KZhead

RAG From Scratch: Part 1 (Overview)

LangChain
2024 ж. 5 Ақп.
51 717 Рет қаралды
Жүктеу

LLMs are a powerful new platform, but they are not always trained on data that is relevant for our tasks. This is where retrieval augmented generation (or RAG) comes in: RAG is a general methodology for connecting LLMs with external data sources such as private or recent data. It allows LLMs to use external data in generation of their output. This video series will build up an understanding of RAG from scratch, starting with the basics of indexing, retrieval, and generation. It will build up to more advanced techniques to address edge cases or challenges in RAG.
Code:
github.com/langchain-ai/rag-f...
Slides:
docs.google.com/presentation/...

Пікірлер

  • Having more, shorter videos is really helpful and makes the content far easier to consume and learn from. Thanks for teaching us! Please keep making tutorial playlists with shorter videos.

    @anonymous6666@anonymous66663 ай бұрын

  • Great walkthrough. Thank you for taking the time to put this together.

    @ZivRivkis@ZivRivkis3 ай бұрын

  • Thanks so much for the hands on tutorial! Very nicely made.

    @newchaoz@newchaoz14 күн бұрын

  • Would love a video series going over using langchain in combination with your own local SQL data.

    @efru1@efru12 ай бұрын

  • Nice walkthrough. thanks!

    @Arvolve@Arvolve3 ай бұрын

  • Great tutorial. 2 small fixes to get the code running. (1) add bs4 to ! pip install (2) and the os.environ['OPENAI_API_KEY'] = 'Your key' to import os. Have fun!

    @bramd_@bramd_2 ай бұрын

  • Great playlist!

    @mori-hosseini@mori-hosseini3 ай бұрын

  • Great video :) thank you

    @micbab-vg2mu@micbab-vg2mu3 ай бұрын

  • Very nice, thanks! It would be great to see a RAG tutorial that was totally off the internet, well, except for installation and downloading. I can't find any such demo's; there's always an API of some sort. In a way, I get it, but still it would be nice to see a RAG with WiFi off and no internet ... just once. Thanks as I've learned a bit more.

    @slipthetrap@slipthetrap3 ай бұрын

    • (This is Lance from the video.) I did one on local RAG. It shows how to set up local LLM and embedding model w/ Ollama and Nomic: kzhead.info/sun/eJasmNWrkKmulqM/bejne.html

      @r.lancemartin7992@r.lancemartin79922 ай бұрын

  • Hoping that too have production ready checklists, Hoping to do the same with JavaScript

    @user-yj2yl8en3i@user-yj2yl8en3i3 ай бұрын

  • Can you use a higher resolution for your videos? At least 1080p for anything with text.

    @OccamsPlasmaGun@OccamsPlasmaGun3 ай бұрын

    • (Lance is Lance from the video.) Yes, will do. It was a problem w/ Loom. Apologies.

      @r.lancemartin7992@r.lancemartin79922 ай бұрын

  • Hi, Great tutorial series here. A quick question as I am not able to find the right documentation for this. Can you tell me how rag_chain = ( | ).invoke snippet works. Per my understanding we are piping one result to another as we would with grep. is it similar?

    @aravindanpe3634@aravindanpe36342 ай бұрын

  • So RAG builds the prompt and this can scale with context window size?

    @jollojakar8995@jollojakar89953 ай бұрын

  • Hi, how are you bypassing rate limit error of openAi

    @salilmandal872@salilmandal8723 ай бұрын

  • anything beyond "frozen" rag?

    @daspradeep@daspradeep3 ай бұрын

  • Could you provide the code demo? Thanks!

    @JuneRay-tg3gd@JuneRay-tg3gdАй бұрын

  • great start. but the code link is broken. 404 error.

    @rohanbsahu3651@rohanbsahu36513 ай бұрын

  • Guest We're too early for the Notebook to be ready. #timeofcomment

    @____2080_____@____2080_____3 ай бұрын

    • ok np

      @peterbliznak8652@peterbliznak86523 ай бұрын

  • Great video, but please fix the code link.

    @kalkal0099@kalkal00993 ай бұрын

  • unfortunately, under 720P resolution, some text in the slides are very difficult to see clearly. I will be much better, if we can get 1080p or even higher resolution.

    @xianwang5183@xianwang5183Ай бұрын

    • There is a link to the slides in the description.

      @nellatara@nellataraАй бұрын

    • @@nellatara many thanks to your help

      @xianwang5183@xianwang5183Ай бұрын

  • How can I run those Jupiter notebook locally, i've clone them now what?

    @blaaarp4u@blaaarp4u17 күн бұрын

  • why 720p?

    @laoyeexuan5346@laoyeexuan5346Ай бұрын

  • code URL == 404

    @peterbliznak8652@peterbliznak86523 ай бұрын

    • Yes, It would be great to have access

      @antoniome5278@antoniome52783 ай бұрын

  • gemini 1.5

    @amallukose3763@amallukose37633 ай бұрын
KZhead