Stefano Fiorucci

🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

Train a Language Model with GRPO to create a schedule from a list of events and priorities

Generates a quiz from a URL. You can play the quiz, or let the LLM play it.

Mistral + Haystack: build RAG pipelines that rock 🤘

Fact checking baseline combining dense retrieval and textual entailment

Knowledge pills on Neural Search

Conference talk: from zero to your first LLM application

Using Llama2 with Haystack, the NLP/LLM framework.

Simple Question Answering system, based on data crawled from Twin Peaks Wiki. It is built using 🔍 Haystack, an awesome open-source framework for building search systems that work intelligently over large document collections.

Materials for the PyCon Italy 2025 talk

Trying the Agents 🕵️ --> new feature introduced in Haystack 1.15.0 to make Large Language Models resolve complex queries and tasks

Collection of content I have created and shared over time

No description.

Haystack node for checking the entailment between a statement and a list of Documents

No description.

Additional packages (components, document stores and the likes) to extend the capabilities of Haystack

🦄 An NLP application just for the lols: built with Haystack to get an overview of what a user is posting about on Twitter

Get up and running with Llama 2 and other large language models locally

Electra model for (Extractive) Question Answering on Italian texts

Randstad Artificial Intelligence Challenge (powered by VGEN). Soluzione proposta da Stefano Fiorucci (anakin87) - primo classificato

My website

A tiny 1.3M parameter model that plays DOOM, outperforming LLMs up to 92,000x its size.

Examples and guides for using the Gemini API

No description.

Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK

No description.

Environments for LLM Reinforcement Learning

Training-Ready RL Environments + Evals

No description.

Async RL Training at Scale

No description.

Haystack integration with DeepL translation services provider.

Python bindings for llama.cpp

Docling Haystack integration

Open-source AI cookbook

👩🏻‍🍳 A collection of example notebooks using Haystack

My old website - offline

LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and chat messages from generic blueprints. It allows attaching metadata to prompts to ease their management, and versioning is first-class citizen. Banks provides ways to store prompts on disk along with their metadata.

Improving Gemma 2 for a Specific Language on a Budget: Post-Training Recipe 💎🌍🇮🇹

AI agent microservice

Train transformer language models with reinforcement learning.

No description.

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Open Source Day: Come join us and discover Open Source in the most inclusive way :)

No description.

Robust recipes for Alignment

Examples and guides for using the OpenAI API

🚀 Template Haystack Search Application with Streamlit

✨ Open-source tool for data-centric NLP. Argilla helps domain experts and data teams to build better NLP datasets in less time.

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

Here you can find all the Tutorials for Haystack 📓

No description.

A Python library to extract tabular data from PDFs