title: Job Id
description: Optional Job ID to track the profiler run.
platforms_to_search:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Platforms To Search
description: List of platforms to search (e.g., ['yelp', 'google_places']). Empty list means no platform search.
platform_finder_addresses:
anyOf:
- items:
$ref: '#/components/schemas/PlatformFinderAddressInput'
type: array
- type: 'null'
title: Platform Finder Addresses
description: Specific addresses for Platform Finder.
platforms_to_search_pf:
anyOf:
- items:
$ref: '#/components/schemas/BusinessReviewType'
type: array
- type: 'null'
title: Platforms To Search Pf
description: Specific platforms for Platform Finder to search.
max_urls_to_analyze:
anyOf:
- type: integer
- type: 'null'
title: Max Urls To Analyze
description: Max URLs from initial scrape to deep scrape.
serp_profiles:
anyOf:
- type: boolean
- type: 'null'
title: Serp Profiles
description: Whether to perform SERP for social/platform profiles.
enable_embeddings_storage:
anyOf:
- type: boolean
- type: 'null'
title: Enable Embeddings Storage
description: Enable storage of embeddings.
type: object
required:
- business_name
- official_websites
title: WebProfilerTestRequest
ProfileStatus:
type: string
enum:
- not_started
- in_progress
- completed
title: ProfileStatus
TraceNode:
properties:
id:
type: string
title: Id
description: Unique identifier for the node.
name:
type: string
title: Name
description: Human-readable name for the step (e.g., 'Scrape Website', 'Call PDL API').
status:
type: string
title: Status
description: Current status of the step (e.g., pending, running, completed, failed).
default: pending
start_time:
anyOf:
- type: string
format: date-time
- type: 'null'
title: Start Time
description: Timestamp when the step started execution.
end_time:
anyOf:
- type: string
format: date-time
- type: 'null'
title: End Time
description: Timestamp when the step finished execution.
details:
type: object
title: Details
description: Arbitrary key-value pairs for additional context (e.g., url, task_id, error_message).
parent_ids:
items:
type: string
type: array
title: Parent Ids
description: List of node IDs that must complete before this node can start, representing dependencies.
type: object
required:
- name
title: TraceNode
description: Represents a single step or operation in a workflow trace.
WorkflowTrace:
properties:
workflow_name:
type: string
title: Workflow Name
description: Name of the overall workflow (e.g., 'WebProfiler').
start_time:
type: string
format: date-time
title: Start Time
end_time:
anyOf:
- type: string
format: date-time
- type: 'null'
title: End Time
nodes:
items:
$ref: '#/components/schemas/TraceNode'
type: array
title: Nodes
description: List of all nodes in the trace.
type: object
required:
- workflow_name
title: WorkflowTrace
description: Represents the entire trace graph for a workflow execution.
AddressWithType:
properties:
type:
type: string
title: Type
description: The type of the model
exclude_from_llm: true
street_1:
anyOf:
- type: string
- type: 'null'
title: Street 1
description: The first line of the street address
examples:
- 123 Main St
street_2:
anyOf:
- type: string
- type: 'null'
title: Street 2
description: The second line of the street address
examples:
- Apt 4B
city:
anyOf:
- type: string
- type: 'null'
title: City
description: The city of the address
examples:
- Anytown
state:
anyOf:
- type: string
- type: 'null'
title: State
description: The state of the address
examples:
- AnyState
country_code:
anyOf:
- type: string
- type: 'null'
title: Country Code
description: The country of the address as 2-letter code (ISO 3166-1 alpha-2)
examples:
- US
postal_code:
anyOf:
- type: string
- type: 'null'
title: Postal Code
description: The postal code of the address
examples:
- '54321'
address_type:
anyOf:
- $ref: '#/components/schemas/AddressType'
- type: 'null'
description: The type of address
type: object
required:
- type
title: AddressWithType
AlternateBusiness:
properties:
business_name:
type: string
title: Business Name
description: Name of the alternate business
description:
type: string
title: Description
description: Brief description of what this business does
website:
anyOf:
- type: string
- type: 'null'
title: Website
description: Website URL if found
address_of_operation:
anyOf:
- $ref: '#/components/schemas/AddressWithType'
- type: 'null'
description: Operating address of this alternate business
type: object
required:
- business_name
- description
title: AlternateBusiness
description: Represents an alternate business found in discarded sources.
