{
  "source_file": "0930",
  "source_platform": "Beehiiv",
  "author": "Akshay Pachaar / ML Spring",
  "title_listed": "Prompting vs RAGs vs Fine-tuning",
  "keywords": "",
  "domain": "大模型算法",
  "content_type": "技术教程",
  "is_paid_flag": "否",
  "url": "https://mlspring.beehiiv.com/p/prompting-vs-rags-vs-finetuning",
  "publish_date": "2023-10",
  "corpus_stage": "",
  "notes": "",
  "id": "783d8830242e",
  "collected_at": "2026-10-02T14:12:27",
  "title": "Prompting Vs RAGs Vs Finetuning",
  "body_markdown": "0\n0\nML Spring\nPosts\nPrompting Vs RAGs Vs Finetuning\nPrompting Vs RAGs Vs Finetuning\nUnderstanding how AI Engineers make decisions❓\nAkshay Pachaar\nDecember 14, 2023\nPrompting vs RAGs vs Fine-tuning!\nAn important decision that every AI Engineer must make when building an LLM-based application.\nTo understand what guides the decision, let's first understand the meaning of these terms.\n(refer the image below as you read each section)\n1️⃣ Prompting Engineering:\nThe prompt is the text input that you provide, based on which the LLM generates a response.\nIt's basically a refined input to guide the model's output.\nThe output will be based on the existing knowledge the LLMs has.\nRead my guide on Prompt engineering\nhere\n!\n2️⃣ RAGs (Retrieval-Augmented Generation):\nWhen you combine prompt engineering with database querying for context-rich answers, we call it RAG.\nThe generated output will be based on the knowledge available in the database.\nRead my intro to RAGs & llamaindex\nhere\n!\n3️⃣ Finetuning\nFinetuning means adjusting parameters of the LLM using task-specific data, to specialise in a certain domain.\nFor instance, a language model could be finetuned on medical texts to become more adept at answering healthcare-related questions.\nIt's like giving additional training to an already skilled worker to make them an expert in a particular area.\nBack to the important question, how do we decide what approach should be taken!\n(refer the image below as you read ahead)\n❗️There are two important guiding parameters, first one is Requirement of external knowledge, second is requirements of model adaptation.\n❗️While the meaning of former is clear, model adaption means changing the behaviour of model, it's vocabulary, writing style etc.\nFor example: a pretrained LLM might find it challenging to summarize the transcripts of company meetings, because they might be using some internal vocabulary in between.\n🔹So finetuning is more about changing structure (behaviour) than knowledge, while it's other way round for RAGs.\n🔸You use RAGs when you want to generate outputs grounded to a custom knowledge base while the vocabulary & writing style of the LLM remains same.\n🔹If you don't need either of them, prompt engineering is the way to go.\n🔸And if your application need both custom knowledge & change in the behaviour of model a hybrid (RAGs + Finetuning) is preferred.\nRead my hands on guide to finetuning using LoRA\nhere\n!\nA big shout-out to\nAbacusAI\nfor supporting my work.\nThey are hosting a FREE webinar on Retrieval APIs, Chat LLMs & AI Agents: Build LLM Apps at Scale\nRSVP here:\nhttp://tinyurl.com/RAGsAPI\nThe image below captures the essence of what we discussed so far!\nPrompting Vs RAGs Vs Finetuning\nThanks for reading! 🥂\nReply\nNewest first\nAdd your comment\nLogin\nLogin\nor\nSubscribe\nto participate\n.",
  "metadata": {
    "title": "Prompting Vs RAGs Vs Finetuning",
    "description": "Understanding how AI Engineers make decisions❓",
    "keywords": "data science, programming, machine learning",
    "author": "Akshay Pachaar",
    "og:type": "article",
    "og:url": "https://mlspring.beehiiv.com/p/prompting-vs-rags-vs-finetuning",
    "og:title": "Prompting Vs RAGs Vs Finetuning",
    "og:description": "Understanding how AI Engineers make decisions❓",
    "og:site_name": "ML Spring",
    "og:image": "https://beehiiv-images-production.s3.amazonaws.com/uploads/asset/file/2954a023-9920-4a8a-8bd8-a5e6a543fce7/Screenshot_2023-12-14_at_9.12.51_AM.png?t=1702525473",
    "og:image:width": "1200",
    "og:image:height": "630",
    "og:image:alt": "Understanding how AI Engineers make decisions❓",
    "twitter:url": "https://mlspring.beehiiv.com/p/prompting-vs-rags-vs-finetuning",
