Who should use the Knowledge Graph workflow?
Teams or solo builders working on data tasks who want a repeatable process instead of one-off tool experiments.
Execution Map
4-step pipeline — follow each step in order
1Setup · Step 1 of 4
Open task pageVector Search
Use Vector Search to find and retrieve relevant data sources and context needed to seed the knowledge graph construction process.
Why this matters
Vector Search sets up the foundation for knowledge graph; clean inputs here reduce downstream rework.
What you get
Inputs, context, and settings are ready so the workflow can move into execution without blockers.
More options
2Core · Step 2 of 4
Open task pageKnowledge Graph
Run the knowledge graph generation algorithm on the prepared data to produce a structured graph of entities and their connections.
Why this matters
This is the core step where knowledge graph actually happens, so it determines baseline quality for everything after it.
What you get
A first-pass final deliverable is generated and ready for refinement in the next steps.
More optionsCompare
3Refine · Step 3 of 4
Open task pageMultimodal Data Management
Refine and validate the knowledge graph output by managing multimodal data, ensuring accuracy and completeness before final delivery.
Why this matters
Multimodal Data Management adds quality control so issues are caught before the workflow is finalized.
What you get
The final deliverable is improved, validated, and prepared for final delivery.
4Deliver · Step 4 of 4
Open task pageVector Database
Package and export the finalized knowledge graph into a vector database for efficient querying and integration with downstream applications.
Why this matters
Vector Database is what turns intermediate output into a usable, publishable result for real users.
What you get
A finalized final deliverable is ready for publishing, handoff, or integration.