Add a Knowledge document
Add a document Agents can consult. kind: text takes text (plain text or Markdown); kind: file takes file (base64, up to 8 MiB: PDF, Word, Excel, HTML, CSV, plain text or Markdown); kind: website takes an approved HTTPS sourceUrl and optional crawl bounds and starts a crawl task (list_tasks with kind=knowledge_crawl). Indexing follows on its own: the document is searchable once indexStatus is ready (check with get_knowledge_document). Then give it to Agents with update_agent (knowledgeDocumentIds).
- Scope:
raiz:knowledge:write - Credentials: an API key, a client-credentials token or a person's access token
- Effect: writes; not idempotent: check the outcome before you retry
- Limits: request body up to 12 MB, response up to 1 MB
- CLI:
arbol raiz knowledge create· MCP tool:raiz_knowledge_create
POST
https://api.getarbol.com/v1/raiz/knowledgeAuthorization
Request body JSON required
Returns
200
Successful operation.
404
NOT_FOUND: The requested operation does not exist.RESOURCE_NOT_FOUND: The requested resource does not exist in this organization.
422
KNOWLEDGE_FILE_INVALID: The file is not valid base64, exceeds the size limit or does not match its declared type.KNOWLEDGE_KIND_MISMATCH: The change does not apply to this kind of Knowledge document.WEBSITE_NOT_APPROVED: This website's origin is not approved for crawling in this deployment.
502
OUTCOME_UNKNOWN: The operation may have been applied; check its result before repeating it.
503
UPSTREAM_UNAVAILABLE: The upstream service could not complete the request.INTEGRATIONS_UNAVAILABLE: The organization's integrations cannot be read right now. Try again shortly.