Full text search that feels like a numpy array

Open Source framework for voice and multimodal conversational AI

EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings (official implementation)

Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

A markup-based typesetting system that is powerful and easy to learn.

A curated list of awesome Recommender System (Books, Conferences, Researchers, Papers, Github Repositories, Useful Sites, Youtube Videos)

Python Keyphrase Extraction module

Google Cloud Platform Vertex AI end-to-end workflows for machine learning operations

A demonstration of metadata generation for RAG using a Health Canada document

Diagrams of concepts in physics/chemistry/ML

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

Your favorite self-hostable alternative to Google Timeline (Google Location History)

LangFair is a Python library for conducting use-case level LLM bias and fairness assessments

Turns Data and AI algorithms into production-ready web applications in no time.

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

Clustering sentence embeddings to extract message intent

200+ detailed flashcards useful for reviewing topics in machine learning, computer vision, and computer science.

Bangla Unicode Normalization

Build a Medical Q&A system using LangChain and Mistral 7B

project: replacing the use of RNNs in gene-regulatory network prediction, with ODEs.

DSPy: The framework for programming—not prompting—language models

OCR, layout analysis, reading order, table recognition in 90+ languages