Chat With Multiple PDF Documents With Langchain And Google Gemini Pro

แชร์
ฝัง
  • เผยแพร่เมื่อ 17 พ.ย. 2024

ความคิดเห็น • 284

  • @krishnaik06
    @krishnaik06  10 หลายเดือนก่อน +34

    Lets Target for 1000 likes :). share your Work In Linkedin and Tag Me :)

    • @Tech_Enthusiasts_Shubham
      @Tech_Enthusiasts_Shubham 10 หลายเดือนก่อน +1

      For sure sir I am always there to support valuable content providing by you ❤

    • @Ashin3
      @Ashin3 10 หลายเดือนก่อน +2

      Valuable information

    • @richierosewall3741
      @richierosewall3741 10 หลายเดือนก่อน +4

      hi sir, if possible, could you do a video for scanned multipage pdf which includes images and tables with in it.

    • @subashr7934
      @subashr7934 10 หลายเดือนก่อน

      what are the prerequisites for this project Sir ?

    • @gopichandkothapalli4045
      @gopichandkothapalli4045 10 หลายเดือนก่อน

      @krishnaik06 pdf contains images or some figure. Is it possible to get those images as output for user response

  • @umeshkumarasamy6608
    @umeshkumarasamy6608 5 หลายเดือนก่อน +2

    quite the Quintessential Indian IT TH-camr, you are good sir.

  • @49_jaypandya40
    @49_jaypandya40 7 หลายเดือนก่อน +4

    Thank You Sir For Giving Us This Valuable Knowledge I Created My First GEN AI App Today Thank You Sir😃

    • @simeonkrah2340
      @simeonkrah2340 6 หลายเดือนก่อน

      Have you figured out how one can fine tune Gen AI app with their own data?

    • @bigRat4335
      @bigRat4335 หลายเดือนก่อน

      can you help me i am getting an error "No module named langchain" 😭

  • @whomisac4616
    @whomisac4616 10 หลายเดือนก่อน +6

    Thanks 🙏. Was planning to do something similar with Gemini pro today. Before I even started writing the code your video popped up 😂.

  • @Rohitpatil-ng8mb
    @Rohitpatil-ng8mb 10 หลายเดือนก่อน +12

    was just looking for this, loved the video and the explanation .
    just a small request sir, can you bring a hands on practical course for LLM, langchain. from the basics or level 0 to be able to build a production level project using MLOPS or LLMOPS.
    thank you sir.

  • @abhikits
    @abhikits 10 หลายเดือนก่อน +5

    Love your video.Please make a tutorial series showcasing Langchain, Gemini, and VectorDB in action.

  • @KEVALKANKRECHA
    @KEVALKANKRECHA 5 หลายเดือนก่อน +1

    olid video! You've covered a lot of ground and explained things well. There's always room to improve, but you're definitely on the right track. Looking forward to seeing more from you!

  • @mlsrihari1283
    @mlsrihari1283 10 หลายเดือนก่อน +5

    Your videos really helpful for learners bro, from Tamilnadu

    • @subashr7934
      @subashr7934 10 หลายเดือนก่อน

      Can you please tell what are the prerequisites for this project

  • @КравчукІгор-т2э
    @КравчукІгор-т2э หลายเดือนก่อน

    Thank you Krish Naik for your work and interesting videos. I have a big request - please make time codes in each of your videos. Believe me it is very convenient, especially when you need to find something very quickly. I'm sure there will be a lot more likes. I already got mine.

  • @harshjoshi114
    @harshjoshi114 4 หลายเดือนก่อน

    Thank you so much. I was struggling to learn this topic using a free LLM. This video covered a lot topics which otherwise I would have to learn from different sources.

  • @gurjeet333
    @gurjeet333 10 หลายเดือนก่อน +5

    Hi Krish, Can you also teach us to deploy this solution on a cloud platform as well. Deployment are being asked a lot in interviews

  • @gowthamdora6146
    @gowthamdora6146 10 หลายเดือนก่อน +1

    Amazing Krish, looking for more end to end projects on gen ai.

  • @almarazmartinez6380
    @almarazmartinez6380 9 หลายเดือนก่อน

    This was really helpful! I didn't know I could talk to PDFs now.

  • @Zaratch
    @Zaratch 10 หลายเดือนก่อน +3

    Will get to it tomorrow morning🙌 do remind me at 11 am on 10/01. Thank you 🤝

  • @k2inovaia
    @k2inovaia 6 หลายเดือนก่อน

    My Dear , thanks you, I tested it and it worked well., you are blessed by god..Carlos from Brazil.

