Multi-Modal Knowledge Graphs for Agents
KGC 2026
•
28m
Most multimodal RAG stacks have a “split-brain” design: embeddings in a vector DB, relationships in a graph DB, and images/video/audio in blob storage. For an agent, that becomes a slow three-hop loop—similarity search, graph traversal, then a network fetch to load the actual frames for a VLM. This talk proposes a Lance-native Multi-Modal Knowledge Graph (MMKG) on lance-context + lance-graph, unifying media bytes, embeddings, and graph topology in one columnar dataset. Nodes become first-class media objects (images, clips, audio segments) stored directly in Lance, enabling zero-copy retrieval during traversal and faster “watch and reason” agents.
We’ll outline a high-level schema: MediaNodes for rich payloads with embeddings, timestamps, and structured metadata; TemporalEdges for explicit ordering (frames/scenes/clips) to support playback and “flashback” queries; and SemanticEdges linking media to entities and concepts. This design enables hybrid retrieval that combines graph constraints with multimodal similarity (e.g., “CEO smiling”), temporal window reasoning (“what happened in the 5 seconds before?”), and other agent workflows. We’ll close with a roadmap of our lance-graph open source project: ingestion utilities and a small set of multimodal graph primitives, and we welcome the graph community to join in the effort!
Up Next in KGC 2026
-
How Graph Technology Reveals the Real...
https://drive.google.com/file/d/16JcyI8agX69uv4bGb_oV1LCuR-tzSmhZ/view?usp=share_link
Behind every public market lies an invisible network of investors, investees, and shared board seats — relationships. This talk shares how we combined Amazon Neptune's graph database capabilities with Linkuriou...
-
The Future of Accounting is Data-Centric
https://drive.google.com/file/d/1ppJ1SP6ISzKVa_Vu5K1BNVPfC4yQZxYZ/view?usp=share_link
Accounting is a last remaining hurdle enterprises face on their journeys to become fully data-centric. Instead of relying on centuries-old artifacts such as journals, ledgers, debits and credits, Data-Centric A...
-
Evaluating the Adequacy of Competency...
https://drive.google.com/file/d/1dXvbNAZw9mdxcL74IRM705kESz4f-xpL/view?usp=share_link
We present an extensible framework specifically designed for the Competency Question-to-Ontology generation, which evaluates a growing set of models from major providers on their ability to generate formal onto...
