tosh

I have a parquet file named ah.parquet.

It contains Apple Health data and has the following columns:

• type: Nullable(String)
• value: Nullable(String)
• start: Nullable(DateTime64(6))
• end: Nullable(DateTime64(6))
• created: Nullable(DateTime64(6))

RyanBalfanz

import json
import urllib.parse
from dataclasses import InitVar, dataclass
from datetime import datetime, timedelta
from typing import Protocol

import httpx
import llm
import streamlit as st

montasaurus

llmc() {
    local system_prompt='Output a command that I can run in a ZSH terminal on macOS to accomplish the following task. Try to make the command self-documenting, using the long version of flags where possible. Output the command first enclosed in a "```zsh" codeblock followed by a concise explanation of how it accomplishes it.'
    local temp_file=$(mktemp)
    local capturing=true
    local command_buffer=""
    local first_line=true
    local cleaned_up=false # Flag to indicate whether cleanup has been run

    cleanup() {
        # Only run cleanup if it hasn't been done yet

PedramNavid

 This uses llm.datasette.io and OpenAI.
 
 I use `git commit --template` to provide the output from the LLM to Git. This way, if you do not like the results, you
 can quit your editor and no commit will be made. 
 
 # Shell function for generating a diff and editing it in your default editor:
 
gcllm() {
  GIT_DIR="$(git rev-parse --git-dir)"
  TEMPLATE="$GIT_DIR/COMMIT_EDITMSG_TEMPLATE"

Brandon7CC

function speak_ollama() {
    if ! command -v ollama &> /dev/null; then
        echo "Error: ollama is not installed."
        return 1
    fi

    if [ "$#" -ne 2 ]; then
        echo "Usage: speak_ollama <file_path> <model>"
        return 1
    fi

vivgui

Here are my favorite tech newsletters:

• Frontend Focus: A once–weekly roundup of the best front-end news, articles and tutorials. HTML, CSS, WebGL, Canvas, browser tech, and more.
• This Week In React: The latest news directly in your inbox!
• Web Tools Weekly: A weekly newsletter for front-end developers with a specific focus on tools.
• NEXT.JS Weekly: A newsletter of the best Next.js articles, tools and projects
• JavaScript Weekly: A newsletter of JavaScript articles, news and cool projects
• Friday Front-End: Front-end development links tweeted daily, emailed weekly.
• CSS Weekly: Weekly e-mail roundup of CSS articles, tutorials, experiments, and tools curated by Zoran Jambor
• Liquid Weekly: Your one-stop shop for all things Shopify Development

willbchang

#!/bin/zsh
# #popclip
# name: Azure TTS
# icon: symbol:message.and.waveform

# Please apply for your own key
AZURE_REGION=
AZURE_SUBSCRIPTION_KEY=

# Create a temporary audio file

hwchase17

from langchain.chat_models import ChatOpenAI
from pydantic import BaseModel, Field
from langchain.document_loaders import UnstructuredURLLoader
from langchain.chains.openai_functions import create_extraction_chain_pydantic

class LLMItem(BaseModel):
    title: str = Field(description="The simple and concise title of the product")
    description: str = Field(description="The description of the product")

def main():

kylemcdonald

CharlesNepote

#!/usr/bin/env bash
# sudo ln -s "$(pwd)/csv2datasette" /usr/bin/csv2datasette

# csv2datasette is meant to explore CSV data. It is not meant to create a sustainable DB.
# csv2datasette is a bash script which open CSV files directly in Datasette. It offers
# a number of options for reading and exploring CSV files, such as --stats, inspired by WTFCsv.
#
# `--stats` option includes, for each column: the column name, the number of unique values,
# the number of filled rows, the number of missing values, the mininmum value, the maximum value, 
# the average, the sum, the shortest string, the longest string, the number of numeric values,