    • @hrikhi
      @hrikhi 6 หลายเดือนก่อน

      I am getting some deserialization error:
      ValueError: The de-serialization relies loading a pickle file. Pickle files can be modified to deliver a malicious payload that results in execution of arbitrary code on your machine.You will need to set `allow_dangerous_deserialization` to `True` to enable deserialization. If you do this, make sure that you trust the source of the data. For example, if you are loading a file that you created, and no that no one else has modified the file, then this is safe to do. Do not set this to `True` if you are loading a file from an untrusted source (e.g., some random site on the internet.).
      new_db = FAISS.load_local("faiss_index", embeddings)
      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
      File "/opt/homebrew/Caskroom/miniforge/base/envs/venv1/lib/python3.11/site-packages/langchain_community/vectorstores/faiss.py", line 1078, in load_local
      raise ValueError(
      how to solve it?

  • @brianhauk8136
    @brianhauk8136 8 หลายเดือนก่อน +1

    Thank you for sharing this useful advice on an important topic. How would you modify it to work with OpenAI's GPT-4 API instead of Google Gemini Pro?

  • @umangternate
    @umangternate 6 หลายเดือนก่อน

    I have been giving up with this kind of project, but I will give this tutorial a try tomorrow.

  • @bhavnitasingh1549
    @bhavnitasingh1549 10 หลายเดือนก่อน +2

    Great Video. Can you please let me know how you identified the limit of not uploading a single pdf exceeding 200MB in size?

  • @jaychauhan2933
    @jaychauhan2933 6 หลายเดือนก่อน

    hey krish awesome knowledge sharing it will be great if you could create a video on how we can deploy LLM model with RAG on cloud. I mean using docker or something and then hosting on AWS, GCP or other cloud platform so we can get idea that how the complete project is done.

  • @izainonline
    @izainonline 10 หลายเดือนก่อน +1

    Great Sir but have a Question that coding not remain important? concept is important?
    I mean we can use your coding to make this so what creative work remains in coding.

  • @wert-yo1ln
    @wert-yo1ln 3 หลายเดือนก่อน +4

    Since langchain changes versions quite frequently you need to improve your requirements.txt file with not just the names of packages but also their versions because the code you've provided is not working

  • @aishu2623
    @aishu2623 10 หลายเดือนก่อน +3

    sir i am a getting a error that is ValidationError: 1 validation error for LLMChain llm Can't instantiate abstract class BaseLanguageModel with abstract methods agenerate_prompt, apredict, apredict_messages, generate_prompt, predict, predict_messages (type=type_error) i tried different methods to solve but i am unable to solve this error , can you plz kindly help with this .
    Since i have taken up this for my 6th sem project.

    • @atharvkute1332
      @atharvkute1332 9 หลายเดือนก่อน

      me tooo plzz help me

  • @MsProtestante
    @MsProtestante 2 หลายเดือนก่อน

    Hi Mr. Naik thanks for sharing your knowledge! I have an usecase that I need to read information from PDF invoices and exhibit on an input HTML form. For that I´m planning to send the PDF to the LLM(GEMINI) along with a JSON format and ask GEMINI to fill up the JSON with the information read from the PDF. How would you implement such a feature? Do you think that I need RAG for this? Or Just extracting the text from the PDF and give it to GEMINI fill up the JSON will do? Which one is better?

  • @hassaniqbal4348
    @hassaniqbal4348 2 หลายเดือนก่อน

    innovative & informative

  • @shaban26muftimufti35
    @shaban26muftimufti35 10 หลายเดือนก่อน

    You are putting crores of content on TH-cam, my only request is that if you bring them all in Hindi, I will be very grateful.

    • @Statsjk
      @Statsjk 10 หลายเดือนก่อน +1

      If you can't understand this in English, this video has no use for you😂

  • @adityaagarwal7997
    @adityaagarwal7997 10 หลายเดือนก่อน +1

    really great video, thanks a lot for such great contents!!.

  • @kamitp4972
    @kamitp4972 10 หลายเดือนก่อน +3

    Sir , I'm getting error as TypeError: 'GoogleGenerativeAIEmbeddings' object is not callable. can you do something?

    • @venky252003
      @venky252003 9 หลายเดือนก่อน +1

      I'm also getting same error, any one fixed this issue.

