RAG
Retrieval-Augmented Generation (RAG) is an AI technical framework that combines information retrieval with the generative capabilities of large language models. Its core mechanism involves retrieving relevant documents or passages from an external knowledge base before generating a response, and providing them as context to the model. This allows the model to draw on current or domain-specific knowledge, effectively mitigating hallucination issues and knowledge cutoff limitations inherent in large language models.
Core Facts
The core idea of RAG is to retrieve relevant information from an external knowledge base as context to inject into the prompt before the large model generates a response.
The core of GraphRAG is integrating knowledge graphs into the traditional RAG pipeline, organizing information in the form of triples (two entities and their relationship).
Prompt注入（Prompt Injection）是针对大语言模型应用的安全威胁，攻击者通过在输入中嵌入恶意指令试图覆盖系统原有行为约束
Timeline (last 90 days)
Localized RAG deployment (documents do not leave the local environment, models run locally) can keep privacy-sensitive internal materials from having to be uploaded to third parties.
Current mainstream RAG implementations mostly use vector databases to perform dense retrieval over unstructured text, while their retrieval support for structured data sources such as tables and relational databases is relatively weak.
Long-context models do not necessarily replace RAG: retrieval is still needed when the corpus far exceeds 1M tokens.
Interviewers may ask questions such as 'What is a vector database?', 'How does RAG mount a knowledge base?', and 'What is MCP?', which have become must-ask questions for large-model-oriented positions.
There are two common approaches for a paper knowledge base: pasting or uploading the literature directly into a chat window that supports long context, or using a tool that supports file upload or RAG to let the model retrieve literature excerpts.
Common approaches to mitigating citation-type hallucinations include retrieval-augmented generation (RAG), mandatory source citation, and rule-based validation of key fields.
WorkBuddy's knowledge base feature is based on RAG technology; after users upload their own materials, the AI prioritizes reading from these materials when answering questions.
Hallucination refers to content generated by large language models that appears plausible but does not match facts or the given context; in RAG systems it can be divided into two types: retrieval failure and lack of faithfulness.
Search engines return a ranked list of candidates, and users can see the 2nd, 5th and 10th results, whereas RAG systems only fuse retrieved snippets into a coherent passage, and the fusion process itself is a round of information filtering.
RAG retrieves external knowledge bases in real time and places the relevant content into the prompt, avoiding writing knowledge into the model parameters.
40 more timeline events
All Facts (20)
The core idea of RAG is to retrieve relevant information from an external knowledge base as context to inject into the prompt before the large model generates a response.
90%VerifiedThe core of GraphRAG is integrating knowledge graphs into the traditional RAG pipeline, organizing information in the form of triples (two entities and their relationship).
90%VerifiedPrompt注入（Prompt Injection）是针对大语言模型应用的安全威胁，攻击者通过在输入中嵌入恶意指令试图覆盖系统原有行为约束
90%VerifiedLlamaIndex (formerly GPT Index) focuses on data indexing and Retrieval-Augmented Generation (RAG) scenarios.
90%VerifiedRAG（检索增强生成）架构由 Meta AI 研究团队在 2020 年提出
90%VerifiedCursor's AI agent capability uses RAG (Retrieval-Augmented Generation) technology to inject relevant code context into large language models to achieve precise task execution.
90%VerifiedThe typical workflow of RAG (Retrieval-Augmented Generation) consists of four steps: document chunking, vector embedding, similarity search, and context injection.
90%Verified混合检索（Hybrid Search）将向量检索与BM25关键词检索的结果通过RRF（倒数排名融合）等算法合并，兼顾语义理解与精确匹配
90%VerifiedPerplexity AI's underlying architecture uses RAG (Retrieval-Augmented Generation) technology, crawling web content in real time and combining it with LLM output to produce structured answers with cited sources.
90%VerifiedRAG（检索增强生成）技术架构将文档切片、向量化、存入向量数据库，查询时先检索相关片段再交给模型生成回答
90%VerifiedParametric knowledge refers to the implicit memory compressed into the weight parameters of a language model during pre-training, while non-parametric knowledge refers to knowledge retrieved at inference time.
85%VerifiedRetrieval-Augmented Generation (RAG) anchors facts by incorporating real-time web search with cited sources, but its effectiveness is influenced by factors such as search result quality, document parsing accuracy, and the model's comprehension capability.
85%VerifiedThe answer quality of RAG depends largely on the retrieval step rather than on the model's capabilities themselves.
85%VerifiedThe core logic of RAG is to slice documents and store them as vectors, then retrieve relevant fragments through semantic similarity at query time and inject them into the context.
85%VerifiedAI evaluation targets are divided into three layers—large language model evaluation, knowledge base (RAG) evaluation, and agent (Agent) evaluation—forming a progressive relationship of increasing complexity and knowledge depth.
80%VerifiedRAG (Retrieval-Augmented Generation) solutions based on vector databases are better suited for handling document-type knowledge, but often fall short in retrieval precision and real-time performance for highly structured engineering facts.
80%VerifiedThe working principle of RAG is divided into a retrieval phase (converting the question into a vector to recall relevant content from the knowledge base) and a generation phase (inputting the recalled context together with the question into the model to produce an answer).
80%VerifiedThe RAG workflow is divided into offline and online phases: offline, documents are chunked and converted into vectors stored in a vector database; online, questions are converted into vectors and the most similar text segments are retrieved via ANN algorithms and concatenated into the context.
80%VerifiedThe RAG mechanism fundamentally mitigates the hallucination problem of LLMs, grounding responses in the content of real knowledge bases and providing traceable sources.
80%VerifiedRAG (Retrieval-Augmented Generation) enables an Agent to retrieve relevant information before answering by building an external knowledge base, thereby overcoming the limitations of the model's training data.
80%