Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Talking To Machines

Cache your API calls with a single line of code. No mocks, no fixtures. Just faster, cleaner code.

Robustness with frontier LLMs: R Software and Paper

Tutorial on Transformers 🤖, HuggingFace 🤗 and Social Science Applications 👥 @ IC2S2

Replication Material and Code for the Paper AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers. Accepted at LaTeCH-CLfL2025

Repository of the ICNLSP 2024 paper "Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes"

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

A guidance language for controlling large language models.

Run LLMs with MLX

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

A collection of notebooks/recipes showcasing usecases of open-source models with Together AI.

lossily compress representation vectors using product quantization

Röttger et al (ACL 2024): "Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models"

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

A web app for analyzing rhetorical framing strategies in German-language journalistic texts.

Code and data for the paper "Narratives at Conflict: Computational Analysis of News Framing in Multilingual Disinformation Campaigns"

Train transformer language models with reinforcement learning.

🤗 smolagents: a barebones library for agents that think in code.

Linguistic profiling of political texts: Language complexity in populist rhetoric

Because we don't want a jupyter notebook mess...

A small library of LLM judges

The most accurate natural language detection library for Python, suitable for short text and mixed-language text