HTML, CSS, JS sandbox.

Convert any text to a graph of knowledge. This can be used for Graph Augmented Generation or Knowledge Graph based QnA

Using bge-large-en-v1.5 to save embeddings to a local file

Ollama Python library

Faster Whisper transcription with CTranslate2

Noise reduction in python using spectral gating (speech, bioacoustics, audio, time-domain signals)

Chrome extension that records your browser interactions and generates a Playwright or Puppeteer script.

Fast, unstyled command menu React component.

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Official implementation for the paper "LongEmbed: Extending Embedding Models for Long Context Retrieval"

Implementing the Chain Of Density text summarisation technique from recent NLP research by researchers at Salesforce, MIT, Columbia, etc. Takes a long text input and iteratively generates increasin…

Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️‍♂️

judini is a Node.js library to interact with the CodeGPTPlus API. It enables sending messages to the API and handling the responses in an efficient and easy manner. It also provides methods to chec…

[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

Esta herramienta permite englobar un conjunto de palabras (patterns) asignadas a un SPAN o categoría asignable. El uso de de esta herramienta es multiple, desde identificar sinónimos, corrector de …

Split and analyze text files using langchain and streamlit

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

Sample code illustrating the VS Code extension API.

Learn how to design systems at scale and prepare for system design interviews

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

Code for our ACL 2023 Paper "Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models".

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

A Python/Pytorch app for easily synthesising human voices

Source code for Twitter's Recommendation Algorithm

🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications

Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.