    • @mohsinqureshi6850
      @mohsinqureshi6850 9 หลายเดือนก่อน +2

      update langchain
      mine is fixed

    • @peterhpchen
      @peterhpchen 8 หลายเดือนก่อน

      After update lanchain, I still get the same error. It looks like the google_api_key become "None"?
      : `embedding_function` is expected to be an Embeddings object, support for passing in a function will soon be removed.
      vector_store:
      Google Generative AI embeddings: model='models/embedding-001' task_type=None google_api_key=None client_options=None transport=None
      `embedding_function` is expected to be an Embeddings object, support for passing in a function will soon be removed.
      perform Similarity_Search for user_question: provide a detailed summary of Multi-Head Attention
      2024-03-11 22:46:57.585 Uncaught app exception
      Traceback (most recent call last):
      File "/home/peter/anaconda3/envs/tf/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 534, in _run_script
      exec(code, module.__dict__)
      File "/home/peter/AIU/AIU_CS515_LLM/020_Gemini/002_Code/pdf_chatbot.py", line 108, in
      main()
      File "/home/peter/AIU/AIU_CS515_LLM/020_Gemini/002_Code/pdf_chatbot.py", line 93, in main
      user_input(user_question)
      File "/home/peter/AIU/AIU_CS515_LLM/020_Gemini/002_Code/pdf_chatbot.py", line 71, in user_input
      docs = new_db.similarity_search(user_question)
      File "/home/peter/anaconda3/envs/tf/lib/python3.10/site-packages/langchain/vectorstores/faiss.py", line 509, in similarity_search
      docs_and_scores = self.similarity_search_with_score(
      File "/home/peter/anaconda3/envs/tf/lib/python3.10/site-packages/langchain/vectorstores/faiss.py", line 390, in similarity_search_with_score
      embedding = self._embed_query(query)
      File "/home/peter/anaconda3/envs/tf/lib/python3.10/site-packages/langchain/vectorstores/faiss.py", line 155, in _embed_query
      return self.embedding_function(text)
      TypeError: 'GoogleGenerativeAIEmbeddings' object is not callable

  • @VijilalFlutter
    @VijilalFlutter 8 หลายเดือนก่อน

    Short and precise. Well Done. I have a question. Can i use this with flutter. I mean i need to develop front end using flutter

  • @firdospathan3700
    @firdospathan3700 9 หลายเดือนก่อน +1

    Hi Krish. Just want to be know for Q&A chatbot. I have Data about insurance in pdf file. So the Data which I am having is same columns and rows. But the insurance cost is different from each pdf file. So I want to build a Q& A chatbot. Which will extract the pdf file name along with that insurance type avilable in the pdf file and then it will display a drop down box or something to select which type of insurance you need and along with the cost. Can you helpe out for this?

  • @483552
    @483552 10 หลายเดือนก่อน +1

    Very Good information bro.
    Can you help.. If headers based information can we take it from PDF to Excel

  • @myLittleLegends
    @myLittleLegends 8 หลายเดือนก่อน

    Hi Krish, thanks for the detailed video. I have a query on this application. Is this one time upload of PDF will keep the vector index for ever in the faiss_index folder? or do we need to keep uploading the file every time to achieve the expected summary. I mean the files uploaded in one session.

  • @jayaprakash7348
    @jayaprakash7348 10 หลายเดือนก่อน

    Nice explanation bro. Could you please share one more video with langchain htmltotxt extract from website with google api

  • @bhaumiks.6543
    @bhaumiks.6543 9 หลายเดือนก่อน

    Thank you for video. It was amazing. Can we use the similar approach for multiple photos as well?

  • @sahiltr1151
    @sahiltr1151 5 หลายเดือนก่อน

    Crazy tutorial!! Loved it

  • @ombaba2153
    @ombaba2153 6 หลายเดือนก่อน +1

    How to fetch image and text form the pdf can u make one more video on this ?

    • @rahilshaikh4954
      @rahilshaikh4954 2 หลายเดือนก่อน

      You got any solution for this?

  • @mayasushma2951
    @mayasushma2951 10 หลายเดือนก่อน +1

    And also will it be able to give a reference where my answer is referring to and if a question is asked from multiple pdfs ... Will be able to give reference page number and also pdf name properly?? Let me know if u have tested that

  • @User-Srishtij
    @User-Srishtij 10 หลายเดือนก่อน

    Thank you Sir for sharing this with us.
    Can we use PandasAI for reading .CSV files, pls confirm

  • @biswanathbiswas5686
    @biswanathbiswas5686 7 หลายเดือนก่อน

    Thanks Krish 🙏, can we use Gemma 2b from huggingface instead of Gemini Pro?
    As for poc it will be cost-effective.

