跟讀練習: RAG's Evolution: From Simple Retrieval to Agentic AI - 通過影片學習英語口語

選擇練習模式

每種模式都會開啟全屏練習室。

94 句

如果句子過短或過長，請點選 Edit 進行調整。

We've all had this experience.

You search for something, you get thousands of results, and somehow none of them are what you wanted.

Well, what if I told you search engines don't actually understand your questions?

At least, they didn't used to.

From simple keyword search to present -day agentic rag, information retrieval has seen an evolution.

And search engines didn't get smarter overnight.

They grew up one step at a time.

Let's start from the beginning.

The earliest search systems were designed around the question of, where does this word appear?

Documents were indexed using what's called inverted indices, aka a mapping of keywords to documents.

When a user asks a question,

the search system will look up these words and quickly return the matching documents.

These documents may then be ranked using TF -IDF or BM -25 to measure how important or frequent different terms were.

This powerful keyword matching approach still powers a lot of the internet today.

But there's a fundamental limitation.

It doesn't understand language.

It treats words as symbols, not meaning.

Synonyms, ambiguity, and any complex intents were essentially invisible.

For example, is the search help

Python related to coding or did I just get a pet snake?

It was on the user to be asking the right questions with the exact right words.

The next major leap was semantic search.

Instead of treating text as words, we began representing them as language.

This is done using vectors or high dimensional number representations that can understand meaning.

For example, coffee might be represented as 010 versus house might be represented as 100.

These embeddings don't just come out of nowhere.

They are learned by large neural networks trained on massive text corpora.

By encountering words in context, Over time, these similar concepts will end up close together, even if they use different words.

If this is coffee, maybe espresso is represented here.

Very close in concept to coffee, but not anywhere close to house.

Semantic search turns your words into a kind of map, so the system knows espresso and coffee are pointing to a very similar place.

It's essentially your friend who knows what you mean even if you don't say it perfectly every time.

This allowed search systems to understand intent.

Even if the exact keywords were not used, you could still find relevant documents.

And this didn't replace keyword search.

It actually complemented it.

Hybrid systems began to emerge, bridging the precision of keyword search with semantic recall.

For the first time, instead of just matching text, search was able to approximate understanding.

Then the world shifted.

Large language models were born.

These are models trained on a large corpora of text to learn patterns in the data.

LLMs don't retrieve facts. When prompted, they will predict the most likely next token

or words for an answer based on those patterns that they learned from the training data.

The user asks a question to the LLM and it will return a text answer.

These are super powerful and revolutionized the business world.

However, they had a problem.

LLMs only use specific knowledge they learned during a long and expensive training process.

Realistically, that means any knowledge is locked to only the documents

that that specific LLM was trained on before a certain point in time.

LLMs don't know today's information and certainly don't know your specific documents.

So what's the solution?

Well, it's actually search.

Retrieval Augmented Generation or RAG was born.

The idea is very simple.

The user asks a question.

The system does a search for relevant documents using an external knowledge base.

This retrieval is used to augment

The LLM's prompt and a final answer is generated.

This gave LLMs a form of external memory.

Now they could cite sources, adapt to new information, and even operate in specialized domains without the costly retraining.

These original RAG pipelines were very linear.

Documents were embedded offline into these vector databases.

They were retrieved once at query time and passed straight into the model.

It was simple but effective.

This massive improvement significantly dropped hallucinations and enabled LLM adoption across a multitude of new domains.

But traditional RAG is nowhere near perfect.

It cannot adapt to new scenarios.

And suddenly, we are back at the problem of traditional search.

The answer is only as good as the search itself.

Within such a short period, countless advancements were made to RAG, developing the simple concept into a sophisticated power to be reckoned with.

Instead of a single retrieval step, pipelines added re -rankers to reorder results to be more relevant.

User queries were rewritten or expanded upon to improve recall.

Similar to before, hybrid retrieval became the norm,

leveraging the precision of keyword search with semantic vector search.

These systems were far more accurate, but still fundamentally static.

The pipeline was predetermined, and retrieval was smarter, but still not intelligent.

Enter the next disruptor, agents.

Agents are systems that use LLMs and tools to perform tasks autonomously.