WebProfilerTestResponse:
properties:
built_profile:
anyOf:
- $ref: '#/components/schemas/WebPresenceConsistencyCheckResult'
- type: 'null'
description: The final synthesized business profile.
structured_scrape_results:
items:
$ref: '#/components/schemas/ScannedWebsiteWithAnalysis'
type: array
title: Structured Scrape Results
description: Websites where structured data (e.g., PDL, LinkedIn) was the primary source.
unstructured_scrape_results:
items:
$ref: '#/components/schemas/ScannedWebsiteWithAnalysis'
type: array
title: Unstructured Scrape Results
description: Websites scraped for text/HTML content and analyzed.
error_log:
items:
type: string
type: array
title: Error Log
description: Log of errors encountered during the profiling process.
trace:
anyOf:
- $ref: '#/components/schemas/WorkflowTrace'
- type: 'null'
description: Workflow execution trace providing a step-by-step graph.
type: object
required:
- structured_scrape_results
- unstructured_scrape_results
- error_log
title: WebProfilerTestResponse
ScannedWebsite:
properties:
type:
type: string
title: Type
description: The type of the model
exclude_from_llm: true
source_id:
type: string
title: Source Id
description: The source id of the webpage.
source_name:
anyOf:
- type: string
- type: 'null'
title: Source Name
description: The source name of the webpage.
language:
anyOf:
- type: string
- type: 'null'
title: Language
description: The language of the webpage.
webpage_url:
anyOf:
- type: string
- type: 'null'
title: Webpage Url
webpage_title:
anyOf:
- type: string
- type: 'null'
title: Webpage Title
webpage_text:
anyOf:
- type: string
- type: 'null'
title: Webpage Text
webpage_urls:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Webpage Urls
description: The urls inside the webpage.
exclude_from_llm: true
screenshot_url:
anyOf:
- type: string
- type: 'null'
title: Screenshot Url
is_valid_url:
anyOf:
- type: boolean
- type: 'null'
title: Is Valid Url
description: Whether the URL is valid and could be opened.
response_code:
anyOf:
- type: integer
- type: 'null'
title: Response Code
description: The response code of the URL.
default: 200
search_snippet:
anyOf:
- type: string
- type: 'null'
title: Search Snippet
description: The search snippet of the URL.
is_relevant:
anyOf:
- type: boolean
- type: 'null'
title: Is Relevant
description: Whether the URL is relevant to business or person being searched.
content_type:
anyOf:
- type: string
- type: 'null'
title: Content Type
description: The content type of the URL.
urls_with_context:
anyOf:
- items:
$ref: '#/components/schemas/UrlWithContext'
type: array
- type: 'null'
title: Urls With Context
description: The urls with context of the webpage.
exclude_from_llm: true
webpage_structured_scrape:
anyOf:
- type: object
- type: 'null'
title: Webpage Structured Scrape
description: The structured scrape of the webpage
scrape_type:
$ref: '#/components/schemas/ScrapeType'
description: The type of webpage scrape
default: generic
publication_date:
anyOf:
- type: string
- type: 'null'
title: Publication Date
description: The publication date of the webpage.
publication_date_source:
anyOf:
- type: string
- type: 'null'
title: Publication Date Source
description: The source of the publication date of the webpage.
pdf_snapshot_url:
anyOf:
- type: string
- type: 'null'
title: Pdf Snapshot Url
description: The URL of the PDF snapshot of the webpage.
