Skip to main content
POST
/
v1
/
annotations
Create Annotation
curl --request POST \
  --url https://api.mixpeek.com/v1/annotations \
  --header 'Content-Type: application/json' \
  --data '
{
  "document_id": "<string>",
  "label": "<string>",
  "collection_id": "<string>",
  "confidence": 0.5,
  "reasoning": "<string>",
  "payload": {},
  "retriever_id": "<string>",
  "execution_id": "<string>",
  "stage_name": "<string>"
}
'
{
  "document_id": "<string>",
  "namespace_id": "<string>",
  "label": "<string>",
  "annotation_id": "<string>",
  "collection_id": "<string>",
  "confidence": 0.5,
  "reasoning": "<string>",
  "payload": {},
  "retriever_id": "<string>",
  "execution_id": "<string>",
  "stage_name": "<string>",
  "actor_id": "system",
  "actor_type": "system",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z"
}

Documentation Index

Fetch the complete documentation index at: https://docs.mixpeek.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

Headers

​
Authorization
string

REQUIRED: Bearer token authentication using your API key. Format: 'Bearer sk_xxxxxxxxxxxxx'. You can create API keys in the Mixpeek dashboard under Organization Settings.

Examples:

"Bearer YOUR_API_KEY"

"Bearer YOUR_STRIPE_API_KEY"

​
authorization
string
​
X-Namespace
string

Namespace identifier for scoping this request. All resources (collections, buckets, taxonomies, etc.) are scoped to a namespace. You can provide either the namespace name or namespace ID. Format: ns_xxxxxxxxxxxxx (ID) or a custom name like 'my-namespace'. Falls back to ?namespace= query parameter if the header is omitted.

Examples:

"ns_abc123def456"

"production"

"my-namespace"

Body

application/json

Create a new annotation on a document.

​
document_id
string
required

Document to annotate.

​
label
string
required

Decision label (e.g. 'approved', 'rejected', 'deferred').

Required string length: 1 - 100
​
collection_id
string | null

Collection the document belongs to.

​
confidence
number | null

Human confidence (0.0–1.0).

Required range: 0 <= x <= 1
​
reasoning
string | null

Why this decision was made.

Maximum string length: 5000
​
payload
Payload · object

Structured payload (use-case-specific).

​
retriever_id
string | null
​
execution_id
string | null
​
stage_name
string | null

Response

Successful Response

Single annotation response.

​
document_id
string
required

The document this annotation is attached to.

​
namespace_id
string
required

Namespace scope.

​
label
string
required

Human decision label. Domain-specific — e.g. 'approved', 'rejected', 'deferred', 'infringement', 'safe', 'confirmed_dupe'.

Required string length: 1 - 100
​
annotation_id
string

Unique annotation identifier.

​
collection_id
string | null

Collection the document belongs to.

​
confidence
number | null

Human confidence in this decision (0.0–1.0).

Required range: 0 <= x <= 1
​
reasoning
string | null

Why this decision was made. Stored for audit trail.

Maximum string length: 5000
​
payload
Payload · object

Use-case-specific structured data. E.g. {'codes_approved': ['E11.40'], 'raf_impact': 0.302}

​
retriever_id
string | null

Retriever that produced the document being annotated.

​
execution_id
string | null

Retriever execution ID.

​
stage_name
string | null

Stage that produced the result (e.g. 'llm_enrich').

​
actor_id
string
default:system

Who made the annotation (user ID or API key ID).

​
actor_type
string
default:system

Actor type: 'user', 'api_key', or 'system'.

​
created_at
string<date-time>
​
updated_at
string<date-time>