Suddenly, we shifted from simple pipelines to complex decision -making systems.

Agents have a variety of tools, such as LLMs, memory, planning,

critics, tactics, retrievers, and many more.

Agents have become autonomous decision makers planning and executing complex tasks.

Now, instead of linear rag retrieval, when the user asks a question, an AI agent will decide whether retrieval is needed,

where to search, what questions should be asked, when enough information is obtained, and then generate a final answer.

Agents can compare sources, validate claims, refine queries, and iterate.

It can invoke APIs, pull data from many knowledge bases, and incorporate multimodal data.

Retrieval is no longer fixed.

It's a tool invoked as part of reasoning.

This opens up a world of possibilities.

Now, agentic rag systems are capable of multi -step research, cross -document synthesis, and general adaptive behavior.

The system doesn't just answer questions, it reasons and figures out how to answer them.

From simple search to current agentic rag, we have learned time and time again that the next big step isn't better answers.

It's systems that know how to find them.

And the hardest part of AI isn't generation, it's deciding what to look at.

下載應用

流利口語所需的一切

AI 發音評分逐句打分

音標練習掌握每個音

詞彙學習建立你的詞庫

詞彙遊戲邊玩邊學

掃碼

Download on theApp Store Get it onGoogle Play

同頻道

FOR YOU

本課的詞彙與口語要點

這節口語課以影片“RAG's Evolution: From Simple Retrieval to Agentic AI”為素材。影片中反覆出現的詞有：search, document, Llm, retrieval, word。這段影片共有 79 個句子、1029 個單詞可供跟讀。講話部分時長為 8:36。說話人語速平穩，每分鐘約 120 個詞，很適合跟讀。只有 77% 的單詞屬於英語最常用的 3,000 詞，詞彙難度較高。

影片中的重點詞彙

影片中 15 個值得學習的單詞，附發音和釋義：

單詞	發音	釋義
pipeline 名詞	/ˈpaɪpˌlaɪn/	管道, 管線 /管線
vector 名詞	/ˈvɛktɚ/	向量, 向量
query 名詞	/ˈkwɪɹ.i/	問題 /問題, 質問 /質問
essentially 副詞	/ɪˈsɛnʃəli/	本質上 /本質上, 基本上
nowhere 副詞	/ˈnoʊ.(h)wɛɹ/	無處 /無處
recall 動詞	/ɹɪˈkɔl/	罷免 /罷免, 召回
domain 名詞	/ˌdəʊˈmeɪ̯n/	領域 /領域
intent 名詞	/ɪnˈtɛnt/	意圖 /意圖
linear 形容詞	/ˈlɪn.i.əɹ/	線性
hybrid 名詞	/ˈhaɪ.bɹɪd/	雜種 /雜種
precision 名詞	/pɹɪˈsɪʒ.ən/	精度, 準確度 /準確度
adapt 動詞	/əˈdæpt/	適應 /適應
retrieve 動詞	/ɹɪˈtɹiːv/	重拾
corpus 名詞	/ˈkɔɹpəs/	語料庫 /語料庫
compare 動詞	/kəmˈpɛɚ/	比, 比較 /比較

影片中出現的短語動詞

單詞	發音	釋義
end up 動詞		到達
figure out 動詞		弄清楚
grow up 動詞		長大 /長大
look up 動詞	/ˌlʊk ˈʌp/	仰, 上看

值得反覆跟讀的句子

影片中簡短而完整的句子，可以直接用在日常對話裡：

We've all had this experience.
Let's start from the beginning.
Related to coding, or did I just get a pet snake?

影片中的語法

說話人最常用的結構，並附上影片中的原話：

結構	影片中的用法
被動語態 be + 過去分詞 — 強調發生了什麼，而不是誰做的	were designed · were indexed · be ranked
現在完成時 have/has + 過去分詞 — 過去發生但與現在仍有關聯的事	has seen · have become · have learned

