End To End LLM Langchain Project using Pinecone Vector Database

Поделиться
HTML-код
  • Опубликовано: 13 янв 2025

Комментарии • 155

  • @krishnaik06
    @krishnaik06  Год назад +5

    Check out other Langchain Projects below
    ruclips.net/video/4O1rs7mrNDo/видео.html&pp=gAQBiAQB

    • @saikatdas4654
      @saikatdas4654 Год назад

      Sir U r amazing.
      Sir, if possible then make videos on poison attacks on text data like trigger attacks or backdoor attacks.

  • @gsb2578
    @gsb2578 День назад

    Aamzing Krishna Bhai...Kya amazing video banaya hai aap ne..Dil jeet liya.

  • @linuxmanju
    @linuxmanju Год назад +14

    19:12 you need to return doc from the function not docs ( which is the raw input before chunks )?. Nice video and tutorials, thanks

  • @nooraftab6101
    @nooraftab6101 10 месяцев назад +6

    @krishnaik06: Thanks for the valuable resources. Couple of changes as I was running the code: 1) the model davinici-002 is deprecated. Instead OpenAI advises to use 'gpt-3.5-turbo-instruct'. 2) Pinecone initialization is also changed. For anyone following and coding from here, it was two breaking changes for me.

    • @rishabhranjan7687
      @rishabhranjan7687 10 месяцев назад +2

      Hey there, I'm stuck at pinecode initialization. Can you please tell me how you proceeded?

    • @darrendacosta6341
      @darrendacosta6341 10 месяцев назад +1

      @@rishabhranjan7687 hey have you been able to get it done?? if yes plz help .

    • @karangupta_DE
      @karangupta_DE 6 месяцев назад

      ​@@rishabhranjan7687 the code in the video works with pinecode-client==2.2.1
      But if you have 4.1.1, just search for langchain pinecode documentation and follow it step by step, it will resolve the issue.

  • @vivekanand1122
    @vivekanand1122 Год назад +1

    Amaizing Knowledge - Thanks Krish for your guidance !!

  • @tamilselvan3525
    @tamilselvan3525 10 месяцев назад +3

    26:28. We should give the chunks as an input to the function 'from_documents' but not 'doc'

    • @RaghavSoni-qv5bd
      @RaghavSoni-qv5bd 9 месяцев назад +1

      AttributeError: type object 'Pinecone' has no attribute 'from_documents'
      how can i resolve this error

    • @deepaliparochey2285
      @deepaliparochey2285 8 месяцев назад

      @@RaghavSoni-qv5bd you got the solution ??

    • @RaghavSoni-qv5bd
      @RaghavSoni-qv5bd 8 месяцев назад

      @@deepaliparochey2285 yes I got the solution of it

  • @Nothing_but_NavEEEn_Official
    @Nothing_but_NavEEEn_Official Год назад +1

    First like and Comment
    So Grateful for your guidance and contribution to the open-source community at the very need of Hour @KrishNaik Sir 🙏🏻❤️
    Love from Bangalore ✨

  • @ivokrastev9467
    @ivokrastev9467 5 месяцев назад

    As simple as that .... Thanks Krish very, very useful stuff.

  • @dastajan6789
    @dastajan6789 Год назад +1

    Informative video like ever

  • @sangeethag1966
    @sangeethag1966 Год назад +9

    def chunk_data(docs,chunk_size=800,chunk_overlap=50):
    text_splitter=RecursiveCharacterTextSplitter(chunk_size=chunk_size,chunk_overlap=chunk_overlap)
    doc=text_splitter.split_documents(docs)
    return docs
    In this part you are not using chunked_data ..need to return - return doc...Is it right?

    • @machinelearning3518
      @machinelearning3518 Год назад

      yes have you checked len(doc)

    • @jaivalani4609
      @jaivalani4609 3 месяца назад

      @@machinelearning3518 in our dir we have one doc or more than one ?

  • @deeks_edits
    @deeks_edits 9 месяцев назад

    Thank you for such an amazing video!

