momentbench
Find the right moment across a video collection, or say nothing matches. 27 licensed videos, 456 published queries, an agentic and a prediction-file track, and a validated leaderboard.
- 2
- Python
- Apache-2.0
- 3 d ago
Find the right moment across a video collection, or say nothing matches. 27 licensed videos, 456 published queries, an agentic and a prediction-file track, and a validated leaderboard.
Python SDK for Mixpeek, the multimodal warehouse for AI: index and search video, images, audio and documents.
Multimodal extractors for video, image, audio, text & PDF — turn any file into searchable vector embeddings (SigLIP, Gemini, E5, CLAP, ArcFace).
A lightweight, production-friendly Model Context Protocol (MCP) server for Mixpeek
LangChain integration for Mixpeek: a multimodal retriever and tool for AI agents over video, images, audio and documents.
Authorized multimodal retrieval: Mixpeek + OpenFGA (ReBAC permission-aware image search), runnable end-to-end
Migrate vectors from any major vector database to Mixpeek MVS - supports 13 sources with batch transfer, validation, and cost comparison