LLM Project | End to End Gen AI Project Using Langchain, OpenAI in Finance Domain

Поделиться
HTML-код
  • Опубликовано: 23 ноя 2024

Комментарии • 379

  • @codebasics
    @codebasics  Год назад +14

    Check out our premium machine learning course with 2 Industry projects: codebasics.io/courses/machine-learning-for-data-science-beginners-to-advanced

    • @shaonsikder556
      @shaonsikder556 Год назад +1

      I am always grateful to you. You are the my only teacher who teaches me basics of data science properly. Now with this LLM. langchain. You have superpower to explain everything in very easy way for a dumb student like me. I couldn't be a data scientist and fulfill my dream if you weren't there. Thanks for everything, please do continue this kinda projects for each domain🙏🙏🙏🙏💝💝💝

    • @chinnibngrm272
      @chinnibngrm272 Год назад

      Did you tried this Rockybot
      I am facing one error please help me to solve it
      list index out of range
      index = faiss.IndexFlatL2(len(embeddings[0]))
      @@shaonsikder556

    • @fusionxfitness_
      @fusionxfitness_ 7 месяцев назад +1

      please resolve the index 0 issue

    • @kishanhajari9231
      @kishanhajari9231 7 месяцев назад

      can I use Gemini API key instead of Open AI?

    • @rahulvishwakarma3996
      @rahulvishwakarma3996 6 месяцев назад

      How model will work when 5 different users are providing different url to model simultaneously?

  • @ashishmalhotra2230
    @ashishmalhotra2230 7 месяцев назад +2

    I like the way you explain the business scenario and toolset required to implement the solution in the PoC and Production phases.

  • @RAGHUPATI.1SI18EC07
    @RAGHUPATI.1SI18EC07 7 месяцев назад +1

    Best thing I love about this guy is, he let the audience feel the problem, so that when he is doing this he will be clear that I am solving this problem this should be the approach, love u man for all the content u make

  • @mrudular348
    @mrudular348 Год назад +17

    This is the best tutorial I have watched on LLM. Crisp, yet detailed. Thank you!

  • @madhu1987ful
    @madhu1987ful Год назад +10

    An end to end langchain project cannot be more clearer and perfect than this one !

  • @frank.nelson
    @frank.nelson Год назад +26

    Found a lot of stuff on Langchain on RUclips. But no one went this deep with individual langchain concepts as you did. A lot of confusing topics got cleared today. THANKS FOR THIS. ❤

    • @codebasics
      @codebasics  Год назад +3

      Glad you enjoyed it!

    • @chinnibngrm272
      @chinnibngrm272 Год назад

      sir please help me to solve this error
      list index out of range
      index = faiss.IndexFlatL2(len(embeddings[0]))@@codebasics

  • @arpitak20
    @arpitak20 5 месяцев назад +5

    One of the best courses on RUclips to learn GenAI. Thanks a lot for this

  • @tarasankarbanerjee
    @tarasankarbanerjee 11 месяцев назад +6

    It's just a perfect combination of depth and width!! Thank you so much!!

    • @aaditstudent
      @aaditstudent 2 месяца назад

      what version of lang chain are you using ?

  • @DeekshithP-r8p
    @DeekshithP-r8p 9 месяцев назад +2

    Thank you so much for this wonderful tutorial, really helps me in implementing a POC in my company

  • @sujithsaikalakonda4863
    @sujithsaikalakonda4863 Год назад +5

    Thank you sir for this wonderful tutorial, which made me understand about the end to end LLM project in a simple way. Great work.

  • @vinamradutt4623
    @vinamradutt4623 10 месяцев назад +4

    Thanks a lot, I'm so happy that I came accross this video. Best tutorial.

  • @mksklb2003
    @mksklb2003 5 месяцев назад +1

    you are awesome teacher, I rarely post comments below yt movies.. you just have explained it in very easy and understable way.. ;-) well done

  • @krishna_kagitha
    @krishna_kagitha 3 месяца назад

    This is the best tutorial i have watched till date, kudos for the effort to put in to make this video.

  • @roshanmaharana
    @roshanmaharana Год назад +83

    Coding... Coding... Coding... I don't like it! I avoid! But! Coding likes me! I can't avoid!

