Launch HN: Trellis (YC W24) – AI-powered workflows for unstructured data

1. unstract

   1 12 5,144 9.8 Python

   No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

   

   For anyone curious who wants to dig deep and solve document processing workflows via open-source, do try Unstract https://github.com/Zipstack/unstract

2. Judoscale

   judoscale.com featured

   Save 47% on cloud hosting with autoscaling that just works. Judoscale integrates with Django, FastAPI, Celery, and RQ to make autoscaling easy and reliable. Save big, and say goodbye to request timeouts and backed-up task queues.

   

3. edsl

   2 3 235 10.0 Python

   Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

   

   Very cool - I've been working on an open source python package that lets you do some similar things (https://github.com/expectedparrot/edsl).

   Here's an example of the Enron email demo using the edsl syntax/package & a few different LLMs:

4. TypeChat

   3 14 8,435 7.8 TypeScript

   TypeChat is a library that makes it easy to build natural language interfaces using types.

   

   Really cool project! I'm doing something similar at a very low scale using [TypeChat](https://github.com/microsoft/Typechat) with Zod and [Unstructured](https://unstructured.io/)

Suggest a related project