> ## Documentation Index
> Fetch the complete documentation index at: https://docs.webless.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Generate FAQs
> Generate questions and answers from an indexed page.
Generate page-specific questions and answers from content already indexed for a
page. Use the page's canonical URL to identify the content.
Send URL context only. Do not send the full page body from the browser. The
API returns `not_found` when the page is not available in the selected index.
## Format the answers
| Goal | Field |
| -------------------------------------- | ------------------------------------------------------------------------------------------------------- |
| Return between one and six questions | Set `max_items`. The default is `4`. |
| Return prose answers | Set `answer_format` to `paragraph`. Use `answer_paragraph_words` to target `50`, `100`, or `150` words. |
| Return list answers | Set `answer_format` to `bullets`. Use `answer_max_bullets` to return between one and six list items. |
| Adjust the writing style | Set `tone` to `neutral`, `warm`, `professional`, or `concise`. |
| Test unpublished runtime changes | Set `version` to `unpublished`. Production requests default to `published`. |
| Bypass the cache and summary analytics | Set `is_private_session` to `true` or `tracking_consent` to `false`. |
A bullet-formatted answer is one string containing newline-separated list
items. It is not an array.
## Handle the response status
The endpoint returns HTTP `200` for each application-level result.
| Status | Meaning |
| ----------- | --------------------------------------------------------- |
| `ready` | `items` contains the generated question-and-answer pairs. |
| `not_found` | The page is not in the selected index. `items` is empty. |
| `error` | The API could not produce usable FAQs. |
## OpenAPI
````yaml api-reference/openapi-latest.json POST /api/v1/faqs
openapi: 3.1.0
info:
title: Webless API
description: >-
Reference for the latest Webless API surface. New integrations should use
the /api/v1 endpoints.
version: v1
servers:
- url: https://api.webless.ai
description: Production API
security: []
paths:
/api/v1/faqs:
post:
tags:
- Page content API
summary: Generate FAQs
description: >-
Returns questions and answers from content already indexed for the
supplied page URL. Send URL context, not the full page body.
operationId: createFaqsV1
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/V1FaqRequest'
examples:
default:
value:
company: YOUR_COMPANY
canonical_url: https://example.com/articles/product-launch
page_url: https://example.com/articles/product-launch#webless
title: Product launch
version: published
max_items: 2
answer_format: paragraph
requestId: 1f7c5f74-7b9e-4a0a-9b7d-4e3e2a5e3b60
sessionId: a1c2d3e4-1111-2222-3333-444455556666
responses:
'200':
description: FAQ result for the supplied page URL
headers:
X-Webless-Requested-Version:
description: Runtime version requested by the client.
schema:
type: string
X-Webless-Resolved-Version:
description: Runtime version used for the response.
schema:
type: string
X-Webless-Version-Fallback-Reason:
description: Reason for a runtime version fallback, when one occurs.
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/V1FaqResponse'
examples:
ready:
value:
status: ready
items:
- question: What does the product launch introduce?
answer: >-
The launch introduces a faster setup flow while
keeping existing integrations compatible.
- question: Who can use the new experience?
answer: The new experience is available to all customers.
source_url: https://example.com/articles/product-launch
title: Product launch
cache_status: miss
version: published
resolved_version: published
resolved_corpus_version: 12
generated_at: '2026-06-12T19:30:00+00:00'
not_found:
value:
status: not_found
items: []
source_url: https://example.com/articles/product-launch
title: Product launch
cache_status: miss
version: published
resolved_version: published
resolved_corpus_version: 12
generated_at: '2026-06-12T19:30:00+00:00'
'422':
description: Invalid request body
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationErrorResponse'
components:
schemas:
V1FaqRequest:
type: object
required:
- company
- canonical_url
properties:
company:
type: string
description: Public company or index identifier.
canonical_url:
type: string
description: Canonical URL of the page used to generate FAQs.
page_url:
type: string
description: >-
Current browser URL. Optional; fragments and tracking params are
normalized server-side.
title:
type: string
description: Optional page title for display and prompt context.
locale:
type: string
description: Optional locale or language hint.
requestId:
type: string
description: Caller-generated request identifier.
sessionId:
type: string
description: Caller-generated session identifier.
is_private_session:
type: boolean
default: false
description: When true, bypasses the cache and summary analytics logging.
tracking_consent:
type: boolean
nullable: true
description: >-
Tracking consent for this request. Setting this to false also
enables private-session behavior.
model:
type: string
default: gpt
description: Model alias configured for the runtime package.
version:
$ref: '#/components/schemas/V1RuntimeVersion'
max_items:
type: integer
minimum: 1
maximum: 6
default: 4
description: Maximum number of question-and-answer pairs to return.
answer_format:
type: string
enum:
- paragraph
- bullets
default: paragraph
description: Format for each answer.
answer_max_bullets:
type: integer
minimum: 1
maximum: 6
default: 3
description: Maximum list items in each answer when answer_format is bullets.
answer_paragraph_words:
type: integer
enum:
- 50
- 100
- 150
default: 100
description: Target word count for each answer when answer_format is paragraph.
tone:
type: string
enum:
- neutral
- warm
- professional
- concise
default: neutral
description: Writing style for generated answers.
V1FaqResponse:
type: object
required:
- status
- items
- cache_status
properties:
status:
$ref: '#/components/schemas/V1FaqStatus'
items:
type: array
items:
$ref: '#/components/schemas/V1FaqItem'
description: >-
Generated question-and-answer pairs. Empty when status is not_found
or error.
source_url:
type: string
nullable: true
description: Normalized source URL used for lookup.
title:
type: string
nullable: true
description: Page title returned by the request or indexed content.
cache_status:
$ref: '#/components/schemas/V1FaqCacheStatus'
version:
$ref: '#/components/schemas/V1RuntimeVersion'
resolved_version:
type: string
nullable: true
description: Resolved runtime pointer after fallback handling.
resolved_corpus_version:
type: integer
nullable: true
description: Resolved indexed corpus version used internally for the response.
generated_at:
type: string
format: date-time
nullable: true
description: Server timestamp for the generated response.
ValidationErrorResponse:
type: object
properties:
detail:
type: array
items:
type: object
additionalProperties: true
V1RuntimeVersion:
type: string
enum:
- published
- unpublished
default: published
description: >-
Runtime package pointer. Omit this field or use `published` for
production traffic. Use `unpublished` only when testing an unpublished
runtime package.
V1FaqStatus:
type: string
enum:
- ready
- not_found
- error
description: FAQ generation status.
V1FaqItem:
type: object
required:
- question
- answer
properties:
question:
type: string
description: Question generated from the indexed page content.
answer:
type: string
description: >-
Answer generated from the indexed page content. Bullet-formatted
answers contain newline-separated list items in this string.
V1FaqCacheStatus:
type: string
enum:
- hit
- miss
- bypass
description: Whether the response came from cache.
````