asgeirtj/system_prompts_leaks
This repository provides a collection of extracted system prompts from various large language models (LLMs) including Anthropic's Claude, OpenAI's ChatGPT, Google's Gemini, and xAI's Grok, updated ...
Awesome AI Agents › Prompt Libraries
HKUDS/RAG-Anything
RAG-Anything is an advanced all-in-one Retrieval-Augmented Generation (RAG) system designed to handle the complexities of modern multimodal documents. Unlike traditional RAG systems that primarily focus on text, RAG-Anything supports a wide range of content types including text, images, tables, mathematical equations, charts, and multimedia. This makes it a comprehensive solution for processing and querying documents with diverse and interleaved content modalities within a single unified framework. The system is built on top of LightRAG and integrates cutting-edge AI technologies to provide seamless multimodal document processing and intelligent query answering. The system features an end-to-end multimodal pipeline that covers the entire workflow from document ingestion and parsing to content analysis, knowledge graph construction, and intelligent retrieval. It supports universal document formats such as PDFs, Office documents, and images, ensuring broad applicability across different domains. Specialized processors analyze heterogeneous content types, enabling detailed understanding and extraction of information from complex documents. A key innovation of RAG-Anything is its multimodal knowledge graph, which automatically extracts entities and discovers cross-modal relationships to enhance the system's comprehension and retrieval capabilities. The system offers adaptive processing modes, including MinerU-based parsing for high-fidelity document structure extraction and direct multimodal content injection workflows. Its hybrid intelligent retrieval mechanism allows advanced search across textual and multimodal content with contextual awareness. RAG-Anything is particularly valuable for academic research, technical documentation, financial reports, and enterprise knowledge management where documents contain rich mixed content. By eliminating the need for multiple specialized tools, it provides a unified interface for querying and interacting with complex multimodal documents. The architecture involves a multi-stage pipeline including document parsing, content analysis, knowledge graph construction, and intelligent retrieval, orchestrated to deliver next-generation multimodal intelligence.
https://github.com/HKUDS/RAG-Anything
Also in Prompt Libraries
dzhng/deep-research
Open Deep Research is an AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models to generate comprehensive markdown reports.
dottxt-ai/outlines
Outlines is an open-source tool that enables structured text generation with large language models, ensuring predictable and schema-compliant outputs for various applications.
microsoft/RD-Agent
RD-Agent is an open-source R&D automation tool by Microsoft designed to automate and enhance industrial research and development processes focused on data and models using AI.
arcee-ai/mergekit
mergekit is a toolkit for efficiently merging pre-trained large language models using various algorithms, supporting CPU and GPU execution, and enabling creation of versatile merged models with maintained inference costs.
icip-cas/PPTAgent
PPTAgent is an innovative system that automatically generates and evaluates high-quality presentations from documents using a two-phase approach and a comprehensive multi-dimensional evaluation framework.
serenakeyitan/awesome-notebookLM-prompts
A curated collection of NotebookLM and Kael.im slide prompts designed to generate presentation-ready decks from various content types.
snap-stanford/Biomni
Biomni is a general-purpose biomedical AI agent that autonomously executes diverse research tasks across multiple biomedical subfields by integrating advanced LLM reasoning, retrieval-augmented planning, and code-based execution.