  • @shaktisingh8217
    @shaktisingh8217 5 месяцев назад +1

    Another excellent learning video! You explained the end-to-end LangChain application workflow very nicely. Thanks!

  • @zainulabideen_1
    @zainulabideen_1 Год назад +7

    Your tutorials are amazing and these are really helpful

  • @AliKibao
    @AliKibao Год назад +4

    Absolute best explanations. To class. Thank you.

  • @himanshupatidar8040
    @himanshupatidar8040 9 месяцев назад

    what more simple explanation could be possible than this. Awesome explanation and project concept.

  • @paramjjethwa8734
    @paramjjethwa8734 2 месяца назад +2

    dude i just started and loved the rocky bhai story HAHAHAHAHAHA

  • @QanbarIjaz
    @QanbarIjaz 4 месяца назад

    Accept my gratitude all the way from Pakistan ❤️

    • @codebasics
      @codebasics  4 месяца назад +1

      🙏🏼

    • @CertifiedAuthur
      @CertifiedAuthur 4 месяца назад

      I'm getting bugs over here. How did you get passed the index out of range?

  • @mohammed37
    @mohammed37 Месяц назад

    Excellent video. Very well explained. Thank you so much!

  • @tusharbedse9523
    @tusharbedse9523 Год назад +3

    Amazing video Dhaval!!! Do you have MLOps playlist please share, if not could you please think about creating it using mlflow or zenml because i like the way you teach. Thanks!

  • @chinnibngrm272
    @chinnibngrm272 Год назад

    The Best best best video on langchain+llm in youtube Thank you sir for wonderful content.
    Please upload the videos on how to finetune our own data and some more real world usecases like this video .............😇😇😇😇

  • @shivampranjale7653
    @shivampranjale7653 9 месяцев назад +4

    Getting an error:
    module 'magic' has no attribute 'from_buffer'
    tried multiple fixes, but unable to resolve.

  • @ayushisingh2924
    @ayushisingh2924 2 месяца назад

    Hi, Thanks for such an amazing session that made me very comfortable with langchain

  • @AlonAvramson
    @AlonAvramson Год назад +1

    Thank you! your trainings were always great and this one is even greater!

  • @jeevananthanm8155
    @jeevananthanm8155 9 месяцев назад

    such a nice explanation sir. well understood. got an idea for my project work ,thank you sir .

  • @rishik-w1j
    @rishik-w1j Год назад

    this is a movie or theory well explained and a powerful content thanks for this need more...

  • @d25102
    @d25102 Год назад

    i was working on a langchain project myself! perfect timing!

  • @markwaller650
    @markwaller650 10 месяцев назад

    Thanks this explains the concepts really well and brings them to life.

  • @ManoharBediya
    @ManoharBediya 4 месяца назад

    Thanks sir theory is completed ,now I have to implement

  • @codebasics
    @codebasics  Год назад +11

    If anyone is facing list index out of range error then here is an open github issue: github.com/langchain-ai/chat-langchain/issues/68
    Using a different version of langchain may help.

    • @meetulagrawal6498
      @meetulagrawal6498 7 месяцев назад +1

      I tried 3 different versions but it did not work, on which version it might work?

  • @zeeshanafridi798
    @zeeshanafridi798 8 месяцев назад

    The best one so far! Amazing

  • @motivationmantra5206
    @motivationmantra5206 8 месяцев назад

    super useful thank you so much. you are great tutor expecting more videos like this

  • @787ankur
    @787ankur 7 месяцев назад

    thank you so much sir. The project and explanation were very helpful

  • @deepankarsharma7840
    @deepankarsharma7840 Год назад

    Literally had this same project last month in my organisation

  • @richardnwachukwu7664
    @richardnwachukwu7664 Год назад +1

    Nice eee jumping in this weekend thank you

  • @keerthanachemburi7121
    @keerthanachemburi7121 8 месяцев назад +1

    i am constantly getting following error at the end: 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.).

  • @sanskarkhandelwal
    @sanskarkhandelwal 2 месяца назад

    The intro is just lit

  • @Arun-lx7bb
    @Arun-lx7bb 8 месяцев назад +2

    I am currently doing this project and it shows error that you exceeded your quotation limit

  • @ZoroOenma
    @ZoroOenma 7 месяцев назад +1

    @codebasics sir when i am running this model in my localhost after spillting step it is showing index out of range

  • @learnwithfun.
    @learnwithfun. Год назад +1

    hello sir the content is awesome and I will recommend it to my friends for sure.If possible it would be still more helpful if you can explain the conversion of table data into the contextual data in further vedio.

