Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
Awesome-LLM-RAG-Application
the resources about the application based on LLM with RAG pattern
https://github.com/lizhe2004/Awesome-LLM-RAG-Application
- 论文：Retrieval-Augmented Generation for Large Language Models: A Survey
- 面向大语言模型的检索增强生成技术：调查
- Github repo
- 大语言模型的检索增强生成 (RAG) 方法
- Advanced RAG Techniques: an Illustrated Overview
- 中译版 高级 RAG 技术：图解概览
- 高级RAG应用构建指南和总结
- Patterns for Building LLM-based Systems & Products
- 构建LLM系统和应用的模式
- RAG大全
- 中译版
- Open RAG Base
- 一个繁体的RAG资料集
- Microsoft-Retrieval Augmented Generation (RAG) in Azure AI Search
- **微软**-Azure AI 搜索之检索增强生成（RAG）
- **azure** openai design patterns- RAG
- IBM-What is retrieval-augmented generation-IBM
- **IBM**-什么是检索增强生成
- **Amazon**-Retrieval Augmented Generation (RAG)
- Nvidia-What Is Retrieval-Augmented Generation?
- **英伟达**-什么是检索增强生成
- Meta-Retrieval Augmented Generation: Streamlining the creation of intelligent natural language processing models
- **Meta**-检索增强生成：简化智能自然语言处理模型的创建
- **Cohere**-Introducing Chat with Retrieval-Augmented Generation (RAG)
- **Pinecone**-Retrieval Augmented Generation
- **Milvus**-Build AI Apps with Retrieval Augmented Generation (RAG)
- Knowledge Retrieval Takes Center Stage
- 知识检索成为焦点
- Disadvantages of RAG
- RAG的缺点
- Retrieval-Augmented Generation (RAG) or Fine-tuning — Which Is the Best Tool to Boost Your LLM Application?
- RAG还是微调，优化LLM应用的最佳工具是哪个？
- RAG vs Finetuning — Which Is the Best Tool to Boost Your LLM Application?
- RAG 与微调 — 哪个是提升优化 LLM 应用的最佳工具？
- A Survey on In-context Learning
- LangChain
- langchain4j
- LlamaIndex
- GPT-RAG
- QAnything
- Quivr
- Quivr
- Dify
- Verba
- danswer
- RAGFlow
- Cognita
- Unstructured
- Open Parse
- ExtractThinker
- OmniParser
- python-readability
- firecrawl
- jina-reader
- nougat
- Pix2Struct
- semantic-router
- ragas
- tonic_validate
- deepeval
- trulens
- uptrain
- langchain-evaluation
- Llamaindex-evaluation
- BCEmbedding
- BGE-Embedding
- bge-reranker-large
- gte-base-zh
- NeMo-Guardrails
- Guardrails
- Guardrails Hub
- LLM-Guard
- Llama-Guard
- RefChecker
- YiVal
- vanna
- OpenLLM
- llamaindex-可观测性
- langfuse
- phoenix
- openllmetry
- lunary
- RAGxplorer
- Rule-Based-Retrieval
- instructor
- Kimi Chat
- GPTs
- 百川知识库
- COZE
- Devv-ai
- Retrieval Augmented Generation: Streamlining the creation of intelligent natural language processing models
- Lost in the Middle: How Language Models Use Long Contexts
- 论文-设计检索增强生成系统时的七个故障点
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
- RankGPT Reranker Demonstration (Van Gogh Wiki)
- Bridging the Preference Gap between Retrievers and LLMs
