Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Unified framework for building enterprise RAG pipelines with small, specialized models

Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

Convert PDF to markdown + JSON quickly with high accuracy

Generative Models by Stability AI

Graph Explorer can be used to explore RDF graphs in SPARQL endpoints or on the web.

Lightweight Linked Data Server and Proxy

Ontodia data diagraming library

Vacancy-resume matching dataset, with human ground truth rankings

Temporal Graph Benchmark project repo

Build ChatGPT over your data, all with natural language

VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of your choice.

Machine Learning Engineering Open Book

HAAS = Hierarchical Autonomous Agent Swarm - "Resistance is futile!"

OpenChat: Advancing Open-source Language Models with Imperfect Data

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion 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]

Refine high-quality datasets and visual AI models

[IJCV 2024] LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

Aligning LMMs with Factually Augmented RLHF

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

[ECCV 2024 Best Paper Candidate] PointLLM: Empowering Large Language Models to Understand Point Clouds

Implementation of Nougat Neural Optical Understanding for Academic Documents

📕 Data Structures and Algorithms library in TypeScript and JavaScript

TUM SS21 Computer Vision Challenge

Video Content Description (VCD) is a schema, API and set of tools to produce semantically rich labels from multi-sensorial data series.