7-End To End Advanced RAG Project using Open Source LLM Models And Groq Inferencing engine

Поділитися
Вставка
  • Опубліковано 26 гру 2024

КОМЕНТАРІ • 58

  • @krishnaik06
    @krishnaik06  8 місяців тому +6

    Support me by joining membership so that I can upload these kind of videos
    ua-cam.com/channels/NU_lfiiWBdtULKOw6X0Dig.htmljoin

    • @dr8544
      @dr8544 8 місяців тому

      make a patreon

    • @r1ckmav
      @r1ckmav 8 місяців тому +2

      Just became member of this amazing channel.

  • @avixek
    @avixek 8 місяців тому +5

    I am using these series to learn langchain and deploy it in our fortune 10 company.. One of the key challenges in knowledge retrieval for all of the engineers in our team. I ran this scenario and we may have a savings of $500K/per yr. Please keep doing what you are doing.

    • @dear_nidhi
      @dear_nidhi 8 місяців тому

      Error initializing FAISS index: Error raised by inference endpoint: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/embeddings (Caused by NewConnectionError(': Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))
      can you solve this error?

    • @theshubhagrwl
      @theshubhagrwl 6 місяців тому

      Consider supporting the creator with 1% of the saving

    • @Santosh-xx4vf
      @Santosh-xx4vf 4 місяці тому

      Reply just for fun, take it like a joke
      If you support with 1% of income
      Than max you will support 50 people in life ie 50% of your income
      And ull go starving soon 🤣
      As other 50% goes a taxes to govt, by direct or indirect means 🤣

    • @Santosh-xx4vf
      @Santosh-xx4vf 4 місяці тому

      On a serious note.
      krish sir, is doing a great job for all of us we should support him in the ways possible

  • @nishantchoudhary3245
    @nishantchoudhary3245 8 місяців тому +3

    Best langchain series by best teacher. Krish sir ❤

  • @DoomsdayDatabase
    @DoomsdayDatabase 8 місяців тому +3

    Can't wait till Groq introduces option for running almost any HuggingFace models! Never came across such a simple, fast and cost effective endpoint setup!

  • @shalabhchaturvedi6290
    @shalabhchaturvedi6290 8 місяців тому +1

    Krish, you are doing an excellent job! Great job, bro!

  • @r1ckmav
    @r1ckmav 8 місяців тому

    Hi Krish, Thanks a lot for such an amazing content. You are doing a great help to humanity by publishing such an amazing content available free for everyone.

  • @canyouvish
    @canyouvish 8 місяців тому

    Very helpful set of videos. And yes, when I type words that have 'ng' in them - the 'g' almost always come before 'n'.

  • @dharmendersingh7565
    @dharmendersingh7565 8 місяців тому +1

    Great work, but make a video on implementing RAG on complex pdf (like extracting financial statements tables)

  • @goldenglowitsolutions
    @goldenglowitsolutions Місяць тому

    Nice video bro, thanks a lot!
    Can you teach us how to build with GROK (from X)?

  • @maazidris4435
    @maazidris4435 8 місяців тому

    Great work sir, Like from Pakistan

  • @dear_nidhi
    @dear_nidhi 8 місяців тому +1

    Error initializing FAISS index: Error raised by inference endpoint: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/embeddings (Caused by NewConnectionError(': Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))
    i m getting this error why?

    • @aiml.meetsolanki
      @aiml.meetsolanki 7 місяців тому

      i got the same error check your .env file paths of keys it is not given properly

    • @samagrashrivastava8042
      @samagrashrivastava8042 7 місяців тому

      @@aiml.meetsolanki I got the same error! can you explain the solution.

    • @aiml.meetsolanki
      @aiml.meetsolanki 7 місяців тому

      @@samagrashrivastava8042problem with api key initialisation. It is not given properly.initialise it properly

  • @rabbanimogal1786
    @rabbanimogal1786 8 місяців тому +1

    Great work!!

  • @DavidHelmen-sb9wf
    @DavidHelmen-sb9wf 8 місяців тому +2

    Hey Krish I hope you are doing well, can you make a video about full stack data scientist AKA Unicorn data scientist role?

  • @varshavaran2558
    @varshavaran2558 8 місяців тому +1

    Sir, the latest advancements in AI and data science trigger anxiousness since I am in early stages of Data science of roadmap. Will I ever catch-up with the latest technology or the basics remain relevant still

    • @ankaleshganorkar
      @ankaleshganorkar 8 місяців тому

      yes, tools will always change, domain knowledge will remain, enjoy the anxiousness.

  • @r1ckmav
    @r1ckmav 8 місяців тому

    Hi Krish, I just tried replacing the WebBaseLoader to PyPDFLoader somehow the same code piece does not seem to be working. Any suggestions to how to replace the WebBaseLoader with PyPDFLoader?

  • @YorkYongYeo
    @YorkYongYeo 7 місяців тому

    Will it be possible to process the vector embeddings before hand and allow the app to run faster in terms of reply?

