Integrations

Sync videos from Mux into Mixpeek for automatic multimodal extraction: scene understanding, object detection, face identity, OCR, and transcription. Build visual search retrievers that let users find the exact frame, scene, or spoken word across your entire video library.

• 95% Less manual review
• 0 Manual indexing steps
• 40-60% Lower processing costs

Connect Backblaze B2 buckets to Mixpeek for automatic multimodal extraction at a fraction of AWS S3 prices. Store your videos, images, and documents in B2, run feature extractors and embeddings through Mixpeek, and write indexed results back to B2: with zero egress fees through Bandwidth Alliance partners.

• 75% Lower storage costs
• $0 Egress fees
• 0 Code changes required

Connect Iconik to Mixpeek and every asset in your DAM becomes searchable by what's inside it: scenes, faces, objects, spoken words, and on-screen text. Sync runs continuously in the background. New uploads are indexed automatically. Deleted assets are cleaned up. No manual tagging, no maintenance.

• Find the exact shot without scrubbing
• Verify talent and brand usage across libraries
• Unlock assets that were buried and forgotten

Generate embeddings with 50+ open-source models hosted on Together AI (BGE, Llama, Mistral, and more) then upsert directly to MVS. No GPUs to manage. Swap models by changing one parameter. Go from text to searchable vectors in three API calls.

• $0 GPU infrastructure cost
• 50+ Open-source models available
• <5 min Time to first search

Sub-10ms embedding generation on Fireworks AI's optimized infrastructure, paired with MVS's sub-50ms vector search. The full query path (embed, search, return ranked results) completes in under 100ms. Serverless scaling from zero to burst, pay-per-use.

• <10ms Embedding latency
• <100ms End-to-end query time
• 0 Cold starts

Generate embeddings inside your AWS account via Bedrock: Amazon Titan, Cohere Embed, or any supported model. IAM controls access, VPC endpoints keep traffic private, CloudTrail logs every call. MVS adds vector storage, indexing, and retrieval on top.

• 100% AWS-native security
• SOC2/HIPAA Compliance ready
• 3+ Embedding providers

A Real-Time Data (RTD) module for Prebid.js that replaces cookie-based targeting with contextual signals, served from a cache so the auction waits only up to the auctionDelay you set. Enables multimodal content understanding for ad targeting without user tracking.

A local processing tool that migrates content categorization from IAB 2.x to IAB Content Taxonomy 3.1 IDs. Every 3.0 ID is also a 3.1 ID. Converts existing taxonomy labels into OpenRTB and VAST-ready category IDs, with cattax 9 for 3.1, and optional semantic enrichment using embeddings and LLM re-ranking.

The langchain-mixpeek package gives LangChain agents the ability to see video, hear audio, search images, and act on unstructured content. Includes a 6-tool agent toolkit (search, ingest, process, classify, cluster, alert), VectorStore with support for all file types, and bridge methods to convert between retrievers, tools, and toolkits.

Add multimodal content intelligence to your Strapi CMS with this plugin. It hooks into Strapi's lifecycle events to automatically process content through Mixpeek, enriching entries with taxonomy labels, embeddings, and structured metadata as content is created and updated.

A zero-dependency connector that extracts text from FHIR R4 clinical resources and enriches them with Mixpeek's multimodal AI. Supports Patient, Observation, Condition, DocumentReference, DiagnosticReport, Encounter, and MedicationRequest resources with automatic fallback to narrative text for all other types. Returns enrichment as FHIR-compatible extensions and meta tags.

A React component library for building multimodal search experiences. Drop in the full SearchKit widget or compose individual pieces, stages streaming, AI answers, filters, and theming included. Connects to any published Mixpeek retriever.