Stars
High-performance retrieval engine for unstructured data
OCR, layout analysis, reading order, table recognition in 90+ languages
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
High accuracy RAG for answering questions from scientific documents with citations
This is the repo for the LegalBench-RAG Paper: https://arxiv.org/abs/2408.10343.
Testing Language Models for Memorization of Tabular Datasets.
🍨 High-fidelity, browser-based, single-page web archiving library and CLI for witnessing the web.
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
A guidance language for controlling large language models.
Python implementation of iterative-random-forests
ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its go…
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Find legal citations in any block of text
OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).
⚫ A spaCy pipeline and model for NLP on unstructured legal text.
Legal citation extractor, via command line, JavaScript, or HTTP. See a live example at:
Manage AWS Glacier vaults in Django and backup local files to Glacier.
Back your Django database and media directory up to Amazon Glacier or a local file
Node.js CMS and web app framework