Cooking functionally

I am not actually using functional programming in the kitchen :-)

I am re-writing my old cookingspace.com web app in Clojure with a new twist: the new web app will be an AI agent for planning recipes based on the food you have on-hand and based on a user's history, preferences, and the general mood they are in (food-wise). I have written some tools to convert my old relational database code for (more or less) static data (USDA nutrition information, recipes) to Clojure literal data.

Based on the type of food a user feels like cooking and what food they have on-hand, I need to transform recipes in an intelligent way to (hopefully!) also taste great after ingredients have substituted or morphed because a user would prefer a different type of sauce over a base recipe, etc., etc.

Anyway, working in Lisp and experimenting in a repl is making the entire process easier.

My wife and I are both very good cooks and we can make up super-tasty recipes on the fly with whatever ingredients we have on hand. I am betting on two things: I can automate our expertise and that people will enjoy using the system when it is finished.

Comments

  1. Ivan Pierre6:08 PM

    Very nice project idea ;)

    ReplyDelete
  2. Unknown7:32 PM

    Hi Mark,

    I recently started a project for setting up default web application templates http://www.luminusweb.net/ it might come in handy, and I'm always open to suggestions and ideas.

    The template simply provides a sane default configuration for a Ring/Compojure app. And I'm working on creating good documentation around using these libraries to save people from having to scour google to figure out basic things. :)

    ReplyDelete
  3. Franklin Chen8:37 PM

    Sounds exciting! It's my turn to do the cooking at home tomorrow and my "method" for coming up with something tends to be to find out what we have on hand and then Google and then come up with something based on the search results and my own experience. Automation of some of the decision-making could definitely be useful.

    ReplyDelete
  4. Mark Watson, author and consultant8:40 PM

    Thanks Ivan. Wish me luck!

    ReplyDelete
  5. grant rettke12:02 PM

    I was thinking of doing something like this as a vehicle to learning a rules engine. Where does the AI part fit in beyond leveraging user's preferences and history? I mean does the system "learn" (by some open ended term) or???

    ReplyDelete
  6. Mark Watson, author and consultant12:12 PM

    Hello Grant,

    I am not using a rules engine, rather I am hard-coding rules for substituting ingredients based on what ingredients taste good together.

    I am breaking recipes up into ingredient and directions "chunks."

    I may end up writing my own case based reasoning engine - not sure, really - just getting started.

    ReplyDelete
  7. Mark Watson, author and consultant12:19 PM

    re: "I may end up writing my own case based reasoning engine - not sure, really - just getting started."

    if you read the literature for AI recipe agents (e.g., Chef) they handled narrow domains. I am trying to handle all general types of recipes, so I believe that I have chosen a difficult problem!

    ReplyDelete
  8. Unknown5:30 AM

    It may be useful to model recipes as projects are modelled in project management. This way you can break a recipe down starting with the set of deliverables at the end (plates of food ready to serve), which is then decomposed in to the work required to deliver them. Subject to the capacity constraints of your kitchen, you want everything for a course to arrive at the same time, so it may be amenable to reverse scheduling.

    Using this modelling approach, it may be possible to use the more visual presentations (e.g. adapted Gantt chart, musical notation) instead of prose.

    A valuable feature would be to scale ingredient quantities for serving a different size party to that used in the original recipe, and to provide useful conversions between weight and volume for common ingredient densities and measurement units.

    The ingredients knowledge base could be derived from a semantic wiki.

    ReplyDelete
  9. Mark Watson, author and consultant8:15 AM

    Thanks Vincent - good ideas, and sort of what I have in mind.

    If this all works out well I will either write a series of blog articles on the back end tech, or perhaps even a short book. First though, I need to finish the project :-)

    ReplyDelete

Post a Comment

Popular posts from this blog

My Dad's work with Robert Oppenheimer and Edward Teller

Robert Oppenheimer and Edward Teller facilitated my Dad getting a professorship at UC Berkeley when I was 3 years old. Oppenheimer left Berkeley but Teller was a good friend of my father and I remember him being in our home. Three weeks ago, my wife and I were just leaving to see the new Oppenheimer movie when my Dad called. He mentioned that when I was in grade school he was invited to give a talk at Princeton. After his talk Oppenheimer talked with my Dad and invited him to have dinner at his house. My Dad said Oppenheimer was not well (I think he died of throat cancer soon afterwards) but his wife Kitty carried the conversation. My Dad, Ken Watson, passed away 10 days ago on August 18, 2023.
Read more

Time and Attention Fragmentation in Our Digital Lives

  As humans we have evolved over a few million years to be both attentive and reactive to danger, live in social communities, and spend much of our time being in the present moment gathering and eating food and socializing. The behavior of rapidly changing short attention to content on social media, too many good short form things to watch on streaming video entertainment platforms, are all rewiring our brains in an unnatural and unhealthy way. I fight back, but in really simple ways that entail little ceremony: Almost every morning I spend 30 minutes scanning Hacker News (about 10 minutes), Apple News (about 5 minutes), and the remaining time on Twitter and Mastodon finding interesting new (mostly tech) things. I make notes in a temporary Apple Note: links of things I may want to research, try, or simply read that day. I like to get this all done at once, and then not feel like I need to interrupt my activities during the day to “catch up” on what is happening in the world. In a w...
Read more

I am moving back to the Google platform, less excited by what Apple is offering

I have been been playing with the Apple Intelligence beta’s in iPadOS and macOS and while I like the direction Apple is heading I am getting more use from Google’s Gemini, both for general analysis of very large input contexts, as well as effective integration my content in Gmail, Google Calendar, and Google Docs. While I find the latest Pixel phone to be compelling, I will stick with Apple hardware since I don’t want to take the time to move my data and general workflow to a Pixel phone. The iPhone is the strongest lock-in that Apple has on me because of the time investment to change. The main reason I am feeling less interested in the Apple ecosystem and platform is that I believe that our present day work flows are intimately wrapped up with the effective use of LLMs, and it is crazy to limit oneself to just one or two vendors. I rely on running local models on Ollama, super fast APIs from Groq (I love Groq for running most of the better open weight models), and other APIs from Mist...
Read more