Ingest a training data source

POST

/api/v1/ai/training/data

Create a new training data source, or update an existing one by passing its trainingDataId. Creating a source of type url starts a website ingestion: Unless crawls the site and trains the AI on its content.

Use cases

• Ingest a website: Create a url source pointing at the website you want the AI to learn from
• Rescan: Update an existing source to change its URL filters or schedule and trigger a retrain
• Add a Q&A: Create a faq source with a question and an answer. Unless trains the AI on it and adds it to the content library

Notes

• Omit trainingData.trainingDataId to create a new source, pass it to update that source
• trainingData.accountId and trainingData.websiteId must match the x-account-id and x-website-id headers
• For website ingestion use type: url with method set to all (crawl the whole site), single (one page) or sitemap
• For a Q&A use type: faq with method: single, and set question, answer and name. The question and answer together may be at most 1900 characters
• Ingestion runs asynchronously, poll the get training data endpoint to follow progress

Parameters

Header Parameters

x-api-key

required

string

Your API key from account settings.

x-user-email

required

string

The email address of your user.

x-account-id

required

string

The ID of your account. You can find this in the account settings.

x-website-id

required

string

The ID of the workspace you want to use.

Request Body ^required

object

trainingData

required

object

trainingDataId

ID of an existing source to update. Omit to create a new source.

string

accountId

required

Must match the x-account-id header.

string

websiteId

required

Must match the x-website-id header.

string

type

required

Kind of source. Use url for website ingestion, other values include faq, pdf, docx, md and csv.

string

method

required

How to crawl a url source. all follows links from the entry point, single ingests one page, sitemap reads the sitemap.

string

Allowed values: single all sitemap

url

Entry point URL for a url source.

string

name

Display name of the source.

string

question

The question of a faq source. Required when creating one.

string

answer

The answer of a faq source. Required when creating one.

string

isPublic

required

Whether content from this source may be shown to anonymous visitors.

boolean

include

Path prefixes to include while crawling.

Array<string>

exclude

Path prefixes to exclude while crawling.

Array<string>

schedule

How often the source is rescanned.

string

Allowed values: Daily Weekly Monthly Never

skipRetrain

Skip retraining after saving, only store the source configuration.

boolean

Responses

200

The source was saved and ingestion was started.

object

message

string

Example

{
  "message": "Training data upserted"
}

401

Unauthorized - invalid API key.