FOSDEM 2024: Using Haystack to Build Custom Functionality for LLM Applications

Retrieval-Augmented Generation (RAG) is an incredibly powerful technique (a hack, if you will) to make use of powerful LLMs while making sure they produce accurate information based on your own data. However, model providers and open-source frameworks cannot know exactly what you need for every application you might need to build.
In this talk, we will look at Haystack, an open-source LLM framework, and see how you can use Haystack to build your own customized LLM functionality: - What is Retrieval-Augmented Generation - How to build custom RAG pipelines with a choice of model providers - How to customize your own tooling for LLM applications - Example: Build a 'HackerNewsFetcher' for a RAG application that uses the latest Hacker News articles.
Presentation slides: docs.google.co...
Hacker News TL;DR Colab: colab.research...
Hacker News Summaries Space: huggingface.co...
Structured GitHub Issues Colab: colab.research...
Mastodon 'Should I follow?' Demo: huggingface.co...