aipl
todo.txt-cli
aipl | todo.txt-cli | |
---|---|---|
4 | 55 | |
119 | 5,478 | |
- | 0.5% | |
9.2 | 2.9 | |
6 months ago | 3 months ago | |
Python | Shell | |
MIT License | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
aipl
-
Ask HN: Tell us about your project that's not done yet but you want feedback on
AIPL is an "Array-Inspired Pipeline Language", a tiny DSL in Python to make it easier to explore and experiment with AI pipelines.
https://github.com/saulpw/aipl
When you want to run some prompts through an LLM over a dataset, with some preprocessing and/or chaining prompts together, AIPL makes it much easier than writing a Python script.
-
The Problem with LangChain
Yes! This is why I started working on AIPL. The scripts are much more like recipes (linear, contained in a single-file, self-evident even to people who don't know the language). For instance, here's a multi-level summarizer of a webpage: https://github.com/saulpw/aipl/blob/develop/examples/summari...
The goal is to capture all that knowledge that langchain has, into consistent legos that you can combine and parameterize with the prompts, without all the complexity and boilerplate of langchain, nor having to learn all the Python libraries and their APIs. Perfect for prototypes and experiments (like a notebook, as you suggest), and then if you find something that really works, you can hand-off a single text file to an engineer and they can make it work in a production environment.
-
Langchain Is Pointless
I agree, and that's why I've been working on AIPL[0]. Our first v0.1 release should be in the next few days. https://github.com/saulpw/aipl
It's basically just a simple scripting language with array semantics and inline prompt construction, and you can drop into Python any time you like.
-
Re-implementing LangChain in 100 lines of code
I also was underwhelmed by langchain, and started implementing my own "AIPL" (Array-Inspired Pipeline Language) which turns these "chains" into straightforward, linear scripts. It's very early days but already it feels like the right direction for experimenting with this stuff. (I'm looking for collaborators if anyone is interested!)
https://github.com/saulpw/aipl
todo.txt-cli
-
Ask HN: What products other than Obsidian share the file over app philosophy?
FSNotes for macOS and iOS is one I used for a little while.
https://fsnot.es/
todo.txt is another thing that comes to mind.
http://todotxt.org/
And of course pretty much all of *nix.
-
My productivity app is a never-ending .txt file
Since at least 2012 I've also been using a text file format from http://todotxt.org/ and more recently I wrote a program that takes a crontab-like list to pre-generate entries on a daily, by-day-name (every Sunday for example), and I also pull in a list of holidays from gov.uk, so they are also populated.
[^1]: (https://github.com/blacksmithgu/obsidian-dataview)
- Why I Like Obsidian
-
Ask HN: Tell us about your project that's not done yet but you want feedback on
It's a web app implementing the todo.txt format (see http://todotxt.org/). It's an exercise to learn frontend currently, I doubt I could successfully monetize it. Would appreciate any feedback!
-
Looking for a note taking app with inline tags.
That format is really similar to todo.txt format, worth taking a look at http://todotxt.org/ (which in turn has application links).
-
Using Acme with Inferno's Shell as a pkm tool
For todo and schedule I use todo.txt (http://todotxt.org/) a plain file managed by scripts which build agenda and plumber to keep track of unique keys.
-
Looking for PC and mobile "to do list" software
The ToDo.Txt format makes it easy to use across devices/software, but this is really limited to ToDos.
-
Yet another To Do manager written in BASH. Simple and colorful.
Here’s the todo.sh features for those interested. There are several addons for it as well: https://github.com/todotxt/todo.txt-cli
-
TaskTXT The Todo List for Hackers
Good idea, something similar to todotxt.org. But no 1) iPhone app 2) you need to sigh up and keep your notes at developers servers 3) subscriptions?! come on!
-
Wish to start cli apps development
There are a couple different routes you can go down. If your goal is to learn CLI stuff, it's hard to beat using shell-scripting for a simple app like a todo manager. Storing them in a plain-text file, a little sed/grep/awk and you're well on your way. For inspiration & hints, you might check out https://todotxt.org However, you can rapidly hit performance issues and limitations on available tooling if you stick to just POSIX tools.
What are some alternatives?
modelfusion - The TypeScript library for building AI applications.
taskpaper.vim - This package contains a syntax file and a file-type plugin for the simple format used by the TaskPaper application.
hamilton - Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage and metadata. Runs and scales everywhere python does.
taskwarrior - Taskwarrior - Command line Task Management
multi-gpt - A Clojure interface into the GPT API with advanced tools like conversational memory, task management, and more
org-caldav - Caldav sync for Emacs orgmode
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
MarvinAPI - API documentation for the Amazing Marvin productivity tool
llm - Access large language models from the command-line
github-orgmode-tests - This is a test project where you can explore how github interprets Org-mode files
llm-gpt4all - Plugin for LLM adding support for the GPT4All collection of models
vimwiki - Personal Wiki for Vim