  • @surajmishra3330
    @surajmishra3330 9 месяцев назад

    Should have invested in Nvidia 5 months before to double the amount, Bro give the best financial advice 😜

  • @SharathBJGowda
    @SharathBJGowda 5 месяцев назад

    happy to see Rocky bhai reference :)

  • @ddiilaaraa
    @ddiilaaraa 11 месяцев назад

    Amazing videos in the playlist! Thank you for your hard work!

  • @RedCloudServices
    @RedCloudServices Год назад +1

    Thank you. I have a question why not use a news API to retrieve article and company topics that individual urls?

  • @CreativeMind0061
    @CreativeMind0061 13 дней назад

    When I tried to run this project I'm getting below error:
    ModuleNotFoundError: No module named 'altair.vegalite.v4' when I run the 'streamlit run main.py' command.
    I tried different versions which is suggested by GPT and also tried stack overflow. But not resolved issue. I appreciate your help.

  • @chan90s
    @chan90s 9 месяцев назад

    Rocky bhai made me watch the whole video😂 good job

  • @lisagirard4504
    @lisagirard4504 Год назад +2

    This was an awesome overview! Thank you for all the work put into it!😍

  • @shubharaju7505
    @shubharaju7505 3 месяца назад

    hi, for classification use cases do you suggest traditional (SVM, Bayes) Vs RAG /LLM approach.I am new and trying to understand the right use case and match right approach to solve,

  • @RZOLTANM
    @RZOLTANM 6 месяцев назад

    Please do a video on LlanGraph...you will do it better than others for sure.

  • @Vedhar2104
    @Vedhar2104 Год назад +1

    To learn llm what is prerequisites... please clearly mention
    Is machine learning /deep learning required? @codebasics

  • @rama_bhuyan
    @rama_bhuyan 10 месяцев назад

    Thank you so much Dhruw for this wonderful explanation :)

  • @souravbarua3991
    @souravbarua3991 Год назад

    Awesome project tutorial. Thank you. Learned a lot and will use in my projects. 🙏🙏🙏🙏

    • @codebasics
      @codebasics  Год назад

      Glad it was helpful!

    • @chinnibngrm272
      @chinnibngrm272 Год назад

      sir please help me to solve this error
      list index out of range
      index = faiss.IndexFlatL2(len(embeddings[0]))@@codebasics

    • @chinnibngrm272
      @chinnibngrm272 Год назад

      sir please help me to solve this error
      index = faiss.IndexFlatL2(len(embeddings[0]))

    • @souravbarua3991
      @souravbarua3991 Год назад

      ​@@codebasicsI have used this technique with open source llm and completed a project of chat with local pdf files. For a lack of resources I can't able to build UI for that.i already posted this project documentation in my LinkedIn profile.

  • @athiagarajan
    @athiagarajan 10 месяцев назад +1

    can we use other llms other than open ai - if so how
    - also can you show how this is done on sagemaker

  • @madhu1987ful
    @madhu1987ful Год назад

    I am a beginner to this langchain, LLM world. Just wanted to understand in this example how is the PROMPT to the LLM being created - is it automatic? we are providing the query in the form of streamlit UI input & context in the form of retrieved chunks from vector DB this I understood.

  • @antony2684
    @antony2684 4 месяца назад

    Nice work sir... It's clear understanding... 🎉🎉😊😊😊

  • @srinivasvenkatraman3594
    @srinivasvenkatraman3594 Год назад

    Very good tutorial.Thanks for all the effort.

  • @FirstNameLastName-fv4eu
    @FirstNameLastName-fv4eu 11 месяцев назад +1

    This is the biggest challenge of AI - 99% of the AI RUclips stars are inventing something which has already been solved 15 yrs back.

  • @gazart8557
    @gazart8557 Год назад

    Woow..my new hero Peter Pandey

  • @wongsimon2387
    @wongsimon2387 4 месяца назад

    Amazing! Big Thank You Sir.

