Maciej Skorski maciejskorski

Summary

The repo shows how to log run results in DBT with ClickHouse SQL.

The idea is to use on-run-end post-hook. The code logs detailed results data, including invocation arguments and timestamps.

⚠️ recall that ClickHouse does not support schemas, so re-work qualified paths when using JINJA

	import instructor
	from openai import OpenAI
	from anthropic import Anthropic
	from pydantic import BaseModel

	class UserInfo(BaseModel):
	field1: str
	field2: int

	# Initialize an AI client with various providers ....

	import anthropic
	from tqdm.asyncio import tqdm as tqdm_async

	async def analyze_with_claude(text: str, temperature=0.7):
	client=anthropic.AsyncAnthropic()
	output = await client.messages.create(
	model="claude-4-sonnet-20250514",
	max_tokens=200,
	temperature=temperature,
	system=prompt,

	# in bash; select the appropriate resource id and use the download api via wget
	osf_id=cwu4m
	wget --content-disposition "https://osf.io/$osf_id/download"