ls1intum / Athena

A system to support (semi-)automated assessment of exercises, built on ls1intum/Athena
https://ls1intum.github.io/Athena/
6 stars 1 forks source link

Feature/rag lecture text #355

Open EneaGore opened 2 weeks ago

EneaGore commented 2 weeks ago

Motivation and Context

In order to provide more contextually accurate and reliable feedback a Retrieval Augmented Generation Approach is being tested.

Description

It uses an in-memory vectore storage, which serves the purposes of having an MVP. If it shows satisfactory results an integration with Pyrius will be the next step.

Steps for Testing

Populate the pdfs directory inside the rag approach directory with relevants documents. Select the approach from the playground and confirm that it works. In langchain you can see whether the retriever was successfully called.

Testserver States

[!NOTE] These badges show the state of the test servers. Green = Currently available, Red = Currently locked Click on the badges to get to the test servers.

Screenshots