louis030195

const createJob = async (image) => {
    const url = 'https://api.hume.ai/v0/batch/jobs';
    const formData = new FormData();
    formData.append('file', image);

    const response = await fetch(url, {
        method: 'POST',
        headers: {
            'X-Hume-Api-Key': process.env.HUME_API_KEY,
            'Accept': 'application/json',

louis030195

SELECT 
    (COUNT(DISTINCT CASE 
        WHEN (raw_session_replay_events.click_count = 0 AND raw_session_replay_events.active_milliseconds < 60000) 
        THEN raw_session_replay_events.session_id 
        ELSE NULL 
    END) * 100.0) / COUNT(DISTINCT properties.$session_id) AS bounce_rate
FROM 
    events
INNER JOIN 
    raw_session_replay_events ON events.properties.$session_id = raw_session_replay_events.session_id

louis030195

import data
import torch
from models import imagebind_model
from models.imagebind_model import ModalityType
import uvicorn
from fastapi import FastAPI
import requests


device = "cuda:0" if torch.cuda.is_available() else "cpu"

louis030195

import Bundlr from "@bundlr-network/client";
import fs from "fs";
import Arweave from "arweave";
import { Neurosity } from "@neurosity/sdk";
const jwk = JSON.parse(fs.readFileSync("wallet.json").toString());

const neurosity = new Neurosity();

neurosity.login({
  email: process.env.NEUROSITY_EMAIL!,

louis030195

from websockets import connect
import json
import numpy as np
from sklearn.decomposition import IncrementalPCA as PCA
import streamlit as st
import plotly.graph_objects as go

# Create initial figure
fig = go.Figure()

louis030195

Today, I bring to you a thought-provoking concept: the amalgamation of technology and psychology, or more specifically, the application of System 1 and System 2 LLMs in AI programming. This idea was born from two main observations I made.

Firstly, there is the revolutionary technology of "embeddings" that has seen its usage skyrocket since 2022. It allows us to create a programmable memory for AI, thus eliminating the need to grapple with prompt engineering. I began to ponder if there could be a more efficient alternative to embeddings, one that utilizes fast and economical LLMs.

Secondly, the theory of System 1 and System 2 in psychology, which speaks about two different decision-making processes in our brain, caught my attention. System 1 corresponds to our intuitive, automatic, often subconscious thought process, like recognizing facial expressions. On the other hand, System 2 is deliberate, slower, and more logical, like solving complex math problems.

Inspired by this theory, I began to explore the po

louis030195

const { exec } = require('child_process');
const recursive = require("recursive-readdir");
const { Configuration, OpenAIApi } = require("openai");
const readline = require('readline');
const fs = require('fs');
const path = require('path');


async function listModels() {
    const response = await fetch("https://api.airtable.com/v0/appwJMZ6IAUnKpSwV/all", {

louis030195

Motley is a marketplace to help developers access open-source LLMs

Hosting

We will use the amazing FastChat python library to host LLMs.

pip install fschat

louis030195

const { Configuration, OpenAIApi } = require("openai");


/**
 * Lists all models available on the platform.
 * @async
 * @returns {Promise<Object>} A promise that resolves to an object containing a list of models.
 * @example
 * listModels().then(models => console.log(models));
 */

louis030195

/**
 * Lists all models available on the platform.
 * @async
 * @returns {Promise<Object>} A promise that resolves to an object containing a list of models.
 * @example
 * listModels().then(models => console.log(models));
 */
async function listModels() {
    const response = await fetch("https://api.airtable.com/v0/appwJMZ6IAUnKpSwV/all", {
        headers: {