- Tuning Language Models by Proxy
- Zero-Shot Listwise Document Reranking with a Large Language Model
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity
- Corrective Retrieval Augmented Generation
- 纠正检索增强生成
- RAPTOR：递归抽象处理用于树组织检索
- 在上下文中学习用于极端多标签分类
- 从分类到生成：洞察跨语言检索增强的 ICL
- 链式笔记：增强检索增强语言模型的鲁棒性
- 通过标记消除优化检索增强阅读器模型
- 知识增强语言模型验证
- 大型语言模型在检索增强生成中的基准测试
- 自我反思检索增强生成: 通过自我反思学习检索、生成及自我批判
- 零样本信息检索中的GAR与RAG相结合的新范式
- InstructRetro: 检索增强预训练后的指令式微调
- 检索增强的双重指令微调 (RA-DIT)
- 让基于检索增强的语言模型对无关上下文更加鲁棒
- 当检索遇上长上下文的大语言模型
- RECOMP: 用压缩和选择性增强提升检索增强语言模型
- 检索与生成的协同作用加强了大语言模型的推理能力
- 利用检索增强大语言模型回答含糊问题的“澄清树”方法
- 借助自我知识的大语言模型检索增强策略
- RAGAS: 对检索增强生成进行自动化评估的指标体系
- 生成而非检索：大型语言模型作为强大的上下文生成器
- 提升 Haystack 中 RAG 系统的能力：DiversityRanker 和 LostInTheMiddleRanker 的引入
- KnowledGPT: 利用知识库检索和存储功能增强大型语言模型
- RAVEN: 借助检索增强编解码器语言模型实现的上下文学习
- RaLLe: 针对检索增强大型语言模型的开发和评估框架
- 中途迷失：大型语言模型处理长篇上下文的方式
- 通过迭代检索-生成协同增强检索增强的大语言模型
- 主动检索增强生成
- 适应增强型检索器改善大语言模型的泛化作为通用插件
- 结构感知的语言模型预训练改善结构化数据上的密集检索
- 知识链：通过动态知识适应异质来源来基础大语言模型
- 用于知识基础对话生成的知识图谱增强大语言模型
- 为检索增强的大语言模型重写查询
- 自我提升：带有自我记忆的检索增强文本生成
- 用参数知识引导增强大语言模型
- RET-LLM：朝向大语言模型的通用读写记忆
- 针对非知识密集型任务的提示引导检索增强
- UPRISE：改进零样本评估的通用提示检索
- 大语言模型不是一个理想的少样本信息提取器，但它在重排难样本方面表现出色！
- 无需相关标签的精确零样本密集检索
- 通过检索和语言模型组合，为复杂的自然语言处理任务提供解决方案
- 结合思维链条推理和信息检索解决复杂多步骤问题
- 大语言模型在学习长尾知识方面的挑战
- 通过回忆增强语言模型的能力
- Promptagator: 基于少量示例实现密集检索
- Atlas: 借助检索增强型语言模型进行少样本学习
- 重新认识训练数据的价值：通过训练数据检索的简单有效方法
- 通过自动机增强检索的神经符号语言建模
- 通过从数万亿 Token 中检索来改善语言模型
- 用于零样本槽填充的鲁棒检索增强生成
- 用于知识密集型 NLP 任务的检索增强生成
- 用于开放域问答的密集段落检索
- From Good to Great: How Pre-processing Documents Supercharges AI’s Output
- 从好到优秀：如何预处理文件来加速人工智能的输出
- Advanced RAG 02: Unveiling PDF Parsing
- Advanced RAG 07: Exploring RAG for Tables
- 5 Levels Of Text Splitting
- Semantic Chunker
- Advanced RAG 05: Exploring Semantic Chunking
- Advanced RAG series: Indexing
- Advanced RAG 06: Exploring Query Rewriting
- Advanced RAG 11: Query Classification and Refinement
- Advanced RAG Series:Routing and Query Construction
- Query Transformations
- 基于LLM的RAG应用的问句转换的技巧（译）
- Query Construction
- 查询构造
- Advanced RAG Series - Query Translation
- Improving Retrieval Performance in RAG Pipelines with Hybrid Search
- 在 RAG 流程中提高检索效果：融合传统关键词与现代向量搜索的混合式搜索技术
- Multi-Vector Retriever for RAG on tables, text, and images
- 针对表格、文本和图片的RAG多向量检索器
- Relevance and ranking in vector search
- 向量查询中的相关性和排序
- Boosting RAG: Picking the Best Embedding & Reranker models
- 提升优化 RAG：挑选最好的嵌入和重排模型
- Azure Cognitive Search: Outperforming vector search with hybrid retrieval and ranking capabilities
- Azure认知搜索:通过混合检索和排序功能优于向量搜索
- Optimizing Retrieval Augmentation with Dynamic Top-K Tuning for Efficient Question Answering
