PaperPass官网-论文查重-论文降重-论文检测-免费论文查重检测系统-智齿数汇
毕设
MinerU/README_zh-CN.md at master · opendatalab/MinerU
代理机构 RAG --- Agentic RAG
RAG 源码
Mistral OCR: World's Best Document Understanding API
z
Basic RAG | Mistral AI Large Language Models
这家有着据说目前最强的 OCR,不过没有开源。 这篇文章是 RAG 的
%E6%9C%AC%E5%9C%B0%E9%83%A8%E7%BD%B2%E6%9C%80%E5%BC%BAOCR%E5%A4%A7%E6%A8%A1%E5%9E%8BolmOCR%EF%BC%81%E6%94%AF%E6%8C%81%E7%BB%93%E6%9E%84%E5%8C%96%E7%B2%BE%E5%87%86%E6%8F%90%E5%8F%96%E5%A4%8D%E6%9D%82PDF%E6%96%87%E4%BB%B6%E5%86%85%E5%AE%B9%EF%BC%81%E5%AE%8C%E7%BE%8E%E8%AF%86%E5%88%AB%E4%B8%AD%E8%8B%B1%E6%96%87%E6%96%87%E6%A1%A3%E3%80%81%E6%A8%A1%E7%B3%8A%E6%89%AB%E6%8F%8F%E4%BB%B6%E4%B8%8E%E5%A4%8D%E6%9D%82%E8%A1%A8%E6%A0%BC%EF%BC%81%E6%9C%AC%E5%9C%B0%E9%83%A8%E7%BD%B2%E4%B8%8E%E5%AE%9E%E9%99%85%E6%B5%8B%E8%AF%95%E5%85%A8%E8%BF%87%E7%A8%8B%EF%BC%81%E5%8C%BB%E7%96%97%E6%B3%95%E5%BE%8B%E8%A1%8C%E4%B8%9A%E5%BF%85%E5%A4%87
OCR
prompt-optimizer/packages/core/src/services/template/defaults.ts at 964a8676fc29279613d8774ea1e195c5a0c93d7e · linshenkx/prompt-optimizer
prompt 优化步骤
stepfun-ai/GOT-OCR-2.0-hf · Hugging Face
看起来很牛逼的 OCR
facebookresearch/nougat: Implementation of Nougat Neural Optical Understanding for Academic Documents
PDF OCR
baehyunsol/ragit: git-like rag pipeline
SaiAkhil066/DeepSeek-RAG-Chatbot: 100 % FREE, Private (No Internet) DeepSeek’s Advanced RAG: Boost Your RAG Chatbot: Hybrid Retrieval (BM25 + FAISS) + Neural Reranking + HyDe🚀
README.md
日语群群友的示例 RAG 代码
GitHamza0206/simba: Portable KMS (knowledge management system) designed to integrate seamlessly with any Retrieval-Augmented Generation (RAG) system
Cinnamon/kotaemon: An open-source RAG-based tool for chatting with your documents.
本地 RAG
rag-web-ui/rag-web-ui: RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.
agno-agi/agno: Agno is a lightweight framework for building multi-modal Agents
成熟的 pdf 索引 RAG
ocrmypdf/OCRmyPDF: OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
bosun-ai/swiftide: Fast, streaming indexing, query, and agent library for building LLM applications in Rust
chroma-core/chroma: the AI-native open-source embedding database
嵌入数据库,封装好的,可以做数据存储部分
deepseek-ai/DeepSeek-V3
phidatahq/phidata: Build multi-modal Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.
IntelLabs/RAG-FiT: Framework for enhancing LLMs for RAG tasks using fine-tuning.
(15 封私信 / 87 条消息) 大模型知识库rag框架,比如langchain chatchat,fastgpt等等,哪个效果比较好? - 知乎
好心得,基本把技术栈都讲完了
rustsbi/Agent: RustSBI Specialized Domain Knowledge Quiz LLM