  • @Pushkar-k2t
    @Pushkar-k2t 8 месяцев назад

    why did you not do Vector Embedding in the project? You did it in the Interstellar Text.

  • @ravi1341975
    @ravi1341975 3 месяца назад

    Hi,thanks for this wonderful video.Whne i was implementing LangChain's UnStructuredURLLoader,i am getting libmagic is unavailable and python version==3.10.

  • @plamenyossifov6135
    @plamenyossifov6135 11 месяцев назад

    great video! could you please do a video on how to set up our jupyter environment?

  • @aishu2623
    @aishu2623 Год назад

    Waiting for this series!!
    Thank you

  • @lohethsenthil9638
    @lohethsenthil9638 2 месяца назад

    we can just provide the web link to gpt-4 and ask questions right? how is this any different from that?

  • @varunkumarsingh758
    @varunkumarsingh758 9 месяцев назад

    Hello, Thank you for the video. I have a Question. Is there a technical way to measure the validity of responses?

  • @MAHDEO
    @MAHDEO 2 месяца назад

    AMAZING WORK DONE, SIR I REALLY APPRECIATE YOUR EFFORTS!

  • @DataFunAnalyticaltricks
    @DataFunAnalyticaltricks 7 месяцев назад

    Great Explaination Thank you so much !

  • @bhaskarmarepalli2448
    @bhaskarmarepalli2448 10 месяцев назад

    Lets assume there is a cron job resding the urls. After a few days will the vector database has huge size? I have requirement where i want to read some documents(PDFs/docx) and get same data from each of it, answer a few questions. Do i need a vector db here? If so doesn't the size grow?

  • @paramjjethwa8734
    @paramjjethwa8734 2 месяца назад +1

    while using unstrcutured URL loader i am facing nltk issue which says punkt tab is not found in the directory i have checked it is present but still same issue

    • @PraptiAdep
      @PraptiAdep Месяц назад

      Same problem
      Did you find solution ??

  • @ravindarmadishetty736
    @ravindarmadishetty736 5 месяцев назад

    One question here
    How are we fetching the required chunks as per the prompt given? Can you please throw some link or suggest how this we can tackle?

  • @rtdi4200
    @rtdi4200 Год назад +4

    Hi Dhaval - do you think streamlit has a future potential to implement a quick dashboard app at corporate level and get rid of tedious frontend coding ?

  • @mainuddinali9561
    @mainuddinali9561 3 месяца назад +1

    i want to deploy this project but lack of secret key, i can't do,

  • @RobertoFabrizi
    @RobertoFabrizi 11 месяцев назад +1

    Is it possible to "replace" the urls with github repositories of code or documentation? I'd also be important to keep the source metadata just like in this urls example to understand from which document inside which repo the answer came from. Thank you very much!

  • @panhtran8384
    @panhtran8384 Год назад

    thank you very much 😍. Can you post the slide, it's very helpful

  • @arpitak20
    @arpitak20 5 месяцев назад

    Is there an advanced course video for industry professionals which can teach how to build such applications for real time company use case?

  • @RutujaKokate-u5h
    @RutujaKokate-u5h 10 месяцев назад

    Why didnt we use SentenceTransformer and FAISS in the final project ?

  • @erwangilloisrenon6315
    @erwangilloisrenon6315 Год назад

    Just a thought is or unniverse is quantified .
    If we want to make a simulation what tokens numberwould be the max.

  • @aishu2623
    @aishu2623 Год назад +1

    Sir this is really superb!! Can u plz generate high end machine learning real life projects with data cleaning preprocessing and modelling and end it with a web application.......it would be a very great help as being a student...

    • @alphar85
      @alphar85 Год назад +2

      I think he has done it already. Potatoe disease project.

    • @aishu2623
      @aishu2623 Год назад

      @@alphar85 that comes under Deep learning for my 5th sem project I have done that

    • @aishu2623
      @aishu2623 Год назад

      @@alphar85 and moreover no data cleaning process is involved in potato disease classification. And plz respect it is sir not him.
      Thank u

    • @alphar85
      @alphar85 Год назад

      @@aishu2623 ok sorry i thought you just wanted an end to end project.