- 动态 Top-K 调优优化检索增强功能实现高效的问答
- Building Production-Ready LLM Apps with LlamaIndex: Document Metadata for Higher Accuracy Retrieval
- 使用 LlamaIndex 构建生产就绪型 LLM 应用程序：用于更高精度检索的文档元数据
- dvanced RAG Series: Retrieval
- Advanced RAG 04: Re-ranking
- RankGPT Reranker Demonstration
- How to Cut RAG Costs by 80% Using Prompt Compression
- LangChain Contextual Compression
- Advanced RAG 09: Prompt Compression
- Bridging the rift in Retrieval Augmented Generation
- Evaluating RAG Applications with RAGAs
- 用 RAGAs（检索增强生成评估）评估 RAG（检索增强型生成）应用
- Best Practices for LLM Evaluation of RAG Applications
- RAG应用的LLM评估最佳实践（译）
- Advanced RAG 03: Using RAGAs + LlamaIndex for RAG evaluation
- Exploring End-to-End Evaluation of RAG Pipelines
- 探索 RAG 管道的端到端评估
- Evaluating Multi-Modal Retrieval-Augmented Generation
- 评估多模态检索增强生成
- RAG Evaluation
- RAG评估
- Evaluation - LlamaIndex
- 评估-LlamaIndex
- Pinecone的RAG评测
- zilliz:Optimizing RAG Applications: A Guide to Methodologies, Metrics, and Evaluation Tools for Enhanced Reliability
- Advanced RAG Series: Generation and Evaluation
- Let’s Talk About LLM Hallucinations
- 谈一谈LLM幻觉
- 短课程 Building and Evaluating Advanced RAG Applications
- Retrieval Augmented Generation for Production with LangChain & LlamaIndex
- A Survey of Techniques for Maximizing LLM Performance
- How do domain-specific chatbots work? An overview of retrieval augmented generation (RAG)
- 文字版
- nvidia:Augmenting LLMs Using Retrieval Augmented Generation
- How to Choose a Vector Database
- 构建企业级AI助手的经验教训
- How to build an AI assistant for the enterprise
- Large Language Model (LLM) Disruption of Chatbots
- 大型语言模型 （LLM）对聊天机器人的颠覆
- Gen AI: why does simple Retrieval Augmented Generation (RAG) not work for insurance?
- 生成式AI:为什么RAG在保险领域起不了作用？
- OpenAI 如何优化 LLM 的效果
- End-to-End LLMOps Platform
- ![Star History Chart - history.com/#lizhe2004/Awesome-LLM-RAG-Application&Date)
Programming Languages
Keywords
llm
17
llmops
11
ai
8
python
8
rag
8
openai
7
machine-learning
5
generative-ai
4
nlp
3
information-retrieval
3
langchain
3
nextjs
3
gpt-4
3
gpt
3
monitoring
3
ml
3
llama
3
prompt-engineering
3
chatgpt
3
large-language-models
3
document-parser
3
retrieval-augmented-generation
3
mlops
3
deep-learning
3
ocr
3
model-monitoring
2
fine-tuning
2
agent
2
open-source
2
observability
2
llms
2
preprocessing
2
evaluation-metrics
2
evaluation-framework
2
gpt-3
2
llama2
2
typescript
2
data-pipelines
2
pdf-to-text
2
llm-eval
2
orchestration
2
data-visualization
1
openllm
1
stablelm
1
stable-diffusion
1
promptengineering
1
prompt-tuning
1
prompt
1
midjourney
1
gpt4
1