maxim-saplin

Install on WSL2

1. Installed Ubuntu-24.04 from the Mircosot Store -> Types WSL and Selected the most recent Ubuntu

2. Windows Terminal -> wsl -d Ubuntu-24.04 (using -d to specify distro name, I have multiple distros)

3. Installing SGLang

Copying and pasting from docs (https://docs.sglang.ai/start/install.html) didn't quite work.

maxim-saplin

Proxy (to Player_Black):

You are a professional chess player and you play as black. Now is your turn to make a move. Before making a move you can pick one of the following actions:
- 'get_current_board' to get the schema and current status of the board
- 'get_legal_moves' to get a UCI formatted list of available moves
- 'make_move <UCI formatted move>' when you are ready to complete your turn (e.g., 'make_move e2e4')

--------------------------------------------------------------------------------
Player_Black (to Proxy):

maxim-saplin

Proxy (to Random_Player):

You are a random chess player.

--------------------------------------------------------------------------------
Random_Player (to Proxy):

get_legal_moves

--------------------------------------------------------------------------------

maxim-saplin

You are an AI assistant designed to provide detailed, step-by-step responses. Your outputs should follow this structure:

1. Begin with a <thinking> section.
2. Inside the thinking section:
   a. Briefly analyze the question and outline your approach.
   b. Present a clear plan of steps to solve the problem.
   c. Use a "Chain of Thought" reasoning process if necessary, breaking down your thought process into numbered steps.
3. Include a <reflection> section for each idea where you:
   a. Review your reasoning.
   b. Check for potential errors or oversights.

maxim-saplin

# pip install -U git+https://github.com/huggingface/transformers.git

from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
import torch
import time


def chat_with_ai(model, tokenizer):
    """
    Function to simulate chatting with the AI model via the command line.

maxim-saplin

def is_special_number(number):
    if number == 7:
        return True
    elif number == 18:
        return True
    else:
        return False

def is_special_number_2 (number):
    return number in [7, 18]

maxim-saplin

// sealed classes are abstract (can't be instatiated) and can only be
// implemented in the same library (library in Dart is one file be default)
sealed class Message {
}

class TextMessage implements Message {
  final String content;
  TextMessage(this.content);
}

maxim-saplin

# https://matplotlib.org/matplotblog/posts/animated-fractals/
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.animation as animation
import time

x_start, y_start = -2, -2  # an interesting region starts here
width, height = 4, 4  # for 4 units up and right
density_per_unit = 80  # how many pixles per unit

maxim-saplin

import 'dart:math';
import 'dart:ui';

import 'package:app/grpc_generated/client.dart';
import 'package:app/grpc_generated/init_py.dart';
import 'package:app/grpc_generated/init_py_native.dart';
import 'package:app/grpc_generated/service.pbgrpc.dart';
import 'package:flutter/material.dart';

Future<void> pyInitResult = Future(() => null);

maxim-saplin

import dotenv from "dotenv";

const API_KEY = process.env.API_KEY;
const API_ENDPOINT = process.env.API_ENDPOINT; // ?api-version=2023-07-01-preview is required as of August 2023

const validate = async (name: string, project: string, role: string, category: string, feedback: string, summary: string): Promise<{ status: string, recommendations: string }> => {
    var nominee = generateNomineeString(name, project, role, category, feedback, summary);

    // Using function call capability of OpenAI API to ensure response is properly formatted JSON
    // Before function calling I asked to reply via JSON, one of side effect was that in 'recomendations'