cloudflare_encountered:
type: boolean
title: Cloudflare Encountered
description: Whether Cloudflare protection was encountered during scraping
default: false
error:
anyOf:
- type: string
- type: 'null'
title: Error
description: Error message if any error occurred during scraping
type: object
required:
- type
title: ScannedWebsite
WebPresenceConsistencyCheckResult:
properties:
business_name:
anyOf:
- $ref: '#/components/schemas/FoundDocBusinessName'
- type: 'null'
description: The name of the business that the webpages are about.
alternate_business_names:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Alternate Business Names
description: List of alternate business names including DBAs (Doing Business As), trade names, or operating names found with strong signals. ONLY include names with explicit DBA/trade name indicators, NOT partners, customers, or similar businesses.
examples:
- XYZ Services
- Quick Solutions
- FastTech
business_description:
anyOf:
- items:
$ref: '#/components/schemas/FoundDocBusinessDescription'
type: array
- type: 'null'
title: Business Description
description: The comprehensive description about the business, in one or more paragraphs. Each paragraph should be a separate string in the list.
business_products_and_services:
anyOf:
- $ref: '#/components/schemas/FoundDocStructuredProductsAndServices'
- type: 'null'
description: A detailed description of the products and services the business offers.
business_customers:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Business Customers
description: The customers of the business
examples:
- Customer 1
- Customer 2
business_country_code:
anyOf:
- type: string
- type: 'null'
title: Business Country Code
description: The most likely country code of the business
keywords:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Keywords
description: The keywords that would be most relevant to the business when searching for it on the web and in documents
associated_individuals:
items:
$ref: '#/components/schemas/FoundDocSimpleAssociatedIndividual'
type: array
title: Associated Individuals
description: The associated individuals of the business
addresses_found:
anyOf:
- items:
$ref: '#/components/schemas/FoundDocNonStrictAddress'
type: array
- type: 'null'
title: Addresses Found
description: Addresses found across all relevant webpages, with source evidence.
type:
type: string
title: Type
description: The type of the model
exclude_from_llm: true
profile_confidence:
$ref: '#/components/schemas/ConfidenceTier'
description: The confidence you had in the generating this profile, from low to high
profile_status:
anyOf:
- $ref: '#/components/schemas/ProfileStatus'
- type: 'null'
description: The status of the business profile report
exclude_from_llm: true
alternate_businesses:
items:
$ref: '#/components/schemas/AlternateBusiness'
type: array
title: Alternate Businesses
description: List of other businesses found in discarded sources that might be related or confused with the target business
source_ids_to_discard:
items:
type: string
type: array
title: Source Ids To Discard
description: List of source_ids that should NOT be stored in GCS because they are about different businesses or completely irrelevant
type: object
required:
- type
- profile_confidence
title: WebPresenceConsistencyCheckResult
description: This class represents the results for the Web Presence Consistency Check.
FoundDocBusinessName:
properties:
source_id:
anyOf:
- type: string
- type: 'null'
title: Source Id
description: The source id for webpage source.
evidence:
anyOf:
- type: string
- type: 'null'
title: Evidence
description: A short citation for the source. DO NOT USE DOUBLE OR SINGLE QUOTES.
business_name:
anyOf:
- type: string
- type: 'null'
title: Business Name
description: The business name
type: object
title: FoundDocBusinessName
WebRelevanceCheckResult:
properties:
type:
type: string
title: Type
description: The type of the model
exclude_from_llm: true
reason_for_relevance:
anyOf:
- type: string
- type: 'null'
title: Reason For Relevance
description: The reason why the webpage is relevant to the business
reason_against_relevance:
anyOf:
- type: string
- type: 'null'
title: Reason Against Relevance
description: The reason why the webpage could not be relevant to the business
is_relevant:
type: boolean
title: Is Relevant
description: Whether the webpage is relevant to the business
extracted_metadata:
anyOf:
- $ref: '#/components/schemas/BusinessWebpageMetadataV3'
- type: 'null'
description: The metadata of the webpage
type: object
required:
- type
- is_relevant
title: WebRelevanceCheckResult
ProductOrServiceItem:
properties:
name:
type: string
title: Name
description: The name of the product or service
description:
anyOf:
- type: string
- type: 'null'
title: Description
description: The description of the product or service
type: object
required:
- name
title: ProductOrServiceItem
PlatformFinderAddressInput:
properties:
street_1:
anyOf:
- type: string
- type: 'null'
title: Street 1
street_2:
anyOf:
- type: string
- type: 'null'
title: Street 2
city:
anyOf:
- type: string
- type: 'null'
title: City
state:
anyOf:
- type: string
- type: 'null'
title: State
postal_code:
anyOf:
- type: string
- type: 'null'
title: Postal Code
country_code:
type: string
title: Country Code
address_type:
$ref: '#/components/schemas/AddressType'
default: operations
type: object
required:
- country_code
title: PlatformFinderAddressInput
UrlWithContext:
properties:
url:
type: string
title: Url
description: The URL of the webpage.