  • @ag_kishan27
    @ag_kishan27 10 หลายเดือนก่อน +2

    Please make same for video. import video nd it give description

  • @anuragmanjramkar2130
    @anuragmanjramkar2130 6 หลายเดือนก่อน +4

    ValueError: The de-serialization relies loading a pickle file. Pickle files can be modified to deliver a malicious payload that results in execution of arbitrary code on your machine.You will need to set `allow_dangerous_deserialization` to `True` to enable deserialization. If you do this, make sure that you trust the source of the data. For example, if you are loading a file that you created, and no that no one else has modified the file, then this is safe to do. Do not set this to `True` if you are loading a file from an untrusted source (e.g., some random site on the internet.).
    How to resolve this error

    • @kunalgupta116
      @kunalgupta116 6 หลายเดือนก่อน +1

      just set the parameter allow_dangerous_deserialization = True i.e. FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

    • @srihbalaji7272
      @srihbalaji7272 5 หลายเดือนก่อน +1

      Bro same here you got it solved? Can you help?

    • @anuragmanjramkar2130
      @anuragmanjramkar2130 5 หลายเดือนก่อน

      @@srihbalaji7272 Change this line new_db = FAISS.load_local("faiss_index", embeddings)
      to new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

    • @anuragmanjramkar2130
      @anuragmanjramkar2130 5 หลายเดือนก่อน

      Change this line new_db = FAISS.load_local("faiss_index", embeddings)
      to new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

    • @umarzafar7759
      @umarzafar7759 5 หลายเดือนก่อน

      @@srihbalaji7272
      In the function user_input(), replace the line and add allow_dangerous_deserialization=True
      #Code
      new_db = FAISS.load_local("faiss_index_react", embeddings, allow_dangerous_deserialization=True)

  • @Sachin-kk3np
    @Sachin-kk3np 4 หลายเดือนก่อน

    How can we leverage an NLP model or Generative AI pre-trained model like ChatGPT or Llama2 to compare two documents, like legal contracts or technical manuals, and find the deviation in the documents.
    Please give me ideas or ways to achieve this or if you have any TH-cam/Github links for the reference.

  • @nishkarve
    @nishkarve 10 หลายเดือนก่อน +1

    Krish, great job. One question. How can this app return images from your attention is all you need paper. I would like to return the encoder decoder architecture diagram along with the steps mentioned in the doc. Can you please make a video for that?

    • @oussamazorrig8762
      @oussamazorrig8762 8 หลายเดือนก่อน

      Please did you find any solution for that? I'm working on something similar and I want to extract images and interact with them

  • @takur1977
    @takur1977 5 หลายเดือนก่อน

    Hi Krish, Thanks for the wonderful video. i could implement this by following your video. However, I am not getting the correct results when I try to analyze pdf file with form fields like checkboxes and radio buttons. I tried using OCR reading etc but still, it is not giving me the correct result. could you please recommend how to deal with pdf with from fields etc?

  • @DebjyotiSaha-lh8lg
    @DebjyotiSaha-lh8lg 9 หลายเดือนก่อน

    Thanks Krish for the video. I have a doubt that if I upload only 1 PDF will it work or I have to upload more than 1 PDF?

  • @Shreddxxr6
    @Shreddxxr6 10 หลายเดือนก่อน +1

    This is truly awesome

  • @malleswararaomaguluri6344
    @malleswararaomaguluri6344 9 หลายเดือนก่อน

    Hi Krish, can you make a video on rag application using llm models locally by using cpu and gpu as well.

  • @rohitshukla1539
    @rohitshukla1539 10 หลายเดือนก่อน +1

    Hello sir when I run this code I am getting type error GoogleGenerativeAIEMbeddings is not collable

  • @ApekshaKallur
    @ApekshaKallur หลายเดือนก่อน

    I am getting pydantic_core._pydantic_core.ValidationError: 1 validation error for RunInfo
    run_id UUID input should be a string, bytes or UUID object while calling :
    response = chain(
    {"input_documents":docs, "question": user_question}
    , return_only_outputs=True)
    Any idea?

