Dbt Ce Ai Functions
dbt-labs/dbt-context-engineering/skills/dbt-ce-ai-functions
ai-mlResmi
Resmi Sağlayıcı Skill'iView repo
Use the row-level AI functions from the dbt_context_engineering package in a consuming dbt project: generate (free-form/structured text), classify (single label from a taxonomy), extract (typed structured records), and ai_agg (group-level LLM aggregation), plus authoring the versioned prompt and schema macros they require in your own project and reading structured output back with text() and field(). Use whenever a user wants an LLM to run over their rows in dbt: 'classify each ticket by priorit
Dosyalar3 dosya
SKILL.md148 satır
Loading editor…
Kurulum
ÖnerilenTek komut — ajanınız otomatik olarak devreye alır.
Kurulum komutunu görmek için yukarıdan bir AI aracı seçin.
veya
Manuel Kurulum
Daha fazla adımArşivi indirin ve dosyaları projenize manuel olarak ekleyin.
Skill detayları
Versiyonv1.0.0
Yazardbt Labs
Kategoriai-ml
Skill IDdbt-labs/dbt-context-engineering/skills/dbt-ce-ai-functions
Dosyalar3 dosya
İlgili skill'ler
Dbt Ce PipelineBuild a retrieval / semantic-search pipeline in a dbt project using the dbt_context_engineering package — chunk, attach metadata, embed, vector search, knowledge base — and make it production-grade (cost guards, run log, incremental re-embed, groundedness/eval tests). Use whenever a user wants to turn a text corpus (transcripts, docs, tickets, emails) into searchable context: semantic search, RAG context tables, retrieval over embeddings, a knowledge base, chunking text for an LLM, embedding a cDbt Ce SetupInstall and configure the dbt_context_engineering package in a consuming dbt project: packages.yml/dbt deps, the per-adapter var configuration everything depends on (embedding_model, model_generate/classify/extract, the ai_functions_enabled safety gate, cost ceilings, output caps), and per-engine prerequisites for Snowflake (Cortex), Databricks (serverless/DBR), and BigQuery (Vertex connection, Gemini thinking budget). Use whenever a user is setting up or configuring the package: 'how do I instaAdding Dbt Unit TestCreates unit test YAML definitions that mock upstream model inputs and validate expected outputs. Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt.Building Dbt Semantic LayerUse when creating or modifying dbt Semantic Layer components — semantic models, metrics, dimensions, entities, measures, or time spines. Covers MetricFlow configuration, metric types (simple, derived, cumulative, ratio, conversion), and validation for both latest and legacy YAML specs.Configuring Dbt Mcp ServerGenerates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt. Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.Maintaining Dbt DocumentationAudits dbt documentation coverage and drafts missing model/column descriptions in the project's own house style, one folder at a time, for human review. Use when documenting undocumented models, backfilling missing YAML descriptions, auditing doc coverage, or keeping schema YAML in sync with model SQL — especially on multi-contributor projects where new models routinely land undocumented.