  • @kamalch8928
    @kamalch8928 5 месяцев назад

    Amazing learning video

  • @StudyExplore-p5n
    @StudyExplore-p5n 9 месяцев назад +1

    @krishnaik06, can we do the same with csv's having some kind of predictions from another ML model? Also, can we do some kind of weather report generation from IMD reports - I did try this, but it was not responding accurately. How to ensure the precision?

  • @prasadagalave9762
    @prasadagalave9762 Год назад +2

    Thank-you dada ❤

  • @tharunps8048
    @tharunps8048 Год назад +2

    17:50 shouldn't we return "doc" instead of "docs" ?

    • @krishnaik06
      @krishnaik06  Год назад

      Yes i guess that is a simple mistake i did :).Gald you found it

    • @pk231
      @pk231 Год назад

      I too noticed and thats why the Chunks have not been created and the size remains 58 I guess. I am not sure though.

  • @krishj8011
    @krishj8011 6 месяцев назад

    Amazing Tutorial...

  • @shanthinimichael5246
    @shanthinimichael5246 2 месяца назад

    Great video. Can we do the same with images and audio, or can we only do similarity searches for those?

  • @StudyExplore-p5n
    @StudyExplore-p5n 9 месяцев назад +1

    Do we have to create vector db all time? Cannot we store the data permanently?

  • @MansiKale-mr5ng
    @MansiKale-mr5ng 7 месяцев назад

    This is outstanding please share me some videos related to this Build one Q&A bot using open Al and Vector DB provide a couple of docs which should be stored in a vector db and when the questions asked to LLM model the LLM model should retrieve the answer from the vectors stored

  • @vaishnokmr
    @vaishnokmr Год назад +1

    Disclaimer: if you dont have pinecone api, you can use chromaDB, Sqlite or multiple db but you have to knowledge about schema and tables.

    • @dhruvsanan4738
      @dhruvsanan4738 Год назад

      Hey!! Would you like to collaborate to make a llm app? I've already done this tutorial but I am thinking of making a full fledged app.

  • @stefano94103
    @stefano94103 Год назад +27

    Unfortunately 90% of the developer videos are useless because they only build the backend. This is useless to show your manager or a client. Videos that show how to connect a backend to the users front end would be 1,000 times more helpful

    • @gudiatoka
      @gudiatoka Год назад

      Right 👍

    • @ARkhan-xw8ud
      @ARkhan-xw8ud Год назад +2

      You can check code with harry he has made with frontend

    • @saurabhsinghjat
      @saurabhsinghjat Год назад +12

      Bhai hr cheez thali me paros ke nhi di jaati. Fr kaahe ke developer. Thoda research kro sb mil jaayega. Is information age me bhi specific information ke liye ro rhe h hm to bantadhar h.

    • @shivii__ss
      @shivii__ss 10 месяцев назад

      ​@@ARkhan-xw8udcan you plz share the link

    • @Vasu-Katravath
      @Vasu-Katravath 9 месяцев назад

      Then you build the backend, Krish Naik will try to make the front end videos if you feel backend is easier.

  • @levius_24
    @levius_24 9 месяцев назад +1

    Hey Krish, great video!
    Do you know if it's possible to automatically create a pinecone db index from code?
    So that you don't have to create them manually

  • @studytips7034
    @studytips7034 10 месяцев назад +4

    can you please solve this error AttributeError: type object 'Pinecone' has no attribute 'from_documents

    • @aibyak
      @aibyak 9 месяцев назад

      same error i'm also getting, it seems like they have removed this feature. Now only server less services can create index

  • @abhi9029
    @abhi9029 Год назад +3

    I am stuck on "You exceeded your current quota, please check your plan and billing details". Anyone help !

    • @mailsuresh9
      @mailsuresh9 Год назад

      I am stuck on the same @krish Naik. Please help

    • @mailsuresh9
      @mailsuresh9 Год назад +1

      Actually, added $5 to open ai and waited for 20 mins and tried and it worked. Just created a new API key for clarity.

    • @narnavar
      @narnavar 11 месяцев назад

      If you are using old account for accessing chat gpt ..create new account and key.
      5 dollars can be used only till 3 months from the date of opening

  • @60pluscrazy
    @60pluscrazy Год назад +1

    Excellent Krish 🙏 🙏 🎉🎉

  • @mitejmadan8672
    @mitejmadan8672 Год назад +2

    Sir i dont have a credit card. Is it possible to create a project without using the openai api and just by open sourced models from huggingface and langchain. I am quite new in this llm field.