  • @bekar-kahaniya-hum-sunaynge
    @bekar-kahaniya-hum-sunaynge 10 หลายเดือนก่อน +1

    hello sir
    after done this.
    not getting answer properly
    getting this when i upload pdf file
    {'output_text': 'answer is not available in the context'}

    • @shubhamrathod9969
      @shubhamrathod9969 9 หลายเดือนก่อน

      First, try this: Increase the context length to 10000 in charactersplitter.
      If that doesn't happen: Try changing
      response = chain(
      {"input_documents": docs, "question": query}
      , return_only_outputs=True)
      to
      response = chain.invoke(
      {"input_documents": docs, "question": query}
      , return_only_outputs=True).
      I just wanted to let you know that this worked for me.

  • @thomasantony3381
    @thomasantony3381 10 หลายเดือนก่อน +6

    I am getting Answer not available in context it's not properly read and storing the vector embeddings it seems😕

    • @pavankumartalari387
      @pavankumartalari387 8 หลายเดือนก่อน

      Yes Even me , I think this comment was almost 2 months ago , I am trying to implement it now , even I am getting the same error , Did you figured it out on how we can solve this issue or the error.
      I know you might be busy but a 2 word reply would mean a lot.

  • @sushsjk
    @sushsjk 10 หลายเดือนก่อน +1

    any idea, that chatbot can display graphical or any kind of comparison graphs?

  • @aungnandaoo443
    @aungnandaoo443 6 หลายเดือนก่อน

    Sir, if you don't mind, can you write the same program using gemini pro, but reading the PDF file from data base. For example, firebase.

  • @meghakeshri6945
    @meghakeshri6945 4 หลายเดือนก่อน

    why you did not used loaders from langchain? which one is better

  • @utpalpaul2933
    @utpalpaul2933 10 หลายเดือนก่อน +3

    Instead of Streamlit, can I use Flask?

  • @yavuzobuz2405
    @yavuzobuz2405 8 หลายเดือนก่อน +1

    After the Gemini update, it constantly gives the error "The answer you are looking for in the text could not be found"

    • @The.Patel.
      @The.Patel. 8 หลายเดือนก่อน

      did you found any solution for this ?

  • @datasciencegyan5145
    @datasciencegyan5145 8 หลายเดือนก่อน

    Zabarjust ... Ek numbwr..

  • @FalahgsGate
    @FalahgsGate 10 หลายเดือนก่อน +1

    thanks for sharing and for the good tutorial.... but why do I always get the Reply: the answer is not available in the context, but I'm sure I upload PDFs

    • @soulfuljourney22
      @soulfuljourney22 9 หลายเดือนก่อน

      initially i got the answer but later I am getting similar answers

    • @raabiyahraabiyah8597
      @raabiyahraabiyah8597 3 หลายเดือนก่อน

      same error here. Did you manage to find a solution?

  • @DS_AIML
    @DS_AIML 10 หลายเดือนก่อน +2

    ValidationError: 1 validation error for LLMChain llm Can't instantiate abstract class BaseLanguageModel with abstract methods agenerate_prompt, apredict, apredict_messages, generate_prompt, predict, predict_messages (type=type_error) .I am getting this error while running the code.

    • @ravikantjain
      @ravikantjain 9 หลายเดือนก่อน

      same, you got solution ?

    • @DS_AIML
      @DS_AIML 8 หลายเดือนก่อน +1

      @@ravikantjain Please check you environment you are working.That might be issue

  • @girirajbagdi
    @girirajbagdi 6 หลายเดือนก่อน +1

    Hello - I am getti g following error while running the program shared in git - plz advise "ValueError: The de-serialization relies loading a pickle file. Pickle files can be modified to deliver a malicious payload that results in execution of arbitrary code on your machine.You will need to set `allow_dangerous_deserialization` to `True` to enable deserialization. If you do this, make sure that you trust the source of the data. For example, if you are loading a file that you created, and no that no one else has modified the file, then this is safe to do. Do not set this to `True` if you are loading a file from an untrusted source (e.g., some random site on the internet.)."

    • @harishsharma9466
      @harishsharma9466 6 หลายเดือนก่อน

      Hey This was all working for me for last 2 days, but then I upgraded streamlit and now 'allow_dangerous_deserialization' flag is not required but facing an error - "TypeError: 'GoogleGenerativeAIEmbeddings' object is not callable". can you help to resolve the error?

    • @ayushpattnaik8396
      @ayushpattnaik8396 6 หลายเดือนก่อน

      @@harishsharma9466 Did you resolve the issue?

    • @finickyniki
      @finickyniki 6 หลายเดือนก่อน

      hey getting same error, were you able to find a resolution?

