Why

Several vendors are looking into this space already, sometimes in relation to extended (vector based) search capabilities, sometimes in relation to more general large language model features like summarization or knowledge graph generation from unstructured text.

Previous work

• Franz (RDF) https://franz.com/agraph/support/documentation/current/neuro-symbolic-llm-intro.html , for vector indexing with LLMs see https://franz.com/agraph/support/documentation/current/llm.html
• Neptune (property graph part) https://docs.aws.amazon.com/neptune-analytics/latest/userguide/vector-index.html
• neo4j (property graphs) https://github.com/neo4j/NaLLM?tab=readme-ov-file
• Related discussions in Standardize free text search of RDF data #40 and Support for Vectors and Matrices #163

See also https://www.biorxiv.org/content/10.1101/463778v1.full.pdf .

Proposed solution

Nothing concrete yet, currently gathering related work.

Considerations for backward compatibility

Too early to discuss.