aipl
KeenWrite
aipl | KeenWrite | |
---|---|---|
4 | 98 | |
119 | 621 | |
- | - | |
9.2 | 0.0 | |
6 months ago | 8 months ago | |
Python | Java | |
MIT License | GNU General Public License v3.0 or later |
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
KeenWrite
-
Ask HN: Tell us about your project that's not done yet but you want feedback on
KeenWrite is my free, open-source, cross-platform desktop Markdown editor that can produce beautifully typeset PDFs. I started working on it years ago to help write a novel that has a complex timeline and I couldn't find a text editor that would allow me to integrate a character sheet with the story itself.
https://github.com/DaveJarvis/keenwrite
Tutorials:
* https://www.youtube.com/playlist?list=PLB-WIt1cZYLm1MMx2FBG9...
Here's what I mean by using variables directly:
* https://www.youtube.com/watch?v=CFCqe3A5dFg
CommonMark doesn't propose a standard for bibliographic references. Would anyone find the editor more appealing if it had cross-references and citations?
-
Documentation as Code for Cloud Using PlantUML
My cross-platform desktop text editor, KeenWrite, allows users to define variables in an external YAML file. The editor calls out to Kroki[1] to convert text-based diagrams to SVG. The diagrams can reference variables and are rendered using EchoSVG[2].
KeenWrite[3] can produce PDF documentation from Markdown documents that has PlantUML diagrams with elements stored in an external, machine-readable file. Here are screenshots showing variables on the left, diagram text in the middle, and a real-time render on the right:
* https://raw.githubusercontent.com/DaveJarvis/KeenWrite/main/...
* https://raw.githubusercontent.com/DaveJarvis/KeenWrite/main/...
KeenWrite supports all diagrams offered by Kroki, which includes "diagram-plantuml".
[1]: https://kroki.io/
[2]: https://github.com/css4j/echosvg/
[3]: https://github.com/DaveJarvis/keenwrite
- On why Markdown is not a good, or even a half-decent, markup language
- MdBook – Create book from Markdown files. Like Gitbook but implemented in Rust
- KeenWrite 3.3.2: MermaidJS diagrams (with caveat)
-
Interactive CommonMark Tutorial
Although not interactive, I've created a video series that shows advanced usage of Markdown. Namely R, external variables, diagrams, math, annotations, and a different approach to metadata:
* https://www.youtube.com/playlist?list=PLB-WIt1cZYLm1MMx2FBG9...
Tutorial 4 shows basic Markdown:
* https://www.youtube.com/watch?v=qNbGSiRzx-0
The top-right of each video shows keyboard and mouse clicks to help follow along.[1] My desktop text editor, KeenWrite[2], is used in the tutorials.
[1]: https://github.com/DaveJarvis/kmcaster
[2]: https://github.com/DaveJarvis/keenwrite
-
“Exit Traps” Can Make Your Bash Scripts Way More Robust and Reliable
https://github.com/DaveJarvis/keenwrite/blob/main/scripts/bu...
My template script provides a way to make user-friendly shell scripts. In a script that uses the template, you define the dependencies and their sources:
DEPENDENCIES=(
-
EchoSVG: SVG rasterizer library supporting level 4 selectors (Apache 2)
I didn't create the fork, nor am I affiliated with the project. I use it in my text editor, KeenWrite to rasterize SVG.
-
Millions of dollars in time wasted making papers fit journal guidelines
KeenWrite Themes[1] are instructions that tell ConTeXt how to typeset XHTML documents (content) into PDF files (presentation). I made a tutorial that shows how my FOSS desktop text editor, KeenWrite[3], allows users to write in Markdown to typeset a document against a particular theme.
Before it can be used for scientific papers, it needs cross-references, which, unfortunately, aren't part of the CommonMark specification.
I posit that the vast majority of LaTeX users don't grok how to separate content from presentation. When I asked a question on TeX.SE about how to adjust the line spacing between enumerated items (spanning a couple dozen enumerated lists), the vast majority of people voted for the answer of using `\itemsep0em` to tweak each list ... individually.[4] The correct answer, IMO, is to fix the problem globally, and not waste time tweaking individual lists.
[1]: https://github.com/DaveJarvis/keenwrite-themes
[2]: https://www.youtube.com/watch?v=3QpX70O5S30
[3]: https://github.com/DaveJarvis/keenwrite
[4]: https://tex.stackexchange.com/questions/6081/reduce-space-be...
What are some alternatives?
modelfusion - The TypeScript library for building AI applications.
markdown-preview.nvim - markdown preview plugin for (neo)vim
hamilton - Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage and metadata. Runs and scales everywhere python does.
marktext - 📝A simple and elegant markdown editor, available for Linux, macOS and Windows.
multi-gpt - A Clojure interface into the GPT API with advanced tools like conversational memory, task management, and more
typst - A new markup-based typesetting system that is powerful and easy to learn.
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.
vim-markdown - Markdown Vim Mode
llm - Access large language models from the command-line
Zettlr - Your One-Stop Publication Workbench
llm-gpt4all - Plugin for LLM adding support for the GPT4All collection of models
kroki - Creates diagrams from textual descriptions!