Open-source vector similarity search for Postgres

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

Wren Engine is the backbone of the WrenAI project - The semantic engine for LLMs, bringing business context to AI agents.

Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23

HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents.

WrenAI makes your database RAG-ready. Implement Text-to-SQL more accurately and securely.

Create LLM agents with long-term memory and custom tools 📚🦙

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。

Self-organizing AI note-taking app that runs models locally.

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

The official code for “Deep Unrestricted Document Image Rectification”, TMM, 2023.

基于大模型搭建的微信聊天机器人，同时支持微信、企业微信、公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/GLM-4/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain（本地/llm）/chatglm/text-generation-webui/闻达/文心一言】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/斗鱼/YouTube/twitch】 直播中与观众实时互动 或 直接在本地进行聊天。它使用文…

DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

An Autonomous LLM Agent for Complex Task Solving

基于Qt的Live2d桌面模型程序，show live2d By Qt。

Revolutionizing Database Interactions with Private LLM Technology

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

Leveraging large language models for text-to-SQL synthesis, this project fine-tunes WizardLM/WizardCoder-15B-V1.0 with QLoRA on a custom Spider training dataset. The resultant model, achieves 61% e…

ML-powered speech recognition directly in your browser

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

FastGPT is a knowledge-based question answering system built on the LLM. It offers out-of-the-box data processing and model invocation capabilities. Moreover, it allows for workflow orchestration t…

One API for plugins and datasets, one interface for prompt engineering and visual operation, all for creating powerful AI applications.

OpenAI's Code Interpreter in your terminal, running locally

Tiny, structured coding tutorials that can be searched semantically.