    • @kunalgupta116
      @kunalgupta116 6 หลายเดือนก่อน

      just set the parameter allow_dangerous_deserialization = True i.e. FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

    • @srihbalaji7272
      @srihbalaji7272 5 หลายเดือนก่อน

      You got solution?

  • @azharudeensalim2898
    @azharudeensalim2898 10 หลายเดือนก่อน +2

    Hi Krish while following the video I have faced an error: 1 validation error for LLMChain llm Can't instantiate abstract class BaseLanguageModel with abstract methods agenerate_prompt, apredict, apredict_messages, generate_prompt, predict, predict_messages (type=type_error) .How can we fix it

    • @Datasciencefiverr
      @Datasciencefiverr 10 หลายเดือนก่อน +1

      same here do you find solution

    • @wanderer_ankur
      @wanderer_ankur 10 หลายเดือนก่อน

      I am also facing the same issue.

    • @ishaanpranava
      @ishaanpranava 10 หลายเดือนก่อน

      @krishnaik06
      Yes, I am also facing the same problem here, please suggest a solution.

    • @vijaybhavesh
      @vijaybhavesh 10 หลายเดือนก่อน

      same here do you find solution

    • @vijaybhavesh
      @vijaybhavesh 10 หลายเดือนก่อน

      i got the solution we need to update the langchain library i am using langchain 0.1.0

  • @subashr7934
    @subashr7934 10 หลายเดือนก่อน +2

    Can anyone pls say what are the prerequisites for this project?

  • @vivekshindeVivekShinde
    @vivekshindeVivekShinde 10 หลายเดือนก่อน +1

    Hi Krish, I have to build a chatbot for a client on domain specific data. Can I use all these for the same? But when I see google gemini or gpt, they charge money for it. So exactly how should I build the bot on large textural data for a client.

    • @SandeepSingh-yr2py
      @SandeepSingh-yr2py 10 หลายเดือนก่อน

      I am guessing your best bet to keep this data private is to host a local LLM (maybe set up an endpoint with LMStudio) and see how it works. Mistral 7 does a good job for me.

  • @umeshkumarasamy6608
    @umeshkumarasamy6608 5 หลายเดือนก่อน

    I don't know for what purpose but everytime I see there is a library called tiktoken imported into the project but it is never used. why is that?

  • @mayasushma2951
    @mayasushma2951 10 หลายเดือนก่อน +1

    Hey hi @krishnaik can it also give proper response with clear output format having around 40 pdfs

    • @krishnaik06
      @krishnaik06  10 หลายเดือนก่อน +1

      Yes it can be any number

  • @DigitaTransforma
    @DigitaTransforma 9 หลายเดือนก่อน +1

    Hi Friend. I think there's something wrong with the code. I always get "answer is not available in the context" when ever i try to chat with a pdf

    • @vansh7311
      @vansh7311 2 หลายเดือนก่อน

      samee , is it solved?

  • @demon-h5p
    @demon-h5p 8 หลายเดือนก่อน

    Hello Krish need your help for one of my poc project:
    i have been asked to build poc on document search for different types of files like pdf, docx and excel:
    i have used streamlit and build the simple ui application using google ai api and gemini pro..
    now i have to implement below functionality:
    "Should have design & approach of the solution
    Two types of user to use this document search bot.
    Admin & Normal User.
    Admin should be able to upload and delete documents.
    Both user should be able to ask query
    The response should match the query asked
    Have test cases created for validation"
    please help me out with the source code how to start and build it

  • @sapnakalra8021
    @sapnakalra8021 10 หลายเดือนก่อน

    Can we get the difference between the two documents also using any utility I'm llm ?

  • @rohithakash8093
    @rohithakash8093 10 หลายเดือนก่อน

    I am getting error: {'output_text': 'This context does not mention anything about Hierarchical Vision Transformers, so I cannot answer this question from the provided context.'}

  • @ishavmahajan
    @ishavmahajan 10 หลายเดือนก่อน +1

    How to use gemini-pro-vision model on textual data

  • @NikhilPrasad-u4g
    @NikhilPrasad-u4g 10 หลายเดือนก่อน +1

    Hello sir, actually i am getting attribute error: bytes object has no attribute seek

  • @demon-h5p
    @demon-h5p 9 หลายเดือนก่อน

    hello krish,
    can we use different types file format for this project

  • @kanth2223
    @kanth2223 8 หลายเดือนก่อน +1

    Hello sir
    I am getting error
    ValueError: The de-serialization relies loading a pickle file. Pickle files can be modified to deliver a malicious payload that results in execution of arbitrary code on your machine.You will need to set allow_dangerous_deserialization
    What to do sir

