somera / codebase_chat_cli_v1.3.py

Created April 5, 2025 15:15

Codebase Chat CLI - A command-line interface for interacting with codebases using local LLMs via Ollama.

	#!/usr/bin/env python3
	"""
	Codebase Chat CLI - GPU Accelerated

	A command-line interface for interacting with codebases using local LLMs via Ollama.
	Supports GPU acceleration for improved performance and ChromaDB for vector indexing.

	Features:
	- Vector index creation of source code files with ChromaDB and Ollama embeddings
	- .codechatignore support for excluding files/folders

somera / .env

Created April 5, 2025 15:13

Environment variables for codebase_chat_cli_v1.3.py

	# ollama
	OLLAMA_URL=http://localhost:11434
	OLLAMA_MODEL=phi4:14b
	OLLAMA_TEMPERATURE=0.2
	OLLAMA_NUM_CTX=16384
	OLLAMA_TOP_P=0.95
	OLLAMA_REPEAT_PENALTY=1.1

	# index
	INDEX_ROOT=~/.codechat/indexes

somera / sync-history.sh

Created October 19, 2024 08:12 — forked from jan-warchol/sync-history.sh

Synchronize history across bash sessions

	# Synchronize history between bash sessions
	#
	# Make history from other terminals available to the current one. However,
	# don't mix all histories together - make sure that all commands from the
	# current session are on top of its history, so that pressing up arrow will
	# give you most recent command from this session, not from any session.
	#
	# Since history is saved on each prompt, this additionally protects it from
	# terminal crashes.

somera / noVNCCopyPasteProxmox.user.js

Created September 25, 2023 18:21 — forked from amunchet/noVNCCopyPasteProxmox.user.js

Copy/Paste for noVNC Proxmox

	// ==UserScript==
	// @name noVNC Paste for Proxmox
	// @namespace http://tampermonkey.net/
	// @version 0.2a
	// @description Pastes text into a noVNC window (for use with Proxmox specifically)
	// @author Chester Enright
	// @match https://*
	// @include /^.novnc./
	// @require http://code.jquery.com/jquery-3.3.1.min.js
	// @grant none

somera / LLM.md

Created July 2, 2023 17:16 — forked from rain-1/LLM.md

LLM Introduction: Learn Language Models

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Prelude

Neural network links before starting with transformers.

somera / generate-certificate-chain.sh

Created May 27, 2023 18:02 — forked from granella/generate-certificate-chain.sh

Create self-signed certificate with root and ca for development

	#!/bin/bash

	rm *.jks 2> /dev/null
	rm *.pem 2> /dev/null

	echo "===================================================="
	echo "Creating fake third-party chain root -> ca"
	echo "===================================================="

	# generate private keys (for root and ca)

somera / latency.txt

Created April 15, 2023 20:35 — forked from jboner/latency.txt

Latency Numbers Every Programmer Should Know

	Latency Comparison Numbers (~2012)
	----------------------------------
	L1 cache reference 0.5 ns
	Branch mispredict 5 ns
	L2 cache reference 7 ns 14x L1 cache
	Mutex lock/unlock 25 ns
	Main memory reference 100 ns 20x L2 cache, 200x L1 cache
	Compress 1K bytes with Zippy 3,000 ns 3 us
	Send 1K bytes over 1 Gbps network 10,000 ns 10 us
	Read 4K randomly from SSD* 150,000 ns 150 us ~1GB/sec SSD

somera / latency.markdown

Created April 15, 2023 20:34 — forked from hellerbarde/latency.markdown

Latency numbers every programmer should know

L1 cache reference ......................... 0.5 ns
Branch mispredict ............................ 5 ns
L2 cache reference ........................... 7 ns
Mutex lock/unlock ........................... 25 ns
Main memory reference ...................... 100 ns             
Compress 1K bytes with Zippy ............. 3,000 ns  =   3 µs
Send 2K bytes over 1 Gbps network ....... 20,000 ns  =  20 µs
SSD random read ........................ 150,000 ns  = 150 µs

Read 1 MB sequentially from memory ..... 250,000 ns = 250 µs

somera / convert_to_safe.py

Created March 10, 2023 18:21 — forked from zer0TF/convert_to_safe.py

Convert all CKPT files to SAFETENSOR files in a directory

	# Got a bunch of .ckpt files to convert?
	# Here's a handy script to take care of all that for you!
	# Original .ckpt files are not touched!
	# Make sure you have enough disk space! You are going to DOUBLE the size of your models folder!
	#
	# First, run:
	# pip install torch torchsde==0.2.5 safetensors==0.2.5
	#
	# Place this file in the SAME DIRECTORY as all of your .ckpt files, open a command prompt for that folder, and run:
	# python convert_to_safe.py

somera / enable-all-advanced-power-settings.ps1

Created November 16, 2022 16:12 — forked from raspi/enable-all-advanced-power-settings.ps1

Enable all advanced power settings in Windows.

	# List all possible power config GUIDs in Windows
	# Run: this-script.ps1 \| Out-File powercfg.ps1
	# Then edit and run powercfg.ps1
	# (c) Pekka "raspi" Järvinen 2017

	$powerSettingTable = Get-WmiObject -Namespace root\cimv2\power -Class Win32_PowerSetting
	$powerSettingInSubgroubTable = Get-WmiObject -Namespace root\cimv2\power -Class Win32_PowerSettingInSubgroup

	Get-WmiObject -Namespace root\cimv2\power -Class Win32_PowerSettingCapabilities \| ForEach-Object {
	$tmp = $_.ManagedElement