aipl
obsidian-releases
aipl | obsidian-releases | |
---|---|---|
4 | 1,654 | |
119 | 8,119 | |
- | 4.2% | |
9.2 | 9.9 | |
6 months ago | 1 day ago | |
Python | JavaScript | |
MIT License | - |
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
obsidian-releases
- Unlocking Efficiency: The Significance of Technical Documentation
-
UX Case Study: Markdown Heading
The closest editor that follows our first principle is Obsidian editor:
-
I switched from Notion to Obsidian
The solution was already installed on both my computer and my phone: Obsidian.
-
Why single vendor is the new proprietary
> why does open source need to "win"
Open source does not need to win.
But your ability to be in control of your computer needs to be preserved. A proprietary fridge cannot control your diet, while a proprietary App Store can control what software you install on YOUR phone (unless you live in EU, hello DMA!). The tail wags the dog, so to speak. Proprietary software has also been shown to break user workflows or remove functions in an update while leaving users with no choice whatsoever.
One alternative to having open source win is to ensure software must come with a robust warranty and other assurances you expect from the things you buy. EU's CRA will make software vulnerabilities in WiFi routers covered by warranty, for example.
You can also ensure robust and interoperable data storage options. For example, https://obsidian.md/ stores all notes in Markdown, not holding the data hostage in case users will not like how future versions will work. GDPR actually has a provision for data portability (Art. 20), but it does not seem to have a requisite effect on the industry yet.
And until the above issues are solved, open source remains the best way to ensure that a software tail cannot wag your computer dog.
-
Ask HN: Has Anyone Trained a personal LLM using their personal notes?
[2] https://obsidian.md/
-
Replatforming from Gatsby to Zola!
So I've had my fair share of personal websites and blogs. I have built them on stacks ranging from the most basic HTML and CSS, to hosted frameworks like Wordpress and Laravel, to the more modern single page applications built in Vue and React. For a simple content blog I think you can't go wrong with a Static Site Generator though. These days I am almost exclusively writing everything in Obsidian. Which is great because its all in standard markdown format. This allows for a really neat and easy content publishing workflow.
-
Show HN: Godspeed is a fast, 100% keyboard oriented todo app for Mac
Consider making an Obsidian[^1] plugin, or writing to Obsidian-compatible Markdown files :)
[^1]: https://obsidian.md/
-
Setting Up Obsidian for Content Planning and Project Management
Obsidian is a writing application created to allow for offline / private note taking in markdown format, in an interface that looks a lot like our regular programming IDE. It is very flexible, with a good collection of community plugins that you can use to customize Obsidian to your heart contents.
-
What is Omnivore and How to Save Articles Using this Tool
Obsidian support via our Obsidian Plugin
- Tools that Make Me Productive as a Software Engineer
What are some alternatives?
modelfusion - The TypeScript library for building AI applications.
Trilium Notes - Build your personal knowledge base with Trilium Notes
hamilton - Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage and metadata. Runs and scales everywhere python does.
QOwnNotes - QOwnNotes is a plain-text file notepad and todo-list manager with Markdown support and Nextcloud / ownCloud integration.
multi-gpt - A Clojure interface into the GPT API with advanced tools like conversational memory, task management, and more
vimwiki - Personal Wiki for Vim
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.
TiddlyWiki - A self-contained JavaScript wiki for the browser, Node.js, AWS Lambda etc.
llm - Access large language models from the command-line
AppFlowy - AppFlowy is an open-source alternative to Notion. You are in charge of your data and customizations. Built with Flutter and Rust.
llm-gpt4all - Plugin for LLM adding support for the GPT4All collection of models
Mermaid - Edit, preview and share mermaid charts/diagrams. New implementation of the live editor.