jamiekt’s gists

jamiekt / data_processing.py

Created July 13, 2025 21:44

Building an offline personal RAG AI

	import os
	import time
	from langchain_community.document_loaders import DirectoryLoader, TextLoader
	from langchain.text_splitter import RecursiveCharacterTextSplitter
	from langchain_ollama import OllamaEmbeddings
	from langchain_chroma import Chroma

	OLLAMA_BASE_URL = "http://host.docker.internal:11434"
	EMBEDDING_MODEL_NAME = "nomic-embed-text"

jamiekt / log.txt

Created November 28, 2024 15:39

tf_log trace output for terraform 1.10 failure

This file has been truncated, but you can view the full file.

	2024-11-28T15:33:20.601Z [DEBUG] using github.com/hashicorp/go-tfe v1.70.0
	2024-11-28T15:33:20.601Z [DEBUG] using github.com/hashicorp/hcl/v2 v2.23.0
	2024-11-28T15:33:20.601Z [DEBUG] using github.com/hashicorp/terraform-svchost v0.1.1
	2024-11-28T15:33:20.601Z [DEBUG] using github.com/zclconf/go-cty v1.15.1-0.20241111215639-63279be090d7
	2024-11-28T15:33:20.601Z [INFO] Go runtime version: go1.23.3
	2024-11-28T15:33:20.601Z [INFO] CLI args: []string{"/runner/_work/_temp/8d1518ff-a289-4de6-95a1-45d05ad67232/terraform-bin", "validate"}
	2024-11-28T15:33:20.601Z [TRACE] Stdout is not a terminal
	2024-11-28T15:33:20.601Z [TRACE] Stderr is not a terminal
	2024-11-28T15:33:20.601Z [TRACE] Stdin is not a terminal
	2024-11-28T15:33:20.601Z [DEBUG] Attempting to open CLI config file: /home/runner/.terraformrc

jamiekt / demo_xcom_problem.py

Created April 14, 2024 20:30

Airflow XCom problem - solved

	import datetime
	from typing import Sequence
	from airflow.decorators import task, dag

	from airflow.providers.amazon.aws.operators.emr import EmrServerlessCreateApplicationOperator

	class JamietEmrServerlessCreateApplicationOperator(EmrServerlessCreateApplicationOperator):
	template_fields: Sequence[str] = ["config"]

	def __init__(self, **kwargs) -> None:

jamiekt / demo_xcom_problem.py

Last active April 14, 2024 20:29

Airflow XCom problem

	import datetime
	from airflow.decorators import task, dag

	from airflow.providers.amazon.aws.operators.emr import EmrServerlessCreateApplicationOperator

	@dag(
	dag_id="demo-xcom-problem",
	start_date=datetime.datetime(2021, 1, 1),
	catchup=False
	)

jamiekt / query.sql

Last active October 22, 2022 16:41

ARRAY() with SELECT AS STRUCT

	SELECT c.borough,c.year,
	ARRAY(
	select as struct c2.month,sum(value) crime_tally
	from `bigquery-public-data.london_crime.crime_by_lsoa` as c2
	where c.borough = c2.borough
	and c.year = c2.year
	group by c2.month
	) as monthly_summary
	FROM (
	select distinct borough,year

jamiekt / satisfy_mypy_with_walrus_operator.py

Last active July 22, 2022 13:16

	return {
	match.group(0)
	for matched_policy in matched_policies
	if (match := re.search(r"p\d{6}", matched_policy)) is not None
	}

jamiekt / satisfy_mypy_with_loop.py

Created July 22, 2022 13:12

	prefixes = set()
	for matched_policy in matched_policies:
	search_result = re.search(r_search, matched_policy)
	assert search_result is not None
	prefixes.add(search_result.group(0))
	return prefixes

jamiekt / mypymoan.py

Last active July 22, 2022 13:11

	import re
	matched_policies = {...} #some logic to derive a set
	return {
	re.search(r"p\d{6}", matched_policy).group(0)
	for matched_policy in matched_policies
	}

jamiekt / pyproject.toml

Created June 15, 2022 21:04

	[tool.poetry]
	name = "real-time-event-processor"
	version = "0.1.0"
	description = ""
	authors = []

	[tool.poetry.dependencies]
	python = "^3.9, <3.10"

	Flask = "^2.0.1"

jamiekt / poetry-env-info-3_8

Created June 15, 2022 21:02

Jamie Thomson jamiekt