📃 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

Large Reasoning Models

Unifying 3D Mesh Generation with Language Models

Parsing-free RAG supported by VLMs

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

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.

Generate large synthetic data using an LLM

🤠 Agent-as-a-Judge and DevAI dataset

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

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

For LLMs to better code with Jina API

Chat UI components for LLM apps

AI toolkit for making Shorts/Tiktoks

Vim plugin for LLM-assisted code/text completion

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

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

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.

An introduction to LLM Sampling

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

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

MagicPIG: LSH Sampling for Efficient LLM Generation

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

[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective

Accelerating your LLM training to full speed

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

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

ApolloMoE: Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts

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

Benchmarking Agentic LLM and VLM Reasoning On Games

🌾 OAT: Online AlignmenT for LLMs

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

Human Demo Videos to Robot Action Plans

End-to-End Navigation with VLMs

A growing list of fake podcasts generated by Notebook LM

DuckDB Community Extension to prompt LLMs from SQL

Exploration into leveraging vision capabilities of an LLM

Splicing: Gen-AI Copilot for Data Engineering

Document parser for RAG

[EMNLP 2024 Findings] ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

Unofficial entropix impl for Gemma2 and Llama and Qwen2 and Mistral

This is the public code repository for the paper 'Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models'

This is an opensource project allowing you to compare two LLM's head to head with a given prompt, this section will be regarding the backend of this project, allowing for llm api's to be incorporated and used in the front-end

Open Source multi-modal LLM environment. Host your own web and mobile chat interface, powered by real-time bots and voice AI functionality.

TensorRT-LLM server with Structured Outputs (JSON) built with Rust

This repository contains a series of samples on how to analyse a video using multimodal Large Language Models, like GPT-4o or GPT-4o-mini.

TrafficJamAnalyzer is an advanced tool designed to help monitor and analyze traffic conditions by processing images from CCTV cameras around the roads of Tenerife. By utilizing artificial intelligence (AI) with Semantic Kernel and OpenAI, the application accurately assesses traffic density and identifies locations with potential traffic jams.

Code for the paper: Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping

Code for the paper "Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation"

BehAV: Behavioral Rule Guided Autonomy Using VLM for Robot Navigation in Outdoor Scenes

The code, data, and models for "Teach Multimodal LLMs to Comprehend Electrocardiographic Images".

基于 Yunzai 的 AIGC 插件，可免费使用 FLUX、SD、MJ 等绘图、LLM 推理、Vits语音合成等。

Arduino library for M5Stack LLM Module

DuckDuckGo AI to OpenAI API

Enhance and modify high-quality compositions using real-time rendering and generative AI output without affecting a hero product asset.

A Python-based AWS solution for automated Jira ticket classification using Amazon Bedrock. This project helps Jira users automate ticket categorization featuring S3 integration, AWS Glue deduplication, LLMs, and Terraform deployment.

NeurIPS'24 - LLM Safety Landscape

Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions

This project provides tools to load and prune large language models using a structured pruning method.

The repository for the LlamaIndex RAG-A-THON 2024 Workshop by AI Makerspace

(WIP) 🦀 An Insanely Fast 🚀 Full Stack Content Generation SaaS Platform Powered by Dioxus, Dioxus Server Functions, Axum, Unsplash, Gemini AI & MongoDB.

An LLM-based app to easily track calories and exercise by taking a photo of your meal or describing your physical activity

LLM for Scientific Research Survey

Iterates on problem via LLM until it finishes

Paper: Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

Nodes for Google Gemini API

Wordpres Chatbot Plugin for Hexabot.ai Live Chat Widget.

A library to compress codebases so much that LLMs can reason through them 100x faster

Repository for the LMS (Last Man Standing) web application developed by Team 1 in CS4337 Big Data Management Module

D-Lab's 1-hour introduction to using LLMs for exploratory research.

REST API for computing cross-modal similarity between images and text using the ColPaLI vision-language model

2024-oct-4-responsible-llm-hackathon-team-cockatiel created by GitHub Classroom

Open source platform for building AI agents

Materials of 2024 Fall cross-lingual visual language models block seminar at LMU Munich.

Python project to convert PDFs/images into an audio file using OpenAI's GPT-4o and TTS-1 models.

Class at Caltech on LLMOps by Brian Ray

The Ollama Plugin Extension for Hexabot Chatbot / Agent Builder that provides a custom block for Generative AI + RAG

Multi agent LLM in-depth researcher

Backend to a custom GPT that can be used to answer queries about your AWS account

Focus on the generation of demonstration animations for mathematics, statistics, etc., based on the Llama large model.

A text to Podcast inference API

GRAMI-AI is a cutting-edge, async-first AI agent framework designed to solve complex computational challenges through intelligent, collaborative agent interactions. Built with unprecedented flexibility, this library empowers developers to create sophisticated, context-aware AI systems that can adapt, learn, and collaborate across diverse domains.

A C# sample of chatting with uploaded images using OpenAI vision models like gpt-4o.

Helpers and Source generator to define OpenAI/Ollama/Anthropic/Gemini/LangChain tools natively through C# interfaces and without Reflection