META LLAMA 3 8B INSTRUCT LLM - How to Create Medical Chatbot with LlamaIndex FastEmbed Colab Demo

Поделиться
HTML-код
  • Опубликовано: 16 окт 2024
  • #genai #llm #metaai
    In this video I explain how you can create a medical chatbot/converse with medical data using LlamaIndex and Meta LLAMA 3 8B LLM. I also explain how you can use custom embeddings(FastEmbed)
    If you like to support me financially, It is totally optional and voluntary. Buy me a coffee here: www.buymeacoff...
    Colab Notebook:
    colab.research...
    Relevant
    huggingface.co...
    llama.meta.com...
    docs.llamainde...
    www.versusarth...
    Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, they took great care to optimize helpfulness and safety.
    Llama 3 comes in two sizes - 8B and 70B parameters - in pre-trained and instruction tuned variants.
    LlamaIndex provides tools for both beginner users and advanced users. Our high-level API allows beginner users to use LlamaIndex to ingest and query their data in 5 lines of code. Our lower-level APIs allow advanced users to customize and extend any module (data connectors, indices, retrievers, query engines, reranking modules), to fit their needs.
    If you like such content please subscribe to the channel here:
    www.youtube.co...

Комментарии • 41

  • @keithwhite2986
    @keithwhite2986 5 месяцев назад +3

    As a fellow citizen of earth I appreciate the diversity of accents we have on our planet, yours too, keep up your good work and thanks for this inspirational video.

  • @NirantK
    @NirantK 10 дней назад

    Hey! FastEmbed creator here - thanks for making this video!

  • @dennisrose40
    @dennisrose40 5 месяцев назад

    Wonderful video, Rithesh. The RAG Architecture Model graphic and your explanations with names of the major parts you used were very instructive.

  • @petermarin
    @petermarin 5 месяцев назад +7

    As a British person, your accent is not bad at all and the video is easy to follow. Well done.
    Edit: for context, this comment was a reply to the comment of the American dude

    • @RitheshSreenivasan
      @RitheshSreenivasan  5 месяцев назад

      Thank You!

    • @petermarin
      @petermarin 5 месяцев назад +1

      @@vishnusureshperumbavoor for the record, my comment came only after I read the American guy..

  • @stargazer-y2z
    @stargazer-y2z 5 месяцев назад

    Hey Rithesh. Greetins from Brasil. Great video you made for us. Just ignore those people can only speak one language and are stuck mentally with local accents. Keep the good work.

  • @danielihenacho
    @danielihenacho 5 месяцев назад

    THANKS. ALWAYS LOOKING FORWARD TO YOUR VIDEOS

  • @maryamiqbal598
    @maryamiqbal598 Месяц назад

    Can we use this model for customized data finetuned model? As i have to make customized chatbot on my dataset

  • @fnaftujhggg
    @fnaftujhggg 5 месяцев назад

    This was very helpful! Thank you.

  • @craftedbysrs
    @craftedbysrs 5 месяцев назад

    Very informative. Thank you, sir.

  • @yanayana-cm5qg
    @yanayana-cm5qg 4 месяца назад

    what is the reason for the following error Exception: data did not match any variant of untagged enum PostProcessorWrapper at line 2395 column 3

  • @vishnusureshperumbavoor
    @vishnusureshperumbavoor 5 месяцев назад

    How to get access to this huggingface instruct model??
    Can u provide me the link??

    • @RitheshSreenivasan
      @RitheshSreenivasan  5 месяцев назад +1

      Google it you will get it. Link is also present in description

  • @tanb13
    @tanb13 5 месяцев назад

    How can we scale this solution to use 50+ pdf files each having 500 pages as input ?

    • @RitheshSreenivasan
      @RitheshSreenivasan  5 месяцев назад

      You need to look a some vector database like Pinecone. Probably you need to look at the best component at each stage

  • @arushini6379
    @arushini6379 4 месяца назад

    After running the code chatbot is created but no responses are generated, What might be the issue? Getting a authentication error

    • @RitheshSreenivasan
      @RitheshSreenivasan  4 месяца назад +1

      No idea as i did not have any issues. Check HF_TOKEN

    • @AruuData
      @AruuData 4 месяца назад

      Is it because I don't have a paid L4 instance

    • @AruuData
      @AruuData 4 месяца назад

      HF token was okay,

    • @RitheshSreenivasan
      @RitheshSreenivasan  4 месяца назад +1

      @@AruuData No

    • @AruuData
      @AruuData 4 месяца назад

      Change the runtime in to T4GPU , it worked ,What can we do if we need to deploy a website permenantly using this model? Can we do it using python anywhere? Or any other sources you know?

  • @vishnusureshperumbavoor
    @vishnusureshperumbavoor 5 месяцев назад

    Thanks mahn this is great

  • @sunshine-seema6095
    @sunshine-seema6095 5 месяцев назад

    Can we run this in colab free version T4 GPU?

  • @AC-go1tp
    @AC-go1tp 5 месяцев назад

    It would be great if you comment and clarify the errors you get when running the colab. Many thanks.

  • @dr_harrington
    @dr_harrington 5 месяцев назад

    chroma? No, you are using the default which is just in-memory

  • @MetaphoricMinds
    @MetaphoricMinds 5 месяцев назад

    As an American, its hard for us to listen to broken accents. Is there an AI that does speech-to-speech where it only alters that accent? It would be so useful.
    Many of the videos i come across in the tech field have english speaking narration, but with foreign accents. I would have so much more content im able to consume.

    • @RitheshSreenivasan
      @RitheshSreenivasan  5 месяцев назад

      Can’t help with my accent. But I believe there are some paid AI tools which can do text to speech or speech to speech

    • @gulamm1
      @gulamm1 5 месяцев назад

      Get used to intelligent tech savvy people accent if you want to make progress. You can’t get everything in life.