Adrián López adrianlzt

DSPy LabeledFewShot Optimizer Example

This repository contains a Python script, dspy_LabeledFewShot.py, that demonstrates how to use the dspy.teleprompt.LabeledFewShot optimizer for sentiment analysis.

The script defines a simple DSPy program to classify the sentiment of a sentence as "Positive", "Negative", or "Neutral". It then uses LabeledFewShot to "compile" this program by creating few-shot prompts from a small training set. Finally, it runs the compiled program on a new sentence and inspects the prompt sent to the Language Model (LLM) to show how the few-shot examples were included.

Requirements

Python 3.13+
uv

❯ uv run https://gist.githubusercontent.com/adrianlzt/b2c2c9581757ad359216eef0f05beb1a/raw/5a0f29c2496a98e9aef0eef8ad1469d1cbdd09e8/awx_secrets.py --host 10.1.1.10 --user awx --password SECRETPASSWORD --secret-key SECRETKEY

Reading inline script metadata from `./awx_secrets.py`
Available secrets:
1. Name: Demo Credential, Type: Machine
Select the secret to decrypt: 7
username: admin

	#!/usr/bin/env -S uv run --script
	# /// script
	# requires-python = ">=3.10"
	# dependencies = [
	# "bleak",
	# ]
	# [tool.uv]
	# exclude-newer = "2025-07-03T00:00:00Z"
	# ///

	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>Shoulder Mobility Assessment Calculator</title>
	<link rel="stylesheet" href="style.css">
	<link rel="preconnect" href="https://fonts.googleapis.com">
	<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
	<link href="https://fonts.googleapis.com/css2?family=Roboto:wght@400;700&display=swap" rel="stylesheet">

	#!/usr/bin/env -S uv run
	# /// script
	# requires-python = ">=3.13"
	# dependencies = [
	# "mlflow",
	# "azureml-mlflow",
	# "azure-ai-ml",
	# "azure-identity",
	# ]
	# [tool.uv]

	<!-- Taken from https://simonwillison.net/2025/Mar/28/incomplete-json-pretty-printer/ -->
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>JSON Pretty Printer</title>
	<style>
	body {
	font-family: Arial, sans-serif;

	#!/usr/bin/env python3

	import subprocess

	def remove_image(image_id):
	"""Safely remove a docker image."""
	try:
	subprocess.run(["docker", "rmi", image_id], check=True, capture_output=True)
	print(f" ✓ Removed: {image_id}")
	except subprocess.CalledProcessError:

	#!/bin/bash

	# Check if two arguments (cgroup paths) are provided
	if [ "$#" -ne 2 ]; then
	echo "Usage: $0 <cgroup1_path> <cgroup2_path>"
	exit 1
	fi

	cgroup1_path="$1"
	cgroup2_path="$2"

	#!/bin/bash
	#
	# Aplicación para editar un KV secret version 2 en Vault
	#

	path=$1
	tmpfile=$(mktemp)

	# Fetch the secret and write it to a temporary file
	vault kv get -format=json $path \| jq -er .data.data > $tmpfile

	# Creamos una CA self-signed para generar los certificados de los clientes VPN
	resource "tls_private_key" "foo-vpn-ca-key" {
	algorithm = "RSA"
	rsa_bits = 4096
	}

	resource "tls_self_signed_cert" "foo-vpn-ca" {
	private_key_pem = tls_private_key.foo-vpn-ca-key.private_key_pem

	subject {