Show HN: Trellis – open-source Python framework to build DAG-based LLM workflows https://ift.tt/7YNz0Tx

Show HN: Trellis – open-source Python framework to build DAG-based LLM workflows Hey HN! Trellis is an open-source framework for programmatically orchestrating LLM workflows as Directed Acyclic Graphs (DAGs) in Python. My friend and I started working on this a few weeks ago after we tried building applications using mainstream LLM frameworks, and faced all the common complaints (too abstracted, hard to customize, bad docs/support). After talking to a few other people building with LLMs, we also noticed that these frameworks were not inherently built to support DAG-based LLM workflows. We designed Trellis to be as minimal and flat as possible, so developers can have lower level control over their DAGs. Trellis is composed of only three abstractions: Node, DAG, and LLM. Node: the atomic unit of Trellis. Nodes are chained together to form a DAG. Node is an abstract class with only one method required to implement. DAG: a directed acyclic graph of Nodes. It is the primary abstraction for orchestrating LLM workflows. When you add edges between Nodes, you can specify a transformation function to reuse Nodes and connect any two Nodes. Trellis verifies the data flowing between Nodes in a DAG to ensure the flow of data is validated. LLM: a wrapper around a large language model with simple catches for common OpenAI errors. Currently, the only provider that Trellis supports is OpenAI. Check out our docs if this sounds interesting: https://ift.tt/ojshWPK... We'd love it if you tried hacking with it and give us any feedback you have! :) https://ift.tt/fdkh47a September 6, 2023 at 07:34AM

Show HN: Revenut – A lightweight open-source alternative to Stripe's mobile app https://ift.tt/rnp6PlW

Show HN: Revenut – A lightweight open-source alternative to Stripe's mobile app https://ift.tt/eXI4p3D September 6, 2023 at 04:23AM

Show HN: Fully client-side GPT2 prediction visualizer https://ift.tt/I8CVA9D

Show HN: Fully client-side GPT2 prediction visualizer https://ift.tt/IEyZTKj September 6, 2023 at 04:12AM

Show HN: ConfigNexus – A way to store configuration data centerally https://ift.tt/50xwqBM

Show HN: ConfigNexus – A way to store configuration data centerally https://ift.tt/OM91Rzt September 6, 2023 at 03:33AM

Show HN: Miko – an alternative to googling healthcare queries https://ift.tt/EykwuQq

Show HN: Miko – an alternative to googling healthcare queries This is a personal experiment that uses AI to respond to healthcare queries. I was fed up of googling symptoms which provided no concrete advice. The only alternative was to fork out for a doctor's appointment that would last a few minutes. So I built a little tool that will hopefully augment people's interactions with their health. I have no interest in replacing the hospital or the need for a doctor. Miko is not flawless but it is a free, instant alternative to expensive healthcare. My hope is that users would try the advice Miko gives them but also visit their doctor if their symptoms persisted. Previously I built a one-stop shop for healthcare which sold services at discounted prices but it is just an interesting side project. I have investigated ways of incorporating GPT and other models into healthcare since last year. I used bubble.io for the web app because of its convenience. https://ift.tt/RpKgVho September 6, 2023 at 01:53AM

Show HN: Ethical AI – Alternate Reality Game on LLMs https://ift.tt/E1V8eX0

Show HN: Ethical AI – Alternate Reality Game on LLMs https://ethical-ai.eu/ September 6, 2023 at 01:35AM

Show HN: Monitoring my life with Grafana, Prometheus and InfluxDB https://ift.tt/XTCt63e

Show HN: Monitoring my life with Grafana, Prometheus and InfluxDB I love the idea of quantified self and recently decided to pull all of my data in one place. I pull all of my data from ActivityWatch, Wakatime, and Health Connect APIs :) https://ift.tt/xVTECqo September 5, 2023 at 03:53PM