kfsone

kfsone

kfsone

Write a rust program that takes counts the number of non-whitespace characters outside of c++ style comments in files. Count stdin unless file name arguments are supplied. Output only the total count, unless "--verbose" or "-v" is specified as an argument, in which case list the count per file, followed by the total.

Run with no arguments, and 0 characters: output = "0"
Run with "-v", 0 files, 0 characters: output = "<stdin>: 0"
Run with 0-byte files file1, file2, file3: output = "0"
Run with 0-byte files file1, file2, file3, and "-v": output = "file1: 0
file2: 0
file3: 0\*total: 
"

kfsone

building_task = """
Generate a set of agents to design, develop, document and test a complete rust program minus version control.

Ensure there is an agent who writes any generated command/configuration/scripts to disk, and a separate, dedicated executor agent who runs commands via docker, so that the agents cannot simply pretend to be writing code.
"""
agent_list, agent_configs = builder.build(building_task, llm_config)

kfsone

import autogen
from textwrap import dedent
import os

try:
    del os.environ['OPENAI_API_BASE']
except:
    pass

os.putenv("OPENAI_API_BASE", "http://localhost:5000")

kfsone

(venv) root@b7e76e6d82d8:/workspace# echo $OPENAI_API_BASE
http://localhost:11434/
(venv) root@b7e76e6d82d8:/workspace# litellm --test --port ${LITELLM_PORT}

LiteLLM: Making a test ChatCompletions request to your proxy
An error occurred: OpenAIException - Error code: 401 - {'error': {'message': 'Incorrect API key provided: none. You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}

 Debug this by setting `--debug`, e.g. `litellm --model gpt-3.5-turbo --debug`
INFO:     127.0.0.1:35604 - "POST /chat/completions HTTP/1.1" 200 OK

kfsone

# Work in progress. V0.1
# ALL THE THINGS.
ARG     APT_PROXY         #=http://apt-cacher-ng.lan:3142/
ARG     PIP_INDEX_URL     #=http://devpi.lan:3141/root/pypi/+simple
ARG     PIP_TRUSTED_HOST  #=devpi.lan
ARG     JUPYTER_PORT=37799
ARG     LITELLM_PORT=11111

FROM    nvidia/cuda:11.8.0-devel-ubuntu22.04 as build-llama

kfsone

# Credit: AutoGPT using OpenAI gpt4
import argparse
import json
import os
import random
import shutil
from pathlib import Path
from random import randint

kfsone

<#
.Synopsis
CMake-Build produces reproducible builds of wxWidgets binaries.
.Description
The CMake-Build script can fetch latest or a specific hash of the
wxWidgets library source from the official github, or it can use
an existing local source directory.

It will configure it for Nuo use, build the binaries, and then
install them in-tree to your Nuo checkout.

kfsone

from __future__ import annotations

from typing import List, Optional

from rich.console import Console, ConsoleOptions, RenderableType
from rich.live import Live
from rich.spinner import Spinner
from rich.table import Table
from rich.text import Text