    • @RISHABH-VERMA
      @RISHABH-VERMA 10 месяцев назад +1

      Use Gemini-Pro's API instead of OpenAI.

  • @ShivamPatel-yg3kd
    @ShivamPatel-yg3kd Год назад +2

    Actually inside chunk_data you are returning the wrong variable

  • @digwijoymandal8662
    @digwijoymandal8662 6 месяцев назад

    Thanks Krish for the wonderful contributions.
    Can you please suggest if we could use tabular data with vector db. If any sample code available, can you please share

  • @pruthvip4457
    @pruthvip4457 26 дней назад

    vectors=embeddings.embed_query("what is indian total budget")
    len(vectors)
    when i excute this it is showing rate limit error
    how i do i slove it

  • @ShubhajitDutta-ve8bb
    @ShubhajitDutta-ve8bb Год назад

    Please consider to build an application based on this LLM model

  • @Bittu-e4y
    @Bittu-e4y 11 месяцев назад

    Hi Krish , Bigg thanks for all your contributions, I just have a doubt How to retrieve all docs that has been injected to elastic db?

  • @oliverkaunds
    @oliverkaunds 11 месяцев назад +1

    I did not understand one thing. Does the Vector DB talk to the LLM? We store data from PDF in Vector DB to make it searchable fast. But where is the part where we query Vector DB and send to LLM I could not see any LLM call may be I missed?

    • @shivii__ss
      @shivii__ss 10 месяцев назад

      Same question

    • @shivii__ss
      @shivii__ss 10 месяцев назад

      I think we use llm as open embedding model...

    • @mohitbokade2691
      @mohitbokade2691 Месяц назад

      Instead of using LLM we used the Langchain dataframe which is the combination of LLM and NLP

  • @SameerAli-nm8xn
    @SameerAli-nm8xn Год назад +1

    Sir please try to apply dockers with it, because it will be really helpful.

    • @dhruvsanan4738
      @dhruvsanan4738 Год назад

      Hey!! Would you like to collaborate to make a llm app? I've already done this tutorial but I am thinking of making a full fledged app.

  • @tanmayjagtap78
    @tanmayjagtap78 10 месяцев назад

    Can anyone explain what is the difference between FAISS and Pinecone? In multiple PDF video he used FAISS but here Pinecone. Is there any specific way to use them?

  • @swet_gokugod9382
    @swet_gokugod9382 6 месяцев назад

    Please recheck your code 10 times before publishing. There is no function named "similarity_search" how your code runs I don't know. Maybe it's a Supercomputer or something.

  • @Stacks-ce2k
    @Stacks-ce2k 11 месяцев назад

    Sir I have a error of NoneType object is not callable in retrieve query vectore.similarity search line how to overcome with it

  • @KeringKirwa
    @KeringKirwa 8 месяцев назад

    how can i make an LLM model produce output that can be fomatted in the browser for display , like with html tags in it , is that possibel ?

  • @GunjanGrunge
    @GunjanGrunge 11 месяцев назад

    Sir, lets say I want to deploy this chatbot trained on one pdf which has 2000 pages, can I remove the docuemnt part and only query from the db so that the load time and the embedding cost can be minimzed in production level chat bot, do let me know if you dint get the question, I will try to explain it in a better way.

  • @soumyaranjansahu4262
    @soumyaranjansahu4262 Год назад

    Hey Krish, Could you please create a video on the setilup of pgvector

  • @sefercanapaydn9347
    @sefercanapaydn9347 Год назад +2

    in chunk_data function you returned "docs" instead of "doc" isn't it wrong?

    • @shivii__ss
      @shivii__ss 10 месяцев назад

      Below you can see docs=doc

  • @sirivennalasanam6078
    @sirivennalasanam6078 4 месяца назад

    Quiz app related video can you share the link

  • @hamza_mehmood
    @hamza_mehmood 8 месяцев назад

    @krishnaik06 sir please can i have the link of that video which you are talking about at the end of this video??