context:
anyOf:
- type: string
- type: 'null'
title: Context
description: The unstructured context of the webpage.
type: object
required:
- url
title: UrlWithContext
FoundDocBusinessDescription:
properties:
sources:
anyOf:
- items:
$ref: '#/components/schemas/SimpleWebSource'
type: array
- type: 'null'
title: Sources
description: The sources of the data
description:
anyOf:
- type: string
- type: 'null'
title: Description
description: A paragraph, part of the business description.
type: object
title: FoundDocBusinessDescription
WebpageType:
type: string
enum:
- official_business_website
- personal_website
- search_engine_result
- adverse_media
- social_media
- news_article
- customer_review
- business_directory
- other
title: WebpageType
SimpleWebSource:
properties:
source_id:
anyOf:
- type: string
- type: 'null'
title: Source Id
description: The source id
type: object
title: SimpleWebSource
BusinessReviewType:
type: string
enum:
- yelp
- tripadvisor
- better_business_bureau
- google_place
- trustpilot
title: BusinessReviewType
ai__data_loaders__schema__base__Address:
properties:
type:
type: string
title: Type
description: The type of the model
exclude_from_llm: true
street_1:
anyOf:
- type: string
- type: 'null'
title: Street 1
description: The first line of the street address
examples:
- 123 Main St
street_2:
anyOf:
- type: string
- type: 'null'
title: Street 2
description: The second line of the street address
examples:
- Apt 4B
city:
anyOf:
- type: string
- type: 'null'
title: City
description: The city of the address
examples:
- Anytown
state:
anyOf:
- type: string
- type: 'null'
title: State
description: The state of the address
examples:
- AnyState
country_code:
anyOf:
- type: string
- type: 'null'
title: Country Code
description: The country of the address as 2-letter code (ISO 3166-1 alpha-2)
examples:
- US
postal_code:
anyOf:
- type: string
- type: 'null'
title: Postal Code
description: The postal code of the address
examples:
- '54321'
type: object
required:
- type
title: Address
description: Address
BusinessWebpageMetadataV3:
properties:
type:
type: string
title: Type
description: The type of the model
exclude_from_llm: true
found_business_name:
anyOf:
- type: string
- type: 'null'
title: Found Business Name
description: The name of the business that the webpages are about.
found_business_country:
anyOf:
- type: string
- type: 'null'
title: Found Business Country
description: The two-letter country code of the business that the webpages are about.
found_business_state:
anyOf:
- type: string
- type: 'null'
title: Found Business State
description: The state (as in a state of a country) of the business that the webpages are about.
webpage_type:
anyOf:
- $ref: '#/components/schemas/WebpageType'
- type: 'null'
description: The type of webpage.
visual_summary:
anyOf:
- type: string
- type: 'null'
title: Visual Summary
description: A visual summary of the webpage.
summary:
anyOf:
- type: string
- type: 'null'
title: Summary
description: An extensive summary of the webpage.
exclude_from_llm: true
simple_profile:
anyOf:
- $ref: '#/components/schemas/SimpleBusinessProfile'
- type: 'null'
description: A simple profile of the business that the webpage is about.
