Run LLM functions inside Spark SQL on AIDP via ai_generate(). Use when the user wants to summarize/classify/extract/enrich rows with an LLM directly in SQL, generate narratives over aggregated results, or do grounded RAG-style analysis in the lakehouse. Signature is model-first; available models must be confirmed live before relying on it.
Install
npx skills add oracle-samples/oracle-aidp-samples --skill aidp-ai-sqlnpx skills add oracle-samples/oracle-aidp-samples --skill aidp-ai-sql -a claude-code -gnpx skills add oracle-samples/oracle-aidp-samples --skill aidp-ai-sql -a codex -ggemini skills install https://github.com/oracle-samples/oracle-aidp-samples.git --path ai/claude-code-plugins/oracle-ai-data-platform-workbench-engineer-agent/skills/aidp-ai-sqlgh skill install oracle-samples/oracle-aidp-samples aidp-ai-sqlgit clone --depth 1 https://github.com/oracle-samples/oracle-aidp-samples /tmp/oracle-samples__oracle-aidp-samples
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/oracle-samples__oracle-aidp-samples/ai/claude-code-plugins/oracle-ai-data-platform-workbench-engineer-agent/skills/aidp-ai-sql ~/.claude/skills/aidp-ai-sql # Claude Code
cp -R /tmp/oracle-samples__oracle-aidp-samples/ai/claude-code-plugins/oracle-ai-data-platform-workbench-engineer-agent/skills/aidp-ai-sql ~/.agents/skills/aidp-ai-sql # Codex, Cursor, Gemini CLI, Copilot, OpenCode