Skip to main content
Training Data

Add a training file

Adds a document the AI agent can learn from. Provide exactly one source:

POST
/v2/training_data/files
  • Inline text — { "name": "refund-policy.md", "content": "..." }. Markdown or plain text is stored as-is and indexing is attempted before the response returns; check indexStatus (status is completed). Best for content you generate yourself, such as an SOP compiled from resolved conversations.
  • Remote file — { "url": "https://..." } (optional name). The file (PDF, DOCX, PPTX, XLSX, TXT, HTML, …; max 50 MB) is downloaded and converted to text in the background. The response returns immediately with status: "processing"; poll the file until it is completed or failed.
  • Multipart upload — send multipart/form-data with the document in a file part and, optionally, a JSON data field such as {"name": "..."}. Converted in the background like a remote file.

Keeping files in sync (create-or-update). Pass your own externalId (unique per workspace) and the same request becomes idempotent: a new ID creates the file (201), a known ID with different content updates that file in place and re-indexes it (200), and a known ID with identical content is a no-op (200, no embedding work). Add a source label to group everything one pipeline owns, then list by source to find entries to remove. Every response carries contentHash so you can diff a whole library from the list endpoint.

Without externalId, uploading a file whose name and bytes match an existing file returns the existing file with status 200 instead of creating a duplicate. Multipart uploads over 50 MB are rejected with 413.

Authorizations

Authorizationstringheaderrequired

API key as Bearer token. Use: Authorization: Bearer sk_...

Headers

Featurebase-Versionenum<string>header

API version for this request. Defaults to your organization's configured API version if not specified.

Available options: 2026-08-19.orbit, 2026-01-01.nova, 2025-12-12.clover
Example: 2026-08-19.orbit

Body

application/json
contentstring

Text or markdown to train on. Stored as-is; indexing is attempted before returning. Check indexStatus. Cannot be combined with url.

Maximum string length: 2000000
Example: # Refund policy Customers can request a refund within 30 days of purchase…
externalIdstring

Your own identifier for this entry (unique per workspace). When provided, the request creates the entry if the ID is new and otherwise updates the existing entry in place — an unchanged payload is a no-op. Use it to keep the AI agent in sync with a system of record without tracking Featurebase IDs.

Required string length: 1 - 255
Example: kb-article-1842
namestring

Display name of the file. Required with content; optional with url (defaults to the downloaded file name) or a multipart upload (defaults to the uploaded file name).

Required string length: 1 - 255
Example: refund-policy.md
sourcestring

Free-form label for the pipeline or system this entry came from. Filter lists by it to review or sweep everything from one source.

Required string length: 1 - 100
Example: resolved-conversations
urlstring

Public http(s) URL of a document to download and convert (PDF, DOCX, TXT, HTML, …; max 50 MB). Conversion runs in the background — poll the file until status is completed. Cannot be combined with content.

Maximum string length: 2048
Example: https://example.com/docs/refund-policy.pdf

Response

application/json

Created

characterCountnumber | nullrequired

Characters of extracted text

Example: 12840
contentstring | null

Full extracted text (markdown). Returned when retrieving or updating a single file; omitted from list and create responses.

Example: # Refund policy Customers can request a refund within 30 days of purchase…
contentHashstring | nullrequired

SHA-256 (hex) of the stored source: for inline text and content edits the trimmed text, for uploads and URLs the original bytes. Compare it with your own hash to detect changes without downloading content.

Example: 9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd15d6c15b0f00a08
contentPreviewstring | nullrequired

First 200 characters of the extracted text

Example: # Refund policy Customers can request a refund within 30 days…
createdAtstringrequired

ISO timestamp of the upload

Example: 2026-09-03T10:15:00.000Z
externalIdstring | nullrequired

Your own identifier for this file, if one was set

Example: kb-article-1842
fileSizenumber | nullrequired

Size of the originally uploaded source in bytes (unchanged by content edits)

Example: 48213
idstringrequired

Training file ID

Example: 67ec1234abcd5678ef901234
indexStatusenum<string>required

Whether the content is searchable by the AI agent. pending while indexing, indexed when the AI agent can use it, failed if indexing failed (the content is stored and indexing is retried hourly).

Available options: pending, indexed, failed
Example: indexed
mimeTypestring | nullrequired

MIME type of the originally uploaded source

Example: application/pdf
namestringrequired

File name shown in the dashboard

Example: refund-policy.pdf
objectenum<string>required

Object type identifier

Available options: training_file
Example: training_file
outcomeenum<string>

On create and update responses: created, updated (same externalId or same name and bytes, content replaced and re-indexed), or unchanged (identical content, nothing done). Absent on reads.

Available options: created, updated, unchanged
Example: created
processingErrorstring | nullrequired

Conversion error message when status is failed

sourcestring | nullrequired

Pipeline label, if one was set

Example: resolved-conversations
statusenum<string>required

processing while the file is being converted to text, completed once the content is stored, failed if conversion failed (see processingError).

Available options: processing, completed, failed
Example: completed
updatedAtstringrequired

ISO timestamp of the last change

Example: 2026-09-03T10:15:30.000Z
wordCountnumber | nullrequired

Words of extracted text

Example: 2130

Still need help? Ask the team