  • @ashokreddyz
    @ashokreddyz 11 месяцев назад

    Openai apikey which we nned to use free tier or subscription, I'm using pro version is 4 apikey error is unauthorized

  • @anjalisingh1588
    @anjalisingh1588 11 месяцев назад

    I have one query - what if I want to connect my local database to a vector database and from that local database, the user can ask the question from the table !! Is this possible ?? if possible then how ??

  • @Joker76-91
    @Joker76-91 4 месяца назад +1

    hii sir , why the pinecone not showing environment value in my pinecone account

    • @rishitadavarthi4384
      @rishitadavarthi4384 4 месяца назад +1

      same issue, GCP is not included in free tier now, i can only use aws cloud and in that we are not getting any environment variable.

    • @ManojKumar-y5w2t
      @ManojKumar-y5w2t 3 месяца назад

      ⁠i also have same issue . Can we still use free tier? How abt environment?

  • @muaadhnazly7022
    @muaadhnazly7022 8 месяцев назад

    Do I need to have a paid account of Open AI to use the OpenAI Embeddings?
    Thank You

  • @TheLeads
    @TheLeads 9 месяцев назад

    Error: init is no longer a top-level attribute of the pinecone package.

  • @AIdevel
    @AIdevel 11 месяцев назад

    If I have many files in the same directory how to upload them ? thank you for your amazing vidoes

  • @koti...3874
    @koti...3874 2 месяца назад

    At the end of the day 😉

  • @rajvimultani871
    @rajvimultani871 7 месяцев назад

    Can you pls provide next video link for UI part

  • @rahulpawar8594
    @rahulpawar8594 7 месяцев назад

    @krishnaik06 : Thank for the detailed video. I need your help, I am trying to replicate the same with my list of documents. I am able to create vector DB, but when I am querying, something like, Give me the list of employee for which data is uploaded, I am not getting correct answer. Can you please help, how can we solve such type of scenario. your help is appreciated. Thank you

  • @noorahmadharal
    @noorahmadharal 4 месяца назад

    which blackboard are you using???
    Anynpne know???

  • @soumyarao3372
    @soumyarao3372 4 месяца назад +1

    If we have multiple PDF documents, how that can be handled here ?

  • @SurajKumar-uf6it
    @SurajKumar-uf6it 8 месяцев назад

    Sir can we do this same for csv files. Please answer this question

  • @ShubhamPandey-v2n
    @ShubhamPandey-v2n Год назад

    What is difference between loader vs parser in langchain?

  • @niravkhanpara5039
    @niravkhanpara5039 Год назад

    How its able to extract the text from the PDF? Is it using Tesseract or something else?

  • @krishnaprasadsheshadri6206
    @krishnaprasadsheshadri6206 11 месяцев назад +3

    The similarity_search function is not defined? Any ideas how to define it cause I dont get how it works without the function being defined

  • @lokeshsharma668
    @lokeshsharma668 8 месяцев назад

    hi krish, when i run this code i am getting error like Pinecone has no attribute from_documents please help me to resolve this issue

  • @lakshmims7590
    @lakshmims7590 10 месяцев назад

    How run this directly on visual studio by git hub repository

  • @inayatph
    @inayatph 9 месяцев назад

    thanku sir

  • @thomasferreira306
    @thomasferreira306 11 месяцев назад

    Hi, just want to tell you thay i created a similar project 8 month ago, everything was working but pinecone has migrate to a new version now "init" is no longer a top-level attribute of the pinecone package. I've made lot of reasearch but i don't find any solution to make it working again did you have a idea ?

    • @pranavbajpai5702
      @pranavbajpai5702 11 месяцев назад

      Yes needed help on this if anyone has a solution to this

  • @hetdave8379
    @hetdave8379 11 месяцев назад

    I don't want to use model API key. Is there any way to integrate LLM model which is stored in local machine and query the SQL database?

    • @krishnaik06
      @krishnaik06  11 месяцев назад

      Use llama2 i have already created a video

  • @RUPALIRAKIBE-v1m
    @RUPALIRAKIBE-v1m 4 дня назад

    I get error in vector generating please help me how can I solve this error

  • @shubhamkumar1305
    @shubhamkumar1305 Год назад +1

    How can we overcome that without using openai key?

