Open-Assistant icon indicating copy to clipboard operation
Open-Assistant copied to clipboard

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Results 1560 Open-Assistant issues
Sort by recently updated
recently updated
newest added
trafficstars

The idea is to have a notebook that takes a code as an input and converts it into set of instructions on how to make it. This can be achieved...

data

This is follow up on https://github.com/LAION-AI/Open-Assistant/issues/38 and https://github.com/LAION-AI/Open-Assistant/tree/main/notebooks/detoxify-evaluation. 1. Use the [hugginface hosted inference API](https://huggingface.co/docs/huggingface_hub/how-to-inference) to host and expose the `multilingual` variant of the ['unitaryai/detoxify'](https://huggingface.co/unitary) models and make it available...

backend
ml

Write a python script that fills the backend postgresql DB with random message-trees and users. Insert 500k messages (each on averge 500 characters long) of 1k randomly selected mock-users (all...

backend
testing

It's very likely we'll create a task that can't be answered because it's not sensible or complete garbage. We should add a button and API piping to ensure a user...

backend
website

Given a `message_id` we can fetch the full conversation tree it resides within and the various branches. It's not obvious how to best do this so please experiment with different...

website

Given a unique message id, we should be able to fetch that message's full conversation and then render all the messages before and after. To finish this we need: -...

website

For now I'm writing here primarily to document my plan for a MVP. As suggested in the discord server, I plan to make a generalization safety checker. This could be...

data

This is a potential plan for cleaning the Red Teaming data from Anthropics. - Step 1: Splitting data into Evil-Harmful and Harmless data. This is fairly easy. The Anthropics dataset...

data

I think some sort of architecture diagram could be useful for people trying to understand the moving parts in this project. I can imagine it will change quite a lot...

documentation