Curate better data for LLMs

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

[Paper][ACM MM 2024] Making Large Language Models Perform Better in Knowledge Graph Completion

Code for TKDE paper "Self-supervised learning on graphs: Contrastive, generative, or predictive"

This is a continuously updated handbook for readers to easily track the latest NL2SQL techniques in the literature and provide practical guidance for researchers and practitioners.

SUQL: Conversational Search over Structured and Unstructured Data with LLMs

Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, and bit vectors using SIMD for both AVX2, AVX-512, NEON, SVE, …

Retrieval-Augmented Generation-based Relation Extraction

SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions

Rapid fuzzy string matching in Python using various string metrics

GLADIS: A General and Large Acronym Disambiguation Benchmark (EACL 23)

End-to-End Local-First Text-to-SQL Pipelines

Efficient Triton Kernels for LLM Training

🚀 Open-source SQL AI Agent for Text-to-SQL. Make Text2SQL Easy! 🙌

A foundation model for knowledge graph reasoning

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Woodwork is a Python library that provides robust methods for managing and communicating data typing information.

A dataset of tabular data from data.gov annotated to business glossaries using LLMs.

A collection of AWESOME things about Graph-Related LLMs.

How to construct knowledge graphs from unstructured data sources

End-to-end zero-shot entity and relation extraction

Awesome-LLM: a curated list of Large Language Model

Must-read papers on graph neural networks (GNN)

Retrieve, Read and LinK: Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget (ACL 2024)

🆔 A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.

This repository provides various implementations, datasets, and research papers that aim to help researchers and developers build accurate and efficient Text2SQL models.