DSPy: MOST Advanced AI RAG Framework with Auto Reasoning and Prompting

Поделиться
HTML-код
  • Опубликовано: 13 дек 2024

Комментарии • 40

  • @sethjchandler
    @sethjchandler 7 месяцев назад +34

    This is very similar to other Dspy videos. I have yet to see it tested on non-canned examples. The video is perfectly fine but I would like to see more independent evaluation.

  • @EnricoGolfettoMasella
    @EnricoGolfettoMasella 7 месяцев назад +9

    Thanks for the content. It would be great to see more and more the use of open source models like Llama3, they have quality enough now to handle those tasks and we do not need to sell our souls to anyone

  • @sanoussabarry4218
    @sanoussabarry4218 7 месяцев назад +6

    simple , clear explantions , Good job Mr Mervin

  • @JuanOlCr
    @JuanOlCr 7 месяцев назад +16

    Thank you for another great video.
    How do we use it with our own documents? Which are the Vector DBs options? Can we use it with local LLMs (i.e. Ollama, LM Studio)?

  • @MrBiscuit696
    @MrBiscuit696 7 месяцев назад +9

    Your RUclips channel is one of the absolute best I am following. You deserve to have soooo many more sub's than you currently have. It won't be long until we get to see that gold RUclips plaque on the wall behind you ❤
    Keep it up!! You are changing life's with your channel. Thank you ❤️

  • @deekshitht786
    @deekshitht786 4 месяца назад +1

    Your content is truly next-level ♥

  • @johngoad
    @johngoad 7 месяцев назад +1

    You are Amazing!
    I have learned more form you than I can say.
    Thank you for always providing the code.. I break your code examples over and over again and truly learn by getting my hands dirty trying to modify for a current need or just to grasp a concept. I refer back to all of it frequently. Thank you so much!

  • @manojr8375
    @manojr8375 7 месяцев назад

    Very happy to see a long video!

  • @MikewasG
    @MikewasG 7 месяцев назад

    Your videos are of great help to me! Thank you so much! Looking forward to your other videos.

  • @SilverCord007
    @SilverCord007 7 месяцев назад +1

    Great Stuff! Reminds me of adding new layers to a model, I will try this with llama3.

  • @sircaju
    @sircaju 7 месяцев назад +1

    Way to go Mervin, now we are cooking.... very nice.

  • @rastinder
    @rastinder 7 месяцев назад +2

    what do u recommend where i can talk to a repo?

  • @SolidBuildersInc
    @SolidBuildersInc 7 месяцев назад +1

    Great discovery and presentation. How can this be used with praisonai ? Is that a deprecated idea or will this be incorporated into it ?

  • @kashyapmanani1624
    @kashyapmanani1624 5 месяцев назад

    This video is really helpful to improve and great video. But I would like to suggest that can you please smaller the circle. Some times we can not see screen content properly. If possible then please circle smaller that audience get better content visibility.
    Thank you for sharing. Please share AI Tech videos and help us to learn Sir.

  • @ArgiSanchez
    @ArgiSanchez 7 месяцев назад

    Hi Mervin, you are one the best professors, your explanations made more easy the complicated things. What do you think about weaviate or pgvecto rs for hybrid search on RAG app? Can you do an introduction to that? please ...

  • @zmeireles68
    @zmeireles68 7 месяцев назад

    Thank you so much for the content. It seems very impressive. I still need to see the papers for deep insight but I wonder how this could integrate with agents using crewai or langgraph.

  • @ctoxyz
    @ctoxyz 7 месяцев назад

    im consuming your #vids - nice work bro

  • @SreeKrishnaDeva
    @SreeKrishnaDeva 7 месяцев назад

    Thanks a lot this is very informative.

  • @erikthegrey
    @erikthegrey 7 месяцев назад

    This plus Autogen to fire off multiple, context explicit, complicated pipelines. Lots of ideas..

  • @cloudshoring
    @cloudshoring 6 месяцев назад

    You should do a 'tour' of dspy only then, its capabilities can be related to RAG and other things

  • @giuseppezani9049
    @giuseppezani9049 3 месяца назад

    can you make some groq example using DSPy. I've followed some example but it doesn't seem to work. Should i simply use it as openai with .env file?

  • @bijucyborg
    @bijucyborg 7 месяцев назад

    Well presented. What does the Baleen score actually mean??
    If I were to create a RAG application and provide the user a Baleen score for each answer I output, what would 58 mean for them??

  • @user-fp6ru7ol6z
    @user-fp6ru7ol6z 7 месяцев назад

    does the Dataset should be in an particular structrure !!! ? , i was checking wheather it can be implemented on LogAnomaly

  • @edoh6381
    @edoh6381 6 месяцев назад

    Do you have any playlist to learn concepts before this? I don't understand this code, I need more context

  • @MeinDeutschkurs
    @MeinDeutschkurs 7 месяцев назад

    Mind blowing! Great!

  • @farazfitness
    @farazfitness 7 месяцев назад

    Can I use llama 3 instead of gpt 3.5 turbo??

  • @Shubham-p1o
    @Shubham-p1o 7 месяцев назад

    Can i use gemini instead of openai for building rag based chatbot in the above case

  • @edmald1978
    @edmald1978 6 месяцев назад +1

    How to use this with my own documents? all tutorials use thus colBERTv2.

  • @devmahad
    @devmahad 2 месяца назад

    thanks :)

  • @nayiii8701
    @nayiii8701 4 месяца назад

    sir how i can use it for open source llms model like gemini

  • @Hypevine
    @Hypevine 7 месяцев назад +1

    How to do it with langchain

  • @geekyprogrammer4831
    @geekyprogrammer4831 7 месяцев назад

    You explained it nicely but your circle is blocking the text my friend.

  • @enriquebruzual1702
    @enriquebruzual1702 6 месяцев назад

    This is really interesting, I will try to implement it 100% locally. can you please modify your talking head, it gets in the way of the code. Thank you.

  • @PoGGiE06
    @PoGGiE06 7 месяцев назад +1

    Thanks Mervin. Can you avoid using openai keys? I want to use llama3 or other models, not support openai’s attempts to lock us into their (paid) ecosystem.

  • @sunnyahmed5935
    @sunnyahmed5935 7 месяцев назад

    is learning code worth in AI era ?

  • @YannochFPV
    @YannochFPV 7 месяцев назад

    Nice !

  • @akintoyeonikoyi4361
    @akintoyeonikoyi4361 7 месяцев назад

    Is this similar to crew ai

  • @OumarDicko-c5i
    @OumarDicko-c5i 7 месяцев назад

    Nice

  • @yoyartube
    @yoyartube 6 месяцев назад

    Whatever you do it seems you need curated data (q and a) so that you have something to evaluate against.