    • @kanth2223
      @kanth2223 8 หลายเดือนก่อน +3

      Change code into
      new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

    • @ezequielbravo7291
      @ezequielbravo7291 8 หลายเดือนก่อน

      It worked for me, thanks!@@kanth2223

    • @paneerselvam7312
      @paneerselvam7312 หลายเดือนก่อน

      @@kanth2223 Thanks bro

  • @Prateikx
    @Prateikx 8 หลายเดือนก่อน

    How to implement chat history/ conversation history when using FastApi for every request to get response?

  • @DavidRoopnarine-zh5dn
    @DavidRoopnarine-zh5dn 6 หลายเดือนก่อน

    does this code still work im having some issues with the chunk function expecting string, but even after converting the stuff to string it doesn't work

  • @plutogaming8981
    @plutogaming8981 6 หลายเดือนก่อน

    Sir how can i extend this to chat bot which take input pdf of 15/50 pages where it containes images tables and content of text using langchain

  • @AbineshM-qg1us
    @AbineshM-qg1us 7 หลายเดือนก่อน

    can we use amazon titan multimodal embedding to get text along side image as output from the PDF and docx files.....

  • @rakeshkumar-pf6yu
    @rakeshkumar-pf6yu 6 หลายเดือนก่อน +2

    I am getting error in this line of code...can you please explain about this Krish....new_db = FAISS.load_local("faiss_index", embeddings)...I have used this line of code also..........langchain_community.allow_dangerous_deserialization = True..........the error is that it is not able to read my local files from the visual studio...

    • @hrikhi
      @hrikhi 6 หลายเดือนก่อน +1

      same problem

  • @edwardchan3521
    @edwardchan3521 10 หลายเดือนก่อน

    Thanks very much. How can I run it in Colab?

  • @bgmihighlights6378
    @bgmihighlights6378 3 หลายเดือนก่อน

    can we include this in our resume?

  • @gamekhela
    @gamekhela 2 หลายเดือนก่อน

    how Implementing Caching Mechanism for Chatbot Responses

  • @vaibhavahire4863
    @vaibhavahire4863 7 หลายเดือนก่อน

    Can we fetch image as well from pdf using this project

  • @ChayanPandit07
    @ChayanPandit07 6 หลายเดือนก่อน

    Hello sir. I have a doubt in 20:33 , what does the variable "context" in prompt template contain? We later using "input_docs" in conversational chain, but "context" is not used. Can you please clarify?

    • @ApekshaKallur
      @ApekshaKallur หลายเดือนก่อน

      I have the same question.

  • @angnat05
    @angnat05 4 หลายเดือนก่อน

    got an error IndexError: list index out of range when try to Submit n Process Scaned document, please help

  • @akeshagarwal794
    @akeshagarwal794 9 หลายเดือนก่อน

    Hello @krishnaik06 sir,
    I want the user to get a response along with token usage for generating that particular response.
    I hope you consider this in the next End-to-End Project lots of love for you channel😊❤

  • @Datasciencefiverr
    @Datasciencefiverr 10 หลายเดือนก่อน +2

    ValidationError: 1 validation error for LLMChain llm Can't instantiate abstract class BaseLanguageModel with abstract methods agenerate_prompt, apredict, apredict_messages, generate_prompt, invoke, predict, predict_messages (type=type_error) what is this error can anyone help

    • @vijaybhavesh
      @vijaybhavesh 10 หลายเดือนก่อน +1

      need to update the langchain inorder to fix it

  • @surindersood2951
    @surindersood2951 4 หลายเดือนก่อน

    how you will read an image in the pdf?

  • @aniketgami2541
    @aniketgami2541 9 หลายเดือนก่อน

    If I need to write good morning to chat...
    so answer should to be display like.
    good morning. How can i help you...

  • @oussamazorrig8762
    @oussamazorrig8762 8 หลายเดือนก่อน

    Can we extract images from pfd files as well?

