A lightweight, powerful framework for multi-agent workflows

基于Dify自主创建的AI应用DSL工作流，你可以免费获取，无论是出于个人需求还是学习目的，它都能为您开启一段充满无限可能的智能之旅。

分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.

Production-ready platform for agentic workflow development.

Parsing-free RAG supported by VLMs

Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents…

This is RAG Modules Repo. This includes various modules in the RAG ecosystem.

[SIGIR 2024] Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check

RAGChecker: A Fine-grained Framework For Diagnosing RAG

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

Retrieval and Retrieval-augmented LLMs

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

The Triton TensorRT-LLM Backend

The repository for the survey paper <<Survey on Large Language Models Factuality: Knowledge, Retrieval and Domain-Specificity>>

FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

ChatGLM2 support for vLLM

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

开源社区第一个能下载、能运行的中文 LLaMA2 模型！

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A high-throughput and memory-efficient inference and serving engine for LLMs

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

The official GitHub page for the survey paper "A Survey of Large Language Models".

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

4 bits quantization of LLaMA using GPTQ