Put YouTube videos into your knowledge base

The request body we sent. Long texts and lists in the result are shortened for this page.

{
  "videos": [
    "https://www.youtube.com/watch?v=zjkBMFhNj_g"
  ]
}

{
  "videoId": "zjkBMFhNj_g",
  "url": "https://www.youtube.com/watch?v=zjkBMFhNj_g",
  "title": "[1hr Talk] Intro to Large Language Models",
  "channelName": "Andrej Karpathy",
  "channelUrl": "https://www.youtube.com/@AndrejKarpathy",
  "durationSeconds": 3590,
  "language": null,
  "languageMatched": true,
  "text": "hi everyone so recently I gave a 30-minute talk on large language models just kind of like an intro talk um unfortunately that talk was not recorded but a lot of people came to me after the talk and they told me that uh they really liked the talk so I would just I thought I would just re-record it and basically put it up on YouTube so here we go the busy person's intro to large language models director Scott okay so let's begin first of all what is a large language model really well a large language model is just two files right um there will be two files in this hypothetical directory so for example working with a specific example of the Llama 270b model this is a large language model released by meta Ai and this is basically the Llama series of language models the second iteration of it…",
  "wordCount": 12151,
  "segments": [
    {
      "start": 0,
      "end": 8.48,
      "text": "hi everyone so recently I gave a 30-minute talk on large language models just kind of like an intro talk um unfortunately that talk was not recorded"
    },
    {
      "start": 8,
      "end": 16.92,
      "text": "but a lot of people came to me after the talk and they told me that uh they really liked the talk so I would just I thought I would just re-record it and basically put it up on YouTube so here"
    },
    {
      "start": 16,
      "end": 24.599,
      "text": "we go the busy person's intro to large language models director Scott okay so let's begin first of all what is a large"
    },
    {
      "start": 24,
      "end": 33.16,
      "text": "language model really well a large language model is just two files right um there will be two files in this hypothetical directory so for example"
    },
    {
      "start": 33,
      "end": 41.399,
      "text": "working with a specific example of the Llama 270b model this is a large language model released by meta Ai and"
    },
    {
      "start": 41,
      "end": 47.76,
      "text": "this is basically the Llama series of language models the second iteration of it and this is the 70 billion parameter"
    },
    {
      "start": 47,
      "end": 54.199,
      "text": "model of uh of this series so there's multiple models uh belonging to the"
    },
    {
      "start": 54,
      "end": 62.28,
      "text": "Llama 2 Series uh 7 billion um 13 billion 34 billion and 70 billion is the biggest one now many people like this"
    },
    {
      "start": 62,
      "end": 70.56,
      "text": "model specifically because it is probably today the most powerful open weights model so basically the weights and the architecture and a paper was all"
    },
    {
      "start": 70,
      "end": 78.68,
      "text": "released by meta so anyone can work with this model very easily uh by themselves uh this is unlike many other language models that you might be familiar with"
    },
    {
      "start": 78,
      "end": 86.24,
      "text": "for example if you're using chat GPT or something like that uh the model architecture was never released it is owned by open aai and you're allowed to"
    },
    {
      "start": 86,
      "end": 95.28,
      "text": "use the language model through a web interface but you don't have actually access to that model so in this case the Llama 270b model is really just two"
    }
  ],
  "chapters": [
    {
      "title": "Chapter 1: Intro: Large Language Model (LLM) talk",
      "start": 0
    },
    {
      "title": "Chapter 2: LLM Inference",
      "start": 20
    },
    {
      "title": "Chapter 3: LLM Training",
      "start": 257
    },
    {
      "title": "Chapter 4: LLM dreams",
      "start": 538
    },
    {
      "title": "Chapter 5: How do they work?",
      "start": 682
    },
    {
      "title": "Chapter 6: Finetuning into an Assistant",
      "start": 854
    },
    {
      "title": "Chapter 7: Summary so far",
      "start": 1072
    },
    {
      "title": "Chapter 8: Appendix: Comparisons, Labeling docs, RLHF, Synthetic data, Leaderboard",
      "start": 1265
    },
    {
      "title": "Chapter 9: LLM Scaling Laws",
      "start": 1543
    },
    {
      "title": "Chapter 10: Tool Use (Browser, Calculator, Interpreter, DALL-E)",
      "start": 1663
    },
    {
      "title": "Chapter 11: Multimodality (Vision, Audio)",
      "start": 2012
    },
    {
      "title": "Chapter 12: Thinking, System 1/2",
      "start": 2100
    }
  ],
  "scrapedAt": "2026-10-21T06:31:41.071Z"
}