    "twitter:title": "Prompting Vs RAGs Vs Finetuning",
    "twitter:description": "Understanding how AI Engineers make decisions❓",
    "twitter:image": "https://beehiiv-images-production.s3.amazonaws.com/uploads/asset/file/2954a023-9920-4a8a-8bd8-a5e6a543fce7/Screenshot_2023-12-14_at_9.12.51_AM.png?t=1702525473",
    "twitter:card": "summary_large_image",
    "article:author": "Akshay Pachaar"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [],
  "images": [
    {
      "status": "ok",
      "url": "https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/user/profile_picture/365b6afb-67c5-48c4-ade3-f57b97ccf42a/thumb_akshay.jpeg",
      "bytes": 7364,
      "reused": true,
      "local_path": "attachments/783d8830242e/images/000.jpeg",
      "src": "https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/user/profile_picture/365b6afb-67c5-48c4-ade3-f57b97ccf42a/thumb_akshay.jpeg",
      "alt": "Author",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/2954a023-9920-4a8a-8bd8-a5e6a543fce7/Screenshot_2023-12-14_at_9.12.51_AM.png?t=1702525473",
      "bytes": 116515,
      "reused": true,
      "local_path": "attachments/783d8830242e/images/001.png",
      "src": "https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/2954a023-9920-4a8a-8bd8-a5e6a543fce7/Screenshot_2023-12-14_at_9.12.51_AM.png?t=1702525473",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/fbe7e525-7d62-4b56-9eb5-fe5e97f047ac/prf.jpeg?t=1702525392",
      "bytes": 74890,
      "reused": false,
      "local_path": "attachments/783d8830242e/images/body-c74b89a5fd13f771d7d1.jpeg",
      "src": "https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/fbe7e525-7d62-4b56-9eb5-fe5e97f047ac/prf.jpeg?t=1702525392",
      "alt": "",
      "downloaded": true
    }
  ],
  "audio": [],
  "videos": [],
  "links": [
    {
      "href": "https://mlspring.beehiiv.com/",
      "label": "ML Spring",
      "type": "a"
    },
    {
      "href": "https://mlspring.beehiiv.com/authors/akshay-pachaar",
      "label": "Akshay Pachaar",
      "type": "a"
    },
    {
      "href": "https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fmlspring.beehiiv.com%2Fp%2Fprompting-vs-rags-vs-finetuning",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://twitter.com/intent/tweet?text=Understanding+how+AI+Engineers+make+decisions%E2%9D%93++&url=https%3A%2F%2Fmlspring.beehiiv.com%2Fp%2Fprompting-vs-rags-vs-finetuning&via=akshay_pachaar",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.threads.net/intent/post?text=Understanding+how+AI+Engineers+make+decisions%E2%9D%93+++https%3A%2F%2Fmlspring.beehiiv.com%2Fp%2Fprompting-vs-rags-vs-finetuning",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.linkedin.com/sharing/share-offsite?url=https%3A%2F%2Fmlspring.beehiiv.com%2Fp%2Fprompting-vs-rags-vs-finetuning",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://mlspring.beehiiv.com/p/guide-prompt-engineering",
      "label": "here",
      "type": "a"
    },
    {
      "href": "https://mlspring.beehiiv.com/p/rags101-introduction-llamaindex",
      "label": "here",
      "type": "a"
    },
    {
      "href": "https://mlspring.beehiiv.com/p/understanding-lora-lowrank-adaption-large-language-models",
      "label": "here",
      "type": "a"
    },
    {
      "href": "http://abacus.ai/?utm_source=mlspring.beehiiv.com&utm_medium=referral&utm_campaign=prompting-vs-rags-vs-finetuning",
      "label": "AbacusAI",
      "type": "a"
    },
    {
      "href": "http://tinyurl.com/RAGsAPI?utm_source=mlspring.beehiiv.com&utm_medium=referral&utm_campaign=prompting-vs-rags-vs-finetuning",
      "label": "http://tinyurl.com/RAGsAPI",
      "type": "a"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:51:10Z",
  "source_url": "https://mlspring.beehiiv.com/p/prompting-vs-rags-vs-finetuning",
  "papers": [],
  "actual_video_files": [],
  "body_chars": 2814,
  "expected_body_images": 3,
  "discovery_status": "ok",
  "delivery_status": "ok",
  "missing_reason": "",
  "raw_html": "attachments/783d8830242e/pages/source.html",
  "local_html": "attachments/783d8830242e/pages/article.html",
  "body_base_path": "attachments/783d8830242e/pages/",
  "body_markdown_path": "attachments/783d8830242e/pages/article.md"
}