Quickstart

Authorization

Mixpeek

Homepage

Engineering Blog

Documentation

API Reference

Studio Walkthrough

Use Mixpeek

Talk to Engineers

Introduction

Key concepts for using a Multimodal Data Warehouse

Concepts

Get up and running with Mixpeek in minutes

Understanding Mixpeek core architecture and data flow

Architecture

Isolated environments for organizing and managing your Mixpeek resources

Namespaces

Store and organize raw multimodal data objects for processing

Buckets

Organize processed documents with consistent schemas for efficient retrieval

Collections

Understanding features and feature extraction in Mixpeek

Features

Automatically detect and split scenes by configuration

Scene Splitting

Generate embeddings from video content for semantic search

Video Embedding

Detect, extract, and identify faces in images and videos

Face Detection

Customize and fine-tune machine learning models for your specific use cases

Model Tuning

Monitor and manage processing tasks for tracking pipeline execution

Tasks

Configure and use retrieval pipelines for powerful multimodal search

Retrievers

Vector-based K-nearest neighbor search for semantic similarity

KNN Search

Combined vector and keyword search for optimal retrieval results

Hybrid Search

Generate content, summaries, or insights using large language models

LLM Generation

Improve search quality by reordering results with advanced relevance models

Reranking

Retrieve documents containing specific faces based on similarity matching

Face Search

Track and leverage user interactions to improve search relevance

Interactions

Research

Taxonomies

Clusters

Errors

Limits

Healthcheck

This endpoint allows you to create a new bucket with a defined schema.
    A bucket is a collection of objects that conform to the schema.
    The schema defines the structure and validation rules for objects in the bucket.

Create Bucket

This endpoint retrieves a bucket by its ID.

Get Bucket

This endpoint allows you to update an existing bucket.
    You can update the bucket's name, description, and metadata.

Update Bucket

This endpoint deletes a bucket and all its objects.

Delete Bucket

This endpoint lists buckets with pagination, sorting, and filtering options.

List Buckets

This endpoint creates a new object in the specified bucket.
    The object must conform to the bucket's schema.

Create Object

This endpoint retrieves an object by its ID from the specified bucket.

Get Object

This endpoint updates an existing object in the specified bucket.
    The updated object must conform to the bucket's schema.

Update Object

This endpoint deletes an object from the specified bucket.

Delete Object

This endpoint lists objects in a bucket with pagination, sorting, and filtering options.

List Objects

This endpoint allows you to create a new collection.

Create Collection

Get Collection

Get Document

Update Document

Delete Document

List documents with pagination and filtering.

List Documents

Batch Update Documents

Batch Delete Documents

List all available feature extractors grouped by category

List Feature Extractors

Create Retriever

Get Retriever

Execute Retriever

List all available retriever stages from the registry

List Retriever Stages

**Requirements:**
- Required permissions: write

Create Taxonomy

Create Cluster

List interactions with optional filters and pagination

**Requirements:**
- Required permissions: read

List Interactions

Record a search interaction (view, click, feedback, etc.)

**Requirements:**
- Required permissions: write

Create Interaction

Get a specific interaction

**Requirements:**
- Required permissions: read

Get Interaction

Delete a specific interaction

**Requirements:**
- Required permissions: write

Delete Interaction

List Namespaces

Creates a new namespace with the specified configuration

Create Namespace

Retrieve details of a specific namespace using either its name or ID

Get Namespace

Fully updates an existing namespace (all fields required)

Update Namespace

Deletes an existing namespace using either its name or ID

Delete Namespace

Retrieve a task by its ID.
    
    A task may have an expiration time, after which it will still be returned but marked as expired.
    This allows tracking of historical tasks while indicating their current validity state.

Get Task Information

Kill Task

Retrieve all tasks that are not in a complete state (DONE, FAILED, SKIPPED, or CANCELLED)

Pages