Stefano Fiorucci
anakin87
AI/SW Engineer/Explorer 🧑🚀
Languages
Repos
49
Stars
526
Forks
47
Top Language
Python
Loading contributions...
Top Repositories
Train a Language Model with GRPO to create a schedule from a list of events and priorities
Mistral + Haystack: build RAG pipelines that rock 🤘
Generates a quiz from a URL. You can play the quiz, or let the LLM play it.
Fact checking baseline combining dense retrieval and textual entailment
Knowledge pills on Neural Search
Conference talk: from zero to your first LLM application
Repositories
49🦄 An NLP application just for the lols: built with Haystack to get an overview of what a user is posting about on Twitter
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.
Environments for LLM Reinforcement Learning
Examples and guides for using the Gemini API
My website
Knowledge pills on Neural Search
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.
Training-Ready RL Environments + Evals
No description provided.
Collection of content I have created and shared over time
Materials for the PyCon Italy 2025 talk
No description provided.
Mistral + Haystack: build RAG pipelines that rock 🤘
Async RL Training at Scale
No description provided.
Haystack integration with DeepL translation services provider.
Python bindings for llama.cpp
Docling Haystack integration
Fact checking baseline combining dense retrieval and textual entailment
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.
Conference talk: from zero to your first LLM application
Improving Gemma 2 for a Specific Language on a Budget: Post-Training Recipe 💎🌍🇮🇹
AI agent microservice
No description provided.
Train transformer language models with reinforcement learning.
No description provided.