    • @CodeVeda
      @CodeVeda 11 месяцев назад

      use gooogle's like .... GoogleGenerativeAI(model="models/text-bison-001",google_api_key=api_key, temperature=0.2)
      It works

  • @kiranshenvi2626
    @kiranshenvi2626 9 месяцев назад

    Hello Krish,
    Kindly request if you can share link to colab file if possible.

  • @saransomasundharam2617
    @saransomasundharam2617 10 месяцев назад

    hello krish, I was tried this code facing some issue with Pinecone.from_documents. there is no library called from_documents in pinecone.

  • @zayanahmad5706
    @zayanahmad5706 11 месяцев назад

    Hi! Guyz when I run the code I got some errors. Please help me

  • @nitinsiwach1989
    @nitinsiwach1989 8 месяцев назад +2

    This video is outdated. The pinecone API has changed significantly and this tutorial wont work

    • @ayushmishra5861
      @ayushmishra5861 8 месяцев назад

      Did you find the updated solution?

  • @umeshnath8818
    @umeshnath8818 Год назад

    Awesome bro!

  • @PrasannaJ-l3y
    @PrasannaJ-l3y Год назад

    hi sir in gihub source code of test.ipynb not avialabel with full code it has only import libirary

  • @abhisheksinghmahra446
    @abhisheksinghmahra446 Год назад

    i dont want to use openai api kindly make it with googlepalm api krish..i have to submit my college project tomorrow just let me know how can i do embedding with the help of palm api key
    i dont have openai subscription

  • @programwithpradhan
    @programwithpradhan Год назад

    Is there any open source embeddings we can use instead of Pinecone

    • @manasviemmadi8072
      @manasviemmadi8072 7 месяцев назад

      pinecone is vector database that stores the embeddings, it doesn't offer embeddings itself. there are many open source embeddings online. you can check the huggingface MTEB leaderboard for embedding models.

  • @DebjyotiSaha-lh8lg
    @DebjyotiSaha-lh8lg 11 месяцев назад

    I am getting an error in the pinecone initiation process. Considering all the process you said I am getting error as pinecone has not attribute init. Can you please help me on how to proceed furhter

    • @syedmuzammilahmed6872
      @syedmuzammilahmed6872 10 месяцев назад

      Pinecone has now changed its framework. Some elements like "init," "from documents" etc. are now removed. So, the procedure used in this tutorial is now outdated.

    • @dijendersaini9056
      @dijendersaini9056 10 месяцев назад

      it should be Pinecone instead of pinecode in pinecode.init

    • @ggg9gg
      @ggg9gg 10 месяцев назад

      ​@@syedmuzammilahmed6872 So how do we load a document object into pinecone now then? Since Pinecone.from_documents(docs, embeddings) no longer work

    • @deepaliparochey2285
      @deepaliparochey2285 8 месяцев назад

      @@ggg9gg Anyone found the solution for this ?

  • @piyush_nimbokar_07
    @piyush_nimbokar_07 9 месяцев назад

    Pinecone instance is not being created and how to do in newer version in v3.2.2 please tell

    • @deepaliparochey2285
      @deepaliparochey2285 8 месяцев назад

      Did you get the solution ?? if yes please help

    • @piyush_nimbokar_07
      @piyush_nimbokar_07 8 месяцев назад

      @@deepaliparochey2285 use older version of langchian and pinecone it will work

  • @amit2k5
    @amit2k5 9 месяцев назад

    The pinecone initialization step described in this video is not working. Any updated video or code please?

    • @deepaliparochey2285
      @deepaliparochey2285 8 месяцев назад

      did you get the solution ?