  • @theshubhagrwl
    @theshubhagrwl 6 місяців тому

    This seriese a gem 💎

  • @sivanthik8288
    @sivanthik8288 8 місяців тому

    Thanks!

  • @adityavipradas3252
    @adityavipradas3252 8 місяців тому

    Is Groq LPU hardware needed to see the actual inference performance boost?

  • @nagrajkaranth123
    @nagrajkaranth123 2 дні тому

    Sir you are looking handsome

  • @andrespineiro7609
    @andrespineiro7609 8 місяців тому

    You are the best, dude!

  • @mithunshet5922
    @mithunshet5922 8 місяців тому

    Hi.. I am interested in predictive analytics where I mainly use ML models.. How will LLM be useful in this field?

  • @NairNitinvenugopal
    @NairNitinvenugopal 7 місяців тому

    instead of chains, can we use agent here?

  • @mohsenghafari7652
    @mohsenghafari7652 8 місяців тому

    Hi dear friend .
    Thank you for your efforts .
    How to use this tutorial in PDFs at other language (for example Persian )
    What will the subject ?
    I made many efforts and tested different models, but the results in asking questions about pdfs are not good and accurate!
    Thank you for the explanation

  • @sarveshudapurkar6235
    @sarveshudapurkar6235 8 місяців тому

    SIr I'm getting some error
    ValueError: Error raised by inference API HTTP code: 404, {"error":"model 'llama2' not found, try pulling it first"}

    • @harikiranm5756
      @harikiranm5756 8 місяців тому

      Were you able to figure this out?

    • @aiml_44_sourikpoddar49
      @aiml_44_sourikpoddar49 7 місяців тому

      Solution?

    • @aiml.meetsolanki
      @aiml.meetsolanki 7 місяців тому

      install llama2 by "ollama run llama2"

    • @aviratsharma771
      @aviratsharma771 7 місяців тому

      i am getting same error in every project from this playlist. do you get the solution??

    • @aiml.meetsolanki
      @aiml.meetsolanki 7 місяців тому

      @@aviratsharma771 install Ollama in your pc then run "Ollama run llama2" in Command Prompt

  • @shankar9063
    @shankar9063 7 місяців тому

    llm=ChatGroq(groq_api_key=groq_api_key,
    model_name="mixtral-8x7b-32768")
    I initialized the mixtral but i 'am getting the following error.
    ValueError: Error raised by inference API HTTP code: 404, {"error":"model 'llama2' not found, try pulling it first"}

  • @afnankhan1278
    @afnankhan1278 5 місяців тому

    we used sessions, but the process looks similare to last streamlit app we created nothing different you said you will explain it

  • @_itsvinay
    @_itsvinay 8 місяців тому

    Hi @krishnaik06 pls make a video on how to connect it with cloud database like pinecone or astra db. After version update it's not working with langchain.

  • @coding-master-shayan
    @coding-master-shayan 8 місяців тому +1

    Nice 🙂

  • @captionjunior6959
    @captionjunior6959 7 місяців тому

    how to develop a plagrism checker?

  • @chinnibngrm272
    @chinnibngrm272 8 місяців тому

    Sir want to build chatbot for Fintuned llama2 model in my local system
    Is it possible to build with streamlit like ur projects
    Please give us solution for this 😊😊

  • @michelle_theodore
    @michelle_theodore 5 місяців тому

    I swearrrrr same issues with me too i press c before g and it always turns out to be lancghain

  • @tootemakan
    @tootemakan 8 місяців тому

    Please build a conversational chain system using open source llms

  • @TarabUTK
    @TarabUTK 7 місяців тому

    out of all the ollama models:
    Llama 3 8B 4.7GB ollama run llama3
    Llama 3 70B 40GB ollama run llama3:70b
    Phi-3 3.8B 2.3GB ollama run phi3
    Mistral 7B 4.1GB ollama run mistral
    Neural Chat 7B 4.1GB ollama run neural-chat
    Starling 7B 4.1GB ollama run starling-lm
    Code Llama 7B 3.8GB ollama run codellama
    Llama 2 Uncensored 7B 3.8GB ollama run llama2-uncensored
    LLaVA 7B 4.5GB ollama run llava
    Gemma 2B 1.4GB ollama run gemma:2b
    Gemma 7B 4.8GB ollama run gemma:7b
    Solar 10.7B 6.1GB ollama run solar
    on a 16 GB RAM 'ok' desktop, Phi-3, Gemma-2b seems to run in reasonable time .... but I could not get Groq to work with either. Please advise what changes are needed for this part of the series. As of now, wait time is too long.
    Thanks

  • @mohamedkeddache4202
    @mohamedkeddache4202 7 місяців тому

    what is the purpose of using open source LLMs with paid groq api.
    just use directly openAi api key
    the only purpose of free LLMs are the ability to run them locally fro free

  • @amritsubramanian8384
    @amritsubramanian8384 7 місяців тому

    awesomeee ;)

  • @ramdasvk0716
    @ramdasvk0716 8 місяців тому +1

    Open source is 🫶🫶🫶