TowardSun

MemGPT

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

pre-commit-hooks

Some out-of-the-box hooks for pre-commit

buffer-of-thought-llm

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

MobileAgent

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

R2R

R2R is an open source RAG engine with a RESTful API. Features include hybrid search, GraphRAG, multimodal RAG, observability and analytics, and more.

FinQwen

FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目，基于大模型搭建金融场景智能问答系统，利用开源开放来促进「AI+金融」。

LaWGPT

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

SoulChat

中文领域心理健康对话大模型SoulChat

trafilatura

Python & command-line tool to gather text on the Web: Crawling & scraping, content extraction, metadata. TXT, Markdown, CSV & XML output.

llama-lab

RAG-Survey

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

llamafile

Distribute and run LLMs with a single file.

llm-guard

The Security Toolkit for LLM Interactions

dspy

DSPy: The framework for programming—not prompting—foundation models

firecrawl

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

FLARE

Forward-Looking Active REtrieval-augmented generation (FLARE)

ALCE

[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627

llama_parse

Parse files for optimal RAG

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

elasticsearch-labs

Notebooks & Example Apps for Search & AI Applications with Elasticsearch

mteb

MTEB: Massive Text Embedding Benchmark

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

imp

a family of highly capabale yet efficient large multimodal models

llava-phi

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

QAnything

Question and Answer based on Anything.

elasticsearch

Free and Open, Distributed, RESTful Search Engine

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

trulens

Evaluation and Tracking for LLM Experiments