Skip to main content

Twelve Labs

Bundles contain custom components that support specific third-party integrations with Orbis Studio.

This page describes the components that are available in the Twelve Labs bundle.

Twelve Labs is a video AI platform that indexes video content and enables semantic search, question answering, and embedding generation over video.

TwelveLabs Pegasus Index Video​

The TwelveLabs Pegasus Index Video component uploads and indexes a video using the Twelve Labs Pegasus model, making it searchable for downstream retrieval and QA tasks.

TwelveLabs Pegasus Index Video parameters​

Some parameters are hidden by default in the visual editor. You can modify all component parameters through the component inspection panel that appears when you select a component.

NameTypeDescription
api_keySecretStringInput parameter. Your Twelve Labs API key from api.twelvelabs.io.
index_idStringInput parameter. The ID of the Twelve Labs index to add the video to.
video_urlStringInput parameter. URL or file path of the video to index.

TwelveLabs Pegasus Index Video outputs​

NameTypeDescription
dataJSONOutput parameter. Indexing task result including the video ID.

TwelveLabs Text Embeddings​

The TwelveLabs Text Embeddings component generates text embeddings using Twelve Labs' multimodal embedding models. These embeddings are compatible with video embeddings generated by Twelve Labs, enabling cross-modal search.

TwelveLabs Text Embeddings parameters​

Some parameters are hidden by default in the visual editor. You can modify all component parameters through the component inspection panel that appears when you select a component.

NameTypeDescription
api_keySecretStringInput parameter. Your Twelve Labs API key. Value: TWELVELABS_​API_​KEY.
model_nameStringInput parameter. The Twelve Labs embedding model to use.

TwelveLabs Text Embeddings outputs​

NameTypeDescription
embeddingsEmbeddingsOutput parameter. Generated text embeddings compatible with Twelve Labs vector search.

See also​