Use Mixpeek
Talk to Engineers
Use Mixpeek

Guide

API Reference

Use Cases

Studio

Health

GET
Healthcheck

Ingest

POST
Ingest Text
POST
Ingest Video Url
POST
Ingest Image Url

Features

POST
Search Features
GET
Get Feature
PUT
Full Feature Update
DEL
Delete Feature
POST
List Features

Collections

GET
List Collections
POST
Create Collection
PUT
Update collection
DEL
Delete collection

Namespaces

GET
List Namespaces
POST
Create Namespace
GET
Get namespace
PUT
Update namespace
DEL
Delete namespace
GET
List Available Indexes

Assets

GET
Get Asset
PUT
Full Asset Update
DEL
Delete Asset
PATCH
Partial Asset Update
GET
Get Asset With Features
POST
List Assets
POST
Search Assets

Collections

GET
List Collections
DEL
Delete collection

Tasks

GET
Get Task Information
DEL
Kill Task

Feature Extractors

POST
Extract Embeddings

Index text

POST

index

text

Authorization

string

Bearer

Authorization

Required

string

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Authorization

string

Authorization

string

Bearer token authentication using your API key. Format: 'Bearer your_api_key'. To get an API key, create an account at mixpeek.com/start and generate a key in your account settings. Example: 'Bearer sk_1234567890abcdef'

X-Namespace

string

X-Namespace

string

Optional namespace for data isolation. Example: 'netflix_prod' or 'spotify_recs_dev'. To create a namespace, use the /namespaces endpoint.

object

collection_id

string

collection_id

Required

string

Unique identifier for the collection where the processed asset will be stored.

Add Example Value

asset_update

object

asset_update

object

Asset update information for existing assets

asset_id

string

asset_id

Required

string

Unique identifier for the asset to be updated

mode

enum<string>

mode

Required

enum<string>

Update mode: 'replace' or 'append'

metadata

object

metadata

object

Additional metadata associated with the file. Can include any key-value pairs relevant to the file.

Add Example Value

feature_extractors

object

feature_extractors

object

Settings for text processing.

embed

array

embed

array

List of embedding settings for generating multiple embeddings. field_name's provided are how the raw text will be inserted, if not provided, the field_name will be auto-generated.

Add Example Value

json_output

object

json_output

object

Settings for structured JSON output of text analysis.

Add Example Value

response_shape

object

response_shape

object

prompt

string

prompt

string

percolate

object

percolate

object

Settings for percolating the asset against stored queries.

Add Example Value

enabled

boolean

enabled

boolean

Whether to enable percolator matching for this request

min_score

number

min_score

number

Minimum similarity score (0-1) required for a match. Higher values mean stricter matching.

max_candidates

integer

max_candidates

integer

Maximum number of matching percolators to return in the response

skip_duplicate

boolean

skip_duplicate

boolean

Skips processing when a duplicate hash is found and stores an error by the task_id with the existing asset_id

Headers

Authorization

string | null

X-Namespace

string | null

Optional namespace for data isolation. Example: 'netflix_prod' or 'spotify_recs_dev'. To create a namespace, use the /namespaces endpoint.

Body

application/json

collection_id

string

required

Unique identifier for the collection where the processed asset will be stored.

asset_update

object | null

Asset update information for existing assets

asset_update.asset_id

string

required

Unique identifier for the asset to be updated

asset_update.mode

enum<string>

required

Update mode: 'replace' or 'append'

Available options:

replace,

append

metadata

object

Additional metadata associated with the file. Can include any key-value pairs relevant to the file.

feature_extractors

object | null

Settings for text processing.

feature_extractors.embed

object[]

List of embedding settings for generating multiple embeddings. field_name's provided are how the raw text will be inserted, if not provided, the field_name will be auto-generated.

feature_extractors.embed.type

enum<string>

required

Type of input to embed

Available options:

url,

text,

file,

base64

feature_extractors.embed.value

string | null

The input content to embed. Could be a URL, text content, file path, or base64 encoded string

feature_extractors.embed.vector_index

enum<string>

required

Name of the vector index to use for embedding

Available options:

image,

multimodal,

text,

keyword

feature_extractors.embed.field_name

string | null

Field name to insert into the database, if not provided, the embedding will be inserted into the default field

feature_extractors.json_output

object | null

Settings for structured JSON output of text analysis.

feature_extractors.json_output.response_shape

object | null

feature_extractors.json_output.prompt

string | null

default: Interpret the provided text and structure it into the supplied JSON format.

percolate

object | null

Settings for percolating the asset against stored queries.

percolate.enabled

boolean

default: true

Whether to enable percolator matching for this request

percolate.min_score

number | null

default: 0.8

Minimum similarity score (0-1) required for a match. Higher values mean stricter matching.

percolate.max_candidates

integer | null

default: 10

Maximum number of matching percolators to return in the response

skip_duplicate

boolean | null

default: true

Skips processing when a duplicate hash is found and stores an error by the task_id with the existing asset_id

Response

200 - application/json

message

string

required

A message describing the status of the task

task_id

string

required

The unique identifier for the processing task

Was this page helpful?

website github