  • @RahulPrajapati-jg4dg
    @RahulPrajapati-jg4dg 9 หลายเดือนก่อน

    Hello sir my business problem is some tricky like how i will also get the page number along with question from the given pdf can you please help me

  • @hanzalahhashmi3090
    @hanzalahhashmi3090 6 หลายเดือนก่อน

    Hey Krish, I am getting a bit of a problem, I've tried from 2 accounts its giving me a 400 eror API kry not valid, but i even made another account for it.
    Please help me out

  • @trinitywarlord
    @trinitywarlord 8 หลายเดือนก่อน

    Check out my project DocCuddle as it was purely inspired by this tutorial, and I believe there is room to enhance it with additional features, such as a video summarizer or other functionalities so let me know what else can I add. Developing this project was truly enjoyable, especially while watching Krish Naik's tutorials. Thanks sir!

  • @KARMAtogetherwithGHOST
    @KARMAtogetherwithGHOST 10 หลายเดือนก่อน +1

    how i write all this commands in pip

  • @kimberly_869
    @kimberly_869 9 หลายเดือนก่อน

    Finally I can get documents to just shut up sometimes, you know?

  • @kopallesidhartha1285
    @kopallesidhartha1285 10 หลายเดือนก่อน +11

    I used your code where the response is {'output_text': 'Answer is not available in the context'} even with the proper context can you help with the proper response

    • @FalahgsGate
      @FalahgsGate 10 หลายเดือนก่อน

      the same error ....no solution now ..are getting a solution for the problem?

    • @shubhamrathod9969
      @shubhamrathod9969 9 หลายเดือนก่อน +3

      First, try this: Increase the context length to 10000 in charactersplitter.
      If that doesn't happen: Try changing
      response = chain(
      {"input_documents": docs, "question": query}
      , return_only_outputs=True)
      to
      response = chain.invoke(
      {"input_documents": docs, "question": query}
      , return_only_outputs=True).
      I just wanted to let you know that this worked for me.

    • @sanjaydas1979
      @sanjaydas1979 7 หลายเดือนก่อน

      @@shubhamrathod9969 i tried the code which shown in the video and got
      IndexError: list index out of range
      Can you help me with this.

    • @Musicvocalhub
      @Musicvocalhub 7 หลายเดือนก่อน

      But where we have used the word query ​@@shubhamrathod9969

    • @akshayrawat7658
      @akshayrawat7658 3 หลายเดือนก่อน

      Even after using above approaches, still facing same problems

  • @Denialliving
    @Denialliving 5 หลายเดือนก่อน

    How to check efficiency of this model..

  • @prazyraj1735
    @prazyraj1735 6 หลายเดือนก่อน

    I have this use-case where there are different types of documents. I can parse documents using document loaders using langchain. But, there are images also in these documents. I want to store them as metadata and if answer generated from a context chunk it show the image also. Please help.

    • @harishsharma9466
      @harishsharma9466 6 หลายเดือนก่อน

      Hey, If you find the answer please let me know.

  • @kingish_yt
    @kingish_yt 10 หลายเดือนก่อน +1

    AttributeError: 'bytes' object has no attribute 'seek'
    please resolve

    • @WhatsDiscuss
      @WhatsDiscuss 9 หลายเดือนก่อน

      You can use request.files.getlist('parameter') instead of You can use request.files['parameter']

  • @mohammedaitkheri6200
    @mohammedaitkheri6200 4 หลายเดือนก่อน

    Plz , what is the last command to run this code?

  • @qzwwzt
    @qzwwzt 8 หลายเดือนก่อน

    How could I print an answer? or a set of answers?

  • @KumR
    @KumR 10 หลายเดือนก่อน +3

    I did the whole thing but no matter what question I ask I keep getting the same - Reply: answer is not available in the context .. Any suggestions?

    • @krishnaik06
      @krishnaik06  10 หลายเดือนก่อน +2

      Increase the context lenght to 10000 in charactersplitter

    • @azharudeensalim2898
      @azharudeensalim2898 10 หลายเดือนก่อน +1

      are u able to run it without any error

    • @KumR
      @KumR 10 หลายเดือนก่อน

      @@azharudeensalim2898 - yeah the streamlit opened and I was also able to upload a pdf.

    • @shubhamrathod9969
      @shubhamrathod9969 9 หลายเดือนก่อน

      First, try this: Increase the context length to 10000 in charactersplitter.
      If that doesn't happen: Try changing
      response = chain(
      {"input_documents": docs, "question": query}
      , return_only_outputs=True)
      to
      response = chain.invoke(
      {"input_documents": docs, "question": query}
      , return_only_outputs=True).
      I just wanted to let you know that this worked for me.

    • @sakshisrivastava1411
      @sakshisrivastava1411 6 หลายเดือนก่อน

      @@shubhamrathod9969 still not working for me