Capabilities
The Column-Level Lineage Tool exposes a single underlying operation: get_column_level_lineage fetches the full lineage graph for a specific model and column combination. It returns a JSON structure of nodes and edges, each carrying the file path, model name, column name, and upstream or downstream direction. Requests time out after 60 seconds.Using the Column-Level Lineage Tool
- Open DinoAI in the right panel of the Code IDE
- Provide the model name and column you want to trace
- Add your prompt describing what you want DinoAI to do with the lineage results
- Review DinoAI’s findings and apply them to your development work
Example Use Cases
Tracing a Column’s Upstream Sources PromptWorking with Other Tools
The Column-Level Lineage Tool works well alongside DinoAI’s other capabilities to support your full development workflow:- Combine with the Catalog Search Tool to first discover the right model or column, then trace its lineage
- Combine with the SQL Execution Tool to validate query logic against columns you’ve traced through lineage
- Combine with the Google Docs Tool or Notion Tool to cross-reference lineage findings against your data modeling specs
- Use alongside Git Lite to commit and push lineage-informed changes before opening a pull request
Best Practices
Be specific with model and column names — Provide the exact model name and column name to ensure DinoAI retrieves the correct lineage graph. Account for refresh cadence — Lineage data reflects the latestmanifest.json and catalog.json, so very recent changes may not yet appear.
Verify complex graphs — For models with many upstream dependencies, review DinoAI’s lineage summary carefully before making structural changes.