    • @alphar85
      @alphar85 Год назад +1

      @@aishu2623 data cleansing is subject yo project. His data cleansing will most probably be different to your project esp if you are customising it. Otherwise if you are just copying and pasting then it is a different matter. Best of luck

  • @harsh2014
    @harsh2014 8 месяцев назад

    Thanks for this nice tutorial !

  • @RakeshA-eq3dw
    @RakeshA-eq3dw Год назад +2

    Rocky boi hehe

  • @naveenreddynarala1700
    @naveenreddynarala1700 7 месяцев назад

    Thanks a lot, Could you please create LLM builder on structured data.

  • @hariprasanth8342
    @hariprasanth8342 6 месяцев назад

    which python version should be used to run this project. Not all the dependencies are getting installed with the latest version of python which is 3.12

  • @bash98ar
    @bash98ar 7 месяцев назад

    Thank you very much. its great.

  • @shalabhchaturvedi6290
    @shalabhchaturvedi6290 7 месяцев назад

    Thank you!. very much useful.

  • @DataDude-oi7si
    @DataDude-oi7si Год назад

    Can we use scrapping and automation libraries like Selenium and beautifulsoup for long term project???

  • @dishatamore9552
    @dishatamore9552 Месяц назад

    what if i put other url links will i get the insights ......and is it made only for finance

  • @mansimaurya2852
    @mansimaurya2852 2 месяца назад

    I am getting this error
    cannot pickle '_thread.RLock' object
    Please tell a fix for this. And also this video is a gem.

  • @mahendrachourasiya
    @mahendrachourasiya 7 месяцев назад +3

    Can anyone please suggest me from where Will I get free api key. And how to use it in the .env file?
    My project is ready but question answer is not working. Please help me with this

  • @sciencedude4733
    @sciencedude4733 10 месяцев назад

    When loading the pkl file, I keep getting "ModuleNotFoundError: No module named 'langchain.schema.document'" error. I am using python 3.11.1 on Macbook Air. Thanks!

  • @gunjansingh9956
    @gunjansingh9956 8 дней назад

    anyone please tell me why we put three URLs and can i put only one if i need?

  • @dineshkhapariye445
    @dineshkhapariye445 2 месяца назад

    is there any key metrics to check the performance of llm ?????

  • @ravindarmadishetty736
    @ravindarmadishetty736 5 месяцев назад

    Great video Dhaval👍

  • @sonalikri52
    @sonalikri52 Месяц назад

    Can an MBA finance student do this project? If she is looking for financial analyst job?

  • @nirmesh44
    @nirmesh44 Год назад +2

    Wonderful content. Super useful. Thanks a lot!. I am getting "list index out of range" error on "FAISS.from_documents(docs, embeddings)". Any idea?

    • @KM-kj6nm
      @KM-kj6nm Год назад

      Same. Did you find any solution?

    • @codebasics
      @codebasics  Год назад

      Hey can you check if it is this issue? github.com/langchain-ai/chat-langchain/issues/68
      One way could be to use the same langchain version that I am using 0.0.284 Please install the same version of libraries as specified in requirements.py

    • @chinnibngrm272
      @chinnibngrm272 Год назад

      Not Able to solve the issue sir .....please provide the correct solution to solve the error@@codebasics

    • @Ep-gw4bl
      @Ep-gw4bl Год назад

      @@chinnibngrm272did u find a solution bro?

    • @FallenAshura
      @FallenAshura 10 месяцев назад

      @@chinnibngrm272 were ypu able to solve that error?

  • @NikhilGupta-e5n
    @NikhilGupta-e5n 10 месяцев назад

    hello sir,
    I was confused how can i create selenium test cases of a web application using langchain
    can i directly import the selenium documentation and expect the ai to create the test case(for example: a button functionality).

  • @Yogic-ignition
    @Yogic-ignition Год назад

    Great helped a lot. But if i want a source link of the document which i have in my knowledge base (vector database) how would i be able to do that?

  • @IlyesBouzidi-f2s
    @IlyesBouzidi-f2s 10 месяцев назад

    can you suggest an open source embedding instead of openAI embedding, that works fine for this project?
    I used bert and glove, and received nothing but endless errors

  • @mrsecretstatus9999
    @mrsecretstatus9999 8 месяцев назад

    What are pre requisites, I have done python and library like numpy and pandas can I do this or I need to learn some thing first