short_summary:
anyOf:
- type: string
- type: 'null'
title: Short Summary
description: A short summary of the webpage content in the `summary` field.
search_keywords:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Search Keywords
description: Search keywords used to find the business represented.
is_website_accessible:
anyOf:
- type: boolean
- type: 'null'
title: Is Website Accessible
description: Whether the website is accessible and could be opened.
not_accessible_reason:
anyOf:
- type: string
- type: 'null'
title: Not Accessible Reason
description: The reason why the website is not accessible.
urls_to_analyze:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Urls To Analyze
description: The urls to analyze in depth.
source_id:
anyOf:
- type: string
- type: 'null'
title: Source Id
description: The source id of the webpage.
found_associated_individual_names:
anyOf:
- items:
$ref: '#/components/schemas/SimpleAssociatedIndividual'
type: array
- type: 'null'
title: Found Associated Individual Names
description: The names and titles of individuals found associated with the business on the page.
addresses_found:
anyOf:
- items:
$ref: '#/components/schemas/ai__data_loaders__schema__base__Address'
type: array
- type: 'null'
title: Addresses Found
description: List of addresses found on the webpage.
email_addresses_found:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Email Addresses Found
description: List of email addresses found on the webpage.
phone_numbers_found:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Phone Numbers Found
description: List of phone numbers found on the webpage.
detected_language:
anyOf:
- type: string
- type: 'null'
title: Detected Language
description: The primary language of the webpage content using ISO 639-1 code (e.g., 'en' for English, 'pt' for Portuguese, 'es' for Spanish)
platform_rating:
anyOf:
- type: number
- type: 'null'
title: Platform Rating
description: Business rating on the platform (e.g., 4.5 out of 5).
platform_max_rating:
anyOf:
- type: number
- type: 'null'
title: Platform Max Rating
description: Maximum possible rating on the platform (e.g., 5.0).
platform_total_reviews:
anyOf:
- type: integer
- type: 'null'
title: Platform Total Reviews
description: Total number of reviews on the platform.
platform_name:
anyOf:
- type: string
- type: 'null'
title: Platform Name
description: Name of the platform (e.g., 'Yelp', 'Google Places', 'TripAdvisor').
platform_business_category:
anyOf:
- type: string
- type: 'null'
title: Platform Business Category
description: Business category as listed on the platform.
platform_business_hours:
anyOf:
- type: string
- type: 'null'
title: Platform Business Hours
description: Business operating hours as listed on the platform.
platform_phone_number:
anyOf:
- type: string
- type: 'null'
title: Platform Phone Number
description: Phone number found on the platform profile.
platform_website_url:
anyOf:
- type: string
- type: 'null'
title: Platform Website Url
description: Official website URL found on the platform profile.
platform_image_urls:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Platform Image Urls
description: List of image URLs associated with the business on the platform.
image_analysis_details:
anyOf:
- type: string
- type: 'null'
title: Image Analysis Details
description: A detailed description and analysis of the images found on the platform profile (e.g., storefront, food, interior, menu, ambiance, quality, professional/user-submitted).
type: object
required:
- type
title: BusinessWebpageMetadataV3
ConfidenceTier:
type: string
enum:
- LOW
- MEDIUM
- HIGH
title: ConfidenceTier
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
type: object
required:
- loc
- msg
- type
title: ValidationError
FoundDocSimpleAssociatedIndividual:
properties:
sources:
anyOf:
- items:
$ref: '#/components/schemas/SimpleWebSource'
type: array
- type: 'null'
title: Sources
description: The sources of the data
first_name:
anyOf:
- type: string
- type: 'null'
title: First Name
description: The first name of the individual associated with the business.
last_name:
anyOf:
- type: string
- type: 'null'
title: Last Name
description: The last name of the individual associated with the business.
role:
anyOf:
- type: string
- type: 'n
# --- truncated at 32 KB (38 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/parcha/refs/heads/main/openapi/parcha-admin-profiler-testing-api-openapi.yml