November 28: Support for entity resolution, agentic GraphRAG, user-scoped knowledge graphs

New Features

• 💡 Graphlit now supports LLM-based entity resolution via the resolveEntities mutation. You can provide a list of JSON-LD entities to the model, and it will return a resolved list with fields merged or new entities split out, helping to deduplicate and consolidate your knowledge graph.

• 💡 We have expanded our agentic GraphRAG capabilities by breaking out specific SDK calls for graph tools, allowing an agentic LLM to manipulate the knowledge graph directly rather than relying solely on graph strategy configuration.

• Graphlit now supports user-specific knowledge graphs. For multi-tenant applications, each user can have their own isolated knowledge graph rather than sharing a project-wide graph.

• We have added support for on-demand entity enrichment. You can now select entities and enrich them with external data sources like Diffbot, Crunchbase, or Parallel to fill in websites, addresses, funding information, and more.

• Observable entities now expose their feed property to the API, and you can filter entities by feed using the updated observable filter.

Bugs Fixed

• GPLA-4748: Fixed entity validation errors when upserting Organization entities

• GPLA-4743: Enrichment now correctly creates and assigns Founder relationships from JSON-LD

• GPLA-4725: graph query now returns inter-entity edges that were being ignored

• GPLA-4728: Deleting a CRM feed now recursively deletes entities sourced from it