wimsey
hal9
| wimsey | hal9 | |
|---|---|---|
| 4 | 7 | |
| 128 | 165 | |
| 3.9% | 3.0% | |
| 7.3 | 9.5 | |
| 16 days ago | 3 days ago | |
| Python | Python | |
| MIT License | 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.
wimsey
-
Classic Data science pipelines built with LLMs
I'm definitely biased because my day job is writing ETL pipelines and supporting software, and my current side project is a data contracts library for helping the above[0]. Still I'm not sure I see this happening.
80% of the focus of an ETL pipeline is in ensuring edge cases are handled appropriately (i.e. not producing models from potentially erroneous data, dead letter queing unknown fields etc).
I think an LLM would be great for "take this json and make it a pandas dataframe", but a lot less great for interact with this billing API to produce auditable payment tables.
For areas that are reliability focused, LLMs still need a lot more improvments to be useful.
[0] https://github.com/benrutter/wimsey
-
The Data Engineering Handbook
Nice list! Although as somebody who works on open source tools for data engineering, it kills me a little to see "companies" as the the list header rather than, say, "projects".
(also, shameless plug for my.latest project Wimsey which is non-company affiliated but does let you test data in a nice, lightweight way: https://github.com/benrutter/wimsey)
- Wimsey: A flexible, lightweight data contracts library
-
This Week In Python
wimsey – Easy and flexible data testing and documentation
hal9
-
Ask HN: What Are You Working On? (February 2025)
Working on hal9.ai -- Long term, a Roblox for AI; short term, a Python customizable ChatGPT that is enterprise ready. Think of ChatGPT without the LLM and support for writing your own RAG.
https://github.com/hal9ai/hal9
-
Classic Data science pipelines built with LLMs
For those interested, you can use LLMs to process CSVs in Hal9 and also generate streamlit apps, in addition, the code is open source so if you want to help us improve our RAG or add new tools, you are more than welcomed.
- https://hal9.ai
- https://github.com/hal9ai/hal9
-
Hal9: Create and Share Generative Apps
Hi there! We built Hal9 (GitHub) to make it radically simpler to create, deploy, and share applications powered by LLMs, diffusers, and other AI models. Whether you're working on chatbots, agents, APIs, or generative apps, Hal9 is designed to minimize the engineering overhead so you can focus on the AI itself.
- New AI startup from the co-authors of the Original Transformers Paper
- Show HN: Generating Streamlit Apps with GPT3
-
[P] Build data apps with GPT-3 in hal9
Hi 👋🏼 I'm Javier, we've been working on an OSS library called hal9. It allows you to build data applications with Python and R with a callback model, kinda like between streamlit and dash.
What are some alternatives?
Scrapling - 🕷️ An undetectable, powerful, flexible, high-performance Python library that makes Web Scraping simple and easy again!
marimo - A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. All in a modern, AI-native editor.
finstruments - Financial instrument definitions built with Python and Pydantic
mistreevous - A tool to build and execute behaviour trees in JavaScript and TypeScript
abacus-minimal - A minimal event-based ledger in Python that follows accounting rules
feed-visualizer - Feed Visualizer creates interactive visualizations by clustering RSS/Atom feed items based on semantic similarity. Feed Visualizer also attempts to automatically predict the labels for each cluster. This application will create a "semantic summary" of a website's contents by scanning its RSS/Atom feed, allowing for easy discovery and navigation to topics of interest. Feed Visualizer creates interactive visualizations in the form of static HTML and JS files, which may be edited and sent to a server.