    • @GauravRajput-yd8lg
      @GauravRajput-yd8lg 16 дней назад

      from pinecone import Pinecone
      pc = Pinecone(api_key=pinecone_api_key)
      index = pc.Index(index_name)

  • @m.rr.c.1570
    @m.rr.c.1570 Год назад

    Why mine is taking so much time to print the answers

  • @parantikaghosh1182
    @parantikaghosh1182 8 месяцев назад

    pinecone is modified, this code does not work now, needs to be updated

  • @RaghavSoni-qv5bd
    @RaghavSoni-qv5bd 9 месяцев назад

    AttributeError: type object 'Pinecone' has no attribute 'from_documents'

    • @shinycaroline3722
      @shinycaroline3722 9 месяцев назад

      Yeah same issue, something wrong with langchain and pinecone once they have upgraded the version

  • @pepper_lab
    @pepper_lab Год назад

    🎉🎉🎉🎉

  • @shubhamkumar1305
    @shubhamkumar1305 Год назад

    Have you anyone give RateLimitError , 429 error?

    • @mailsuresh9
      @mailsuresh9 Год назад

      Yup. Stuck on the same on open AI 429 error.

    • @mailsuresh9
      @mailsuresh9 Год назад

      Actually, added $5 to open ai and waited for 20 mins and tried and it worked. Just created a new API key for clarity.

  • @koti...3874
    @koti...3874 2 месяца назад

    29:38 😂😂

  • @gowthamdora6146
    @gowthamdora6146 Год назад +1

    You need to return doc in chunk function but you are returning docs which is same as original documents,so you are not giving the text chunks for embeddings but whole documents.

    • @krishnaik06
      @krishnaik06  Год назад

      Ha bhai its a minor mistake u can update the code :)

  • @VikashKumar-ty6uy
    @VikashKumar-ty6uy 11 месяцев назад +1

    Getting this error while using pinecone vector db, can someone plz help me to resolve this
    pinecone.init(
    api_key="a4e02d-d1db-4d66-aaf9-fec1a868",
    environment="gcp-starter"
    )
    index_name="langchainvector"
    AttributeError Traceback (most recent call last)
    Cell In[33], line 2
    1 ## Vector Search DB In Pinecone
    ----> 2 pinecone.init(
    3 api_key="a4e0266d-d1db-4d66-aaf9-fe1be7c1a868",
    4 environment="gcp-starter"
    5 )
    6 index_name="langchainvector"
    File e:\Gen AI Project\Langchain_using_vectorDB\vectordbvenv\lib\site-packages\pinecone\deprecation_warnings.py:38, in init(*args, **kwargs)
    AttributeError: init is no longer a top-level attribute of the pinecone package.
    Please create an instance of the Pinecone class instead.

    • @harshadapatke885
      @harshadapatke885 10 месяцев назад

      Pinecone has removed init() in latest update. please use pinecone-client==2.2.4

  • @rishiraj2548
    @rishiraj2548 Год назад

    👍🙏

  • @AmarAmar-q8s
    @AmarAmar-q8s Месяц назад

    Man I'm facing 10000 errors, how could every people speaking out like they done it in 1st attempt

    • @vibodhjain2457
      @vibodhjain2457 Месяц назад

      because some functions are depricated and may be you are running as usual code.

  • @siddappakurabar9015
    @siddappakurabar9015 Год назад

    Sir how to get openai key sir

  • @mohammadriyaz5586
    @mohammadriyaz5586 9 месяцев назад

    Please use free api's

  • @charlesrsears
    @charlesrsears 3 месяца назад

    You probably should stop using “probably” as a filler word. It never makes sense in the context you’re using it.
    You aren’t “probably” doing something, you “are” doing something.

  • @WhiteHat-h2d
    @WhiteHat-h2d 11 месяцев назад

    Can someone please help me, PyPDFDirectoryLoader is not working, Below is the error, tried my best to resolve not happening
    Traceback (most recent call last):
    File "C:\LLMAppPinecone\test.py", line 4, in
    from langchain_community.document_loaders.pebblo import PebbloSafeLoader
    File "C:\Users\jchristian2\AppData\Local\anaconda3\Lib\site-packages\langchain_community\document_loaders\__init__.py", line 163, in
    from langchain_community.document_loaders.pebblo import PebbloSafeLoader
    File "C:\Users\jchristian2\AppData\Local\anaconda3\Lib\site-packages\langchain_community\document_loaders\pebblo.py", line 5, in
    import pwd
    ModuleNotFoundError: No module named 'pwd'