📃 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

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.

🤠 Agent-as-a-Judge and DevAI dataset

Generate large synthetic data using a local LLM

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.

For LLMs to better code with Jina API

Vim plugin for LLM-assisted code/text completion

Chat UI components for LLM apps

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

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

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

An introduction to LLM Sampling

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

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.

MagicPIG: LSH Sampling for Efficient LLM Generation

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

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

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

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

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

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

🌾 OAT: Online AlignmenT for LLMs

Accelerating your LLM training to full speed

Human Demo Videos to Robot Action Plans

A growing list of fake podcasts generated by Notebook LM

Splicing: Gen-AI Copilot for Data Engineering

DuckDB Community Extension to prompt LLMs from SQL

Exploration into leveraging vision capabilities of an LLM

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

Document parser for RAG

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

Unofficial entropix impl for Gemma2 and Llama and Qwen2 and Mistral

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

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

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

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

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".

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.

Arduino library for M5Stack LLM Module

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

DuckDuckGo AI to OpenAI API

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

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.

NeurIPS'24 - LLM Safety Landscape

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。

LLM for Scientific Research Survey

End-to-End Navigation with VLMs

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

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

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

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.

Nodes for Google Gemini API

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

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

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

A text to Podcast inference API

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

Unity - Google-Gemini

Templates of Japanese colors ( Macha, Azuki, Kinako, Sora )

LLM Tooling

REST API for FatGPT Project which using GPT-4o OpenAI API

The LMOS-Config repo contains a shared config provider for the entire LMOS system.

LMOS-Docs container documentation for all aspects of the LMOS Ecosystem

This project demonstrates how to incorporate AI features (streaming chatbot responses, LLM-generated channel names) into a modern Next.js chat application powered by Stream's Chat SDK.

The Google Gemini Plugin for Hexabot Chatbot / Agent Builder to enable the LLM RAG Capability

The Gemini Helper Extension for Hexabot Chatbot / Agent Builder to enable the LLM RAG Capability

CLI for Hexabot to create projects and run them.

Hexabot Project Starter Template, fork this project to create you own template then create project with `hexabot create --template=username/my-template-repo`

The Ollama Helper Extension for Hexabot Chatbot / Agent Builder to enable the LLM Capability

llama.cpp rust bindings

LLM Models used: The Falcon, LLAMA2, BLOOM, MPT, Vicuna, FLAN-T5, GPT2/GPT3, GPT NEOX BERT 101, Distil BERT FINE-Tuning Small Models under supervision of BIG Models Image Generation : LLAMA models Gemini Dall-E OpenAI Hugging face Models

Slangroom double sided executor

Async Python library for building Google Gemini AI Agents, AI Crew, Powered By AWS.

Multi agent LLM in-depth researcher