Upload a Document

POST /v1/knowledge-bases/{knowledge_base_id}/documents

Property	Value
Operation	`upload_knowledge_document`
Group	Knowledge bases
Scope	`knowledge:write`
Route class	`control`
Idempotency	`Idempotency-Key` accepted: a retry with the same key replays the first answer
Audit	Audited `knowledge.document.upload` (mutation)
Released in	1.53.0
Phase 0 host	Served (the hosted api pins 1.65.0)

Uploads a file to an upload Source as multipart/form-data (1.53.0). The api checks the parts (KnowledgeDocumentIssueCode), encrypts the file under the data key of the Organization, stores it under the knowledge/ prefix, creates or revises the Document pending and starts an Ingestion run with cause manual, all before it answers. A new external_ref answers 201 with the new Document; one the Source holds answers 200 with the Document, revised, or unchanged when the content is the same. From 1.54.0: a cell with no object storage refuses every upload with 422 capability_not_available.

Request

Set VOCAL_API to the base URL of your API and VOCAL_API_KEY to an API key with the knowledge:write scope (Authentication and keys). Replace each placeholder, such as agt_... or <name>, with your own value.

curl -X POST "$VOCAL_API/v1/knowledge-bases/kb_.../documents" \
  -H "Authorization: Bearer $VOCAL_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -F "source_id=ksrc_..." \
  -F "file=@<file>"

import { readFile } from 'node:fs/promises';

const form = new FormData();
form.append('source_id', 'ksrc_...');
form.append(
  'file',
  new Blob([await readFile('<file>')]),
  '<file>',
);

const response = await fetch(`${process.env.VOCAL_API}/v1/knowledge-bases/kb_.../documents`, {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.VOCAL_API_KEY}`,
    'Idempotency-Key': crypto.randomUUID(),
  },
  body: form,
});
console.log(response.status, await response.text());

import os
import uuid

import requests

response = requests.post(
    f"{os.environ['VOCAL_API']}/v1/knowledge-bases/kb_.../documents",
    headers={
        "Authorization": f"Bearer {os.environ['VOCAL_API_KEY']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    data={
        "source_id": "ksrc_...",
    },
    files={
        "file": ("<file>", open("<file>", "rb")),
    },
)
print(response.status_code, response.text)

Parameters

Name	In	Type	Required	Description
`knowledge_base_id`	path	KnowledgeBaseId	yes	The id of a Knowledge base: `kb_` and the row's UUIDv7 in 26 Crockford base32 characters. Opaque and safe to log.
`idempotency-key`	header	string	no	A client-chosen key, kept 24 hours per Organization, environment and route. A replay returns the stored response.

Request body

Content type multipart/form-data, required: KnowledgeDocumentUploadRequest.

Field	Type	Required	Description
`external_ref`	string	no	The reference to revise; the file name when omitted.
`file`	string (binary)	yes	The file part: its bytes, at most 25 MiB (a target), with a `filename` and a `Content-Type` among `KnowledgeMediaType`.
`source_id`	KnowledgeSourceId	yes
`tags`	array of DocumentTag	no	Sent as repeated `tags` parts.
`title`	string	no

Responses

Status	Content type	Shape	Error codes
`200`	`application/json`	KnowledgeDocument
`201`	`application/json`	KnowledgeDocument
`400`	`application/json`	ErrorEnvelope	`invalid_request`
`401`	`application/json`	ErrorEnvelope	`unauthenticated`
`403`	`application/json`	ErrorEnvelope	`forbidden`, `org_suspended`
`404`	`application/json`	ErrorEnvelope	`not_found`
`409`	`application/json`	ErrorEnvelope	`knowledge_base_archived`, `idempotency_in_progress`, `idempotency_key_reused`
`422`	`application/json`	ErrorEnvelope	`validation_failed`, `capability_not_available`
`429`	`application/json`	ErrorEnvelope	`rate_limited`
`500`	`application/json`	ErrorEnvelope	`internal_error`

Fields of the `200` answer

The shape is KnowledgeDocument.

Field	Type	Required	Description
`byte_size`	integer or null	yes
`chunk_count`	integer	yes
`chunker_version`	string or null	yes
`classification`	KnowledgeClassification or null	yes
`created_at`	Timestamp	yes
`embedding_space`	EmbeddingSpace or null	yes
`entity_counts`	array of KnowledgeEntityCount	yes
`error_code`	IngestionErrorCode or null	yes	Set when `failed`.
`external_ref`	string or null	yes	The file name, URL or vendor reference the Source knows the Document by. The content class `names`: null unless the read names `include=names`, and null in the answer of a write (1.53.0, second part).
`id`	KnowledgeDocumentId	yes
`indexed_at`	Timestamp or null	yes
`knowledge_base_id`	KnowledgeBaseId	yes
`last_ingestion_run_id`	IngestionRunId or null	yes
`media_type`	KnowledgeMediaType or null	yes
`object`	`"knowledge_document"`	yes
`page_count`	integer or null	yes
`parser_version`	string or null	yes
`purged_at`	Timestamp or null	yes
`quarantine_expires_at`	Timestamp or null	yes	When the parsed text held for review is deleted, 14 days after the quarantine (a target); null otherwise.
`quarantined_at`	Timestamp or null	yes
`review_status`	KnowledgeReviewStatus	yes
`revision`	integer	yes	Counts writes to the Document; returned as the ETag and required in If-Match. Not the number of content revisions.
`source_id`	KnowledgeSourceId	yes
`status`	KnowledgeDocumentStatus	yes
`tags`	array of DocumentTag	yes
`title`	string or null	yes	The title the upload or the parse stage gave, or null when it has none. The content class `names`: null unless the read names `include=names`, and null in the answer of a write (1.53.0, second part).
`updated_at`	Timestamp	yes