需要注意的發音

說話人用了 14 次縮略和弱讀形式，例如 don't, didn't, doesn't。請按聽到的簡短形式來說。

“sh” 和 “zh” 音: essentially /ɪˈsɛnʃəli/, precision /pɹɪˈsɪʒ.ən/, evolution /ˌiːvəˈluːʃ(ə)n/, representation /ˌɹɛp.ɹə.zɛnˈteɪ.ʃən/, adoption /əˈdɑp.ʃən/
長單詞——注意重音位置: essentially /ɪˈsɛnʃəli/, evolution /ˌiːvəˈluːʃ(ə)n/, representation /ˌɹɛp.ɹə.zɛnˈteɪ.ʃən/, fundamental /ˌfʌn.dəˈmɛn.təl/, intelligent /ɪnˈtɛlɪd͡ʒənt/

中文母語者容易讀錯的音：

/v/ — 不要讀成 /w/，上齒輕觸下唇: vector /ˈvɛktɚ/, retrieve /ɹɪˈtɹiːv/, evolution /ˌiːvəˈluːʃ(ə)n/, versus /ˈvɝsəs/, overnight /əʊvə(ɹ)ˈnaɪt/
詞尾子音 — 要讀清楚，後面不要加母音: intent /ɪnˈtɛnt/, generate /ˈd͡ʒɛn.ə.ɹeɪt/, hybrid /ˈhaɪ.bɹɪd/, adapt /əˈdæpt/, prompt /pɹɑmpt/
/r/ 和 /l/ 的區別: recall /ɹɪˈkɔl/, linear /ˈlɪn.i.əɹ/, leverage /ˈlɛv.(ə.)ɹɪd͡ʒ/, neural /ˈnʊɹəl/, retrieval /ɹɪˈtɹiːvəl/

如何用這段影片練習

先完整聽一遍影片，不要開口，記下不認識的單詞。
用正常速度逐句跟讀，每句重複到你的節奏與說話人一致為止。
錄下自己的聲音並與原聲對比，特別注意 pipeline, vector, query 這類單詞。

什麼是跟讀法？

跟讀法 (Shadowing) 是一種有科學依據的語言學習技巧，最初開發用於專業口譯員的培訓，並由多語言者Alexander Arguelles博士普及。這個方法簡單而強大：您在聽英語母語原聲的同時立即大聲重複——就像是一個延遲1-2秒緊跟說話者的影子。與被動聽力或語法練習不同，跟讀法強迫您的大腦和口腔肌肉同時處理並模模擬實的講話模式。研究表明它能顯著提高發音準確性，語調，節奏，連讀，聽力理解和口語流利度——使其成為雅思口語備考和真實英語交流最有效的方法之一。

影子跟讀法: 閱讀完整分步指南 →

跟讀練習: RAG's Evolution: From Simple Retrieval to Agentic AI - 通過影片學習英語口語

選擇練習模式

下載應用

Every Generation Thinks This Time Is Different: The AI Job Myth

What is Event Driven Architecture (EDA)?

Agentic AI Frameworks Explained: Workflows, Multi-Agent, & Production

Spec-Driven Development: AI Assisted Coding Explained

AI Agents vs Business Rules: Which Should Make Decisions?

AI & Education: Generative AI & the Future of Critical Thinking

EDR vs. EPP vs. NGAV

MCP vs ADK: How Modern AI Agents Connect and Work Together

Cybersecurity Architecture: Data Security

What Is Jev? The AI Model That Doesn't Generate Text

How Smart Organizations Will Use AI: Jevons Paradox & Workforce Impact

What are AI Agents?

Cybersecurity Architecture: Five Principles to Follow (and One to Avoid)

AI, Machine Learning, Deep Learning and Generative AI Explained

Zero Trust Explained in 4 mins

The 7 Skills You Need to Build AI Agents

What is Responsible AI? A Guide to AI Governance

What is AI Ethics?

How I use AI to learn engineering (anti brain rot studying)

The Complete Guide to Hybrid Search in RAG (BM25 + Embeddings + Reranker)

十年後的電腦會長什麼樣？黃仁勳：就像今天的手機，最少拿來打電話｜中英字幕

AI Agent Memory Architecture: Structured SQL, Semantic Vector Search & Memory Bank

Jack Dorsey’s New Dessa AI Voice Sounds Scary Human

Living with Machines: The language of mechanisation

What Is Chain-of-Thought Prompting in Generative AI?

Master AI in 60 Minutes with Vector Databases!

When AIs act emotional

Why Is There So Much AI Slop?