"LightRAG: Simple and Fast Retrieval-Augmented Generation"

📃 A better UX for chat, writing content, and coding with LLMs.

GLM-4-Voice | 端到端中英语音对话模型

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

Document (PDF) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

Use ChatGpt 4o forFree - No API Key Need. also ChatGpt 3 and ChatGpt 3.5 Experience the power of ChatGPT with a user-friendly interface, enhanced jailbreaks, and completely free.

Azure OpenAI code resources for using gpt-4o-realtime capabilities.

Large Reasoning Models

The world's smartest system-wide grammar assistant; a better version of the Apple Intelligence Writing Tools. Works with the free Gemini API, local LLMs, and other cloud providers.

实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

Chat with your documents using Vision Language Models. This repo implements an End to End RAG pipeline with both local and proprietary VLMs

Parsing-free RAG supported by VLMs

Official code for paper: Chain of Ideas: Revolutionizing Research via Novel Idea Development with LLM Agents

PDF 生成中文播客

Python API client for AI providers that intends to replace LangChain and LangGraph for most common use cases.

PearAI acts as an inventory that curates the leading, cutting-edge AI tools in one place. We build a centralized user interface for these solutions, allowing you to effortlessly use the best AI tools without having to waste effort looking for alternatives. This repository lists all the other repos that make up the entire PearAI project.

Engy is an AI-powered development tool that generates fully functional web applications from natural language, streamlining the process from idea to working prototype.

Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI

Generate large synthetic data using a local LLM

🤠 Agent-as-a-Judge and DevAI dataset

Codai is an AI code assistant that helps developers through a session-based CLI, providing intelligent code suggestions, refactoring, and code reviews based on the full context of the project. It supports multiple LLMs, including GPT-4o, GPT-4, and Ollama, to streamline daily development tasks.

JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.

The official implementation of the paper "AgentSquare: Automatic LLM Agent Search in Modular Design Space""

Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

aider emacs plugin for https://github.com/paul-gauthier/aider

An easy-to-understand framework for LLM samplers that rewind and revise generated tokens

Write and execute jq programs with the help of LLM

For LLMs to better code with Jina API

A command-line personal assistant that integrates with Google Calendar, Gmail, and Tasks to help manage your digital life.

Chat UI components for LLM apps

Vim plugin for LLM-assisted code/text completion

An Open Source implementation of Notebook LM with more flexibility and features

Text to Shorts/Tiktoks, AI Video Engine

A GitHub Action that automatically reviews pull requests using Google's Gemini AI.

[arXiv 2024] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".

Hands-on tutorials on fine-tuning various LLMs using different fine-tuning techniques

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

LearnGo, a ios versatile learning tool with RAG and Prompting under LLM like GPT-4o-mini, enabling subject Q&A, smart note generation from uploaded materials, offline photo(or AR) object recognition with translations, and multilingual voice input (Cantonese, English, Mandarin). It also features customizable themes for a personalized experience

💬 AI Chat Bot demo app showcasing the integration of Gemini SDK with Firebase Realtime Database for real-time chat functionality.

The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".

A replication of Andy Ayrey's "Backrooms" (https://dreams-of-an-electric-mind.webflow.io/), but runnable with Opus 3, Sonnet 3.5, GPT 4o, and o1-preview

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

This repo contains the code and data for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks"

[CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding

Ollama client written in Python

A Ruby gem for seamlessly and uniformly interacting with large language and vision model (LLM) API's served by numerous services, including those of OpenAI, Anthropic, Google and others.

Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"

An introduction to LLM Sampling

This is a tool that can automatically translate the chat log into a note using LLM API

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models

Official Implementation of "Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models".

MagicPIG: LSH Sampling for Efficient LLM Generation

Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" proposed by Peking University and UC Berkeley.

[NeurIPS 2024] SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation

NotebookLlama powered by Groq - Create podcasts on any topic lightning fast

Open source AI analyst powered by E2B. Analyze your CSV files with Llama 3.1 and create interactive charts.

HTTP proxy for on-demand model loading with llama.cpp (or other OpenAI compatible backends)

OpenAI o1 advanced reasoning powered vulnerable web page generator for testing and educational purposes

PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model similar to large language models (LLMs). The architecture incorporates a novel Differential Attention mechanism, Multi-Head structure, RMSNorm, and SwiGLU.

Free AI & Community powered Learning Experience

This repository is for the paper entitled: From News to Forecast: Integrating Event Analysis in LLM-based Time Series Forecasting with Reflection (NeurIPS 2024)

Chat with your pdf using your local LLM, OLLAMA client.

Accelerating your LLM training to full speed

Contextual Doc Retrieval is a Python-based system leveraging OpenAI GPT-4o and Cohere for re-ranking and query expansion, combined with BM25 for accurate document retrieval. It parses PDFs, chunks content contextually, and enhances search precision with AI-powered contextual understanding and re-ranking.

Official Code for SyllableLM: Learning Coarse Semantic Units for Speech Language Models

Official implementation of "GPT or BERT: why not both?"

Chat with PDF using Llama 3.2

A native macOS app that allows users to chat with a local LLM with context of your files, folders and websites on your Mac without installing any other software.

A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability

Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."

Official repository for Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning

Frontend Engine Extension for Stable Diffusion Web UI and Stable Diffusion Web UI Forge.

🌾 OAT: Online AlignmenT for LLMs

Human Demo Videos to Robot Action Plans

Codebase for the paper-Elucidating the design space of language models for image generation

Graphy v1: A Realtime GraphRAG App using Langchain, Neo4j, GPT-4o, and Streamlit.

Screenshot LLM is a Python application that leverages the power of AI to analyze screenshots. Built with PyQt6 for a user-friendly interface and integrating with various AI models (including Ollama), it provides insightful information directly from images.

Code & Dataset for Paper: "Distill Visual Chart Reasoning Ability from LLMs to MLLMs"

This repository provides an improved LLamaGen Model, fine-tuned on 500,000 high-quality images, each accompanied by over 300 token prompts. And it's also powered by additional prompt refining features for improved performance.

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering

An LLM-powered programming-by-example programming language.

Execute chains of LLM models and actions

A growing list of fake podcasts generated by Notebook LM

Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision

Capture webcam via browser, generate text descriptions with Google Gemini, generate speech with ElevenLabs

Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval

Compose Multiplatform sample that uses the Firebase Vertex AI SDKs

DuckDB Community Extension to prompt LLMs from SQL

Splicing: Gen-AI Copilot for Data Engineering

A unified client for seamless interaction with multiple AI providers.

MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for LLMs.

Exploration into leveraging vision capabilities of an LLM

Use XML tags for long context prompting using Claude's multi-document structure.