hrishioa

DO NOT ANSWER THE QUESTION DIRECTLY, INSTEAD FOLLOW THE STEPS BELOW. You are an expert in outputting JSON and transforming questions and documents, and you can only respond in pieces of valid JSON.

Follow these steps to respond to the user:
1. If they haven't uploaded a document (or specified a piece of context to extract information from), ask them to do so. Don't proceed until you have it.
2. Once you have a document, make sure you have a question or query from the user. If don't, ask for it. Don't proceed to step 3 until you have a document (or corpus) and a question.
3. Once you have both, transform the question and output JSON in this typespec:
```typescript
type QuestionTransformations = {
     potentialAnswers: string[]; // Make up creative hypothetical answers that could answer this question. Need not be real, or grounded in truth.
     potentialFacts: string[]; // Make up some facts that could be important to answering this question.

hrishioa

AI Object to DB

Claude-2

All the key information in this file was generated by an LLM. Treat it as a starting point, don't ever run auto-generated code without a sandbox unless you have checked it yourself.

The primary intent for this analysis is to go from an object to all the tools you need to use this library. The hardest part is the object-to-relational conversion, of converting a (potentially) nested json into flat tables that can be queried.

We will generate the following things:

1. A typespec - We need good type definition for our incoming object. You might already have this, in which case make sure to provide a string version to the function to treat this as a starting point.

hrishioa

// Hrishi Olickel, 14 Aug 2023.
// Simple example and prompt template for context decomposition, described here:
// https://twitter.com/hrishioa/status/1690453115471040512

const applyContextDecomp = {
  systemPrompt: (documentPurpose: string, documentContent: string) => `You are converting a document into a simpler, intermediate step that can be used by someone else to derive an answer.

DOCUMENT_PURPOSE:
"""
${documentPurpose}

hrishioa

// Hrishi Olickel
// https://olickel.com
// 25 July 2023

const fs = require('fs');
const readline = require('readline');

const speakers = {}; // Hold start time and speaker
const speakerNames = ['Hrishi', 'Nick']; // Speaker names array

hrishioa

type Role = 'system' | 'user' | 'assistant';

interface Message {
  role: Role;
  content: string;
}

type Messages = Array<Message>;

const B_INST = '[INST]';

hrishioa

// Proquint implementation based on https://arxiv.org/html/0901.4016

const uint2consonant: string[] = [
  'b',
  'd',
  'f',
  'g',
  'h',
  'j',
  'k',

hrishioa

// Meant to work with the code in https://github.com/hrishioa/socrate, specifically the functions in the `gpt/base.ts`.
// Created by Hrishi Olickel (@hrishioa) Sub 7 May

import { Messages, askChatGPT } from '../base';

async function generateRegexFromTypeSpec(typeSpec: string): Promise<string | null> {
  //prettier-ignore
  const prompts = {
    systemPrompt: () => `You are a Typescript type to Regex converter that can only output valid Regexes.`,
    specPrompt: (spec: string) => `Convert the following TYPESCRIPT_TYPE into a valid Regex that matches the type.

hrishioa

// Requires the gpt library from https://github.com/hrishioa/socrate and the progress bar library.
// Created by Hrishi Olickel (hrishioa@gmail.com) (@hrishioa). Reach out if you have trouble running this.

import { ThunkQueue } from '../../utils/simplethrottler';
import {
  AcceptedModels,
  Messages,
  askChatGPT,
  getMessagesTokenCount,
  getProperJSONFromGPT,

hrishioa

import { getAllPosts, getCondensedPost, getFileNameFromSlug } from "./mdx";
import { Corpus, Similarity } from 'tiny-tfidf';

const fs = require('fs');

const relatedPostsFile = './public/relatedMatrix.json';

export type FrontMatter = {
  title: string;
  layout: string;

hrishioa

/**
 *
 * Task: Implement typeahead, suggestions and command search for cats using https://cataas.com/#/.
 *
 * Subtask 1: Implement a search box for users to search for cats by a tag, using `/cat/:tag`. Results should show the picture of the cat
 * and the description. Example search `angry` -> API call would be https://cataas.com/cat/angry -> Picture of angry cat
 *
 * Subtask 2: Implement typeahead and suggestions for past searches (can be extended to common words from https://www.wordsapi.com/)
 *
 * Subtask 3: Implement command search, where users can type in `{cat type} says Hello`, and the returned picture uses this to call `/cat/:tag/says/:text`.