I Analyzed My Finance With Local LLMs

Поділитися
Вставка
  • Опубліковано 21 гру 2024

КОМЕНТАРІ • 422

  • @YoutubeCom_11
    @YoutubeCom_11 6 місяців тому +42

    Update: Ollama now works on Windows normally

    • @Thuvu5
      @Thuvu5  6 місяців тому

      Yayyy! Great news!

  • @TailorJohnson-l5y
    @TailorJohnson-l5y 8 місяців тому +39

    Are you a real human? I have NEVER seen an author on youtube cover so much incredible knowledge in such a short video. This is absolutely AMAZING!!! Thank you

    • @martingrillo6956
      @martingrillo6956 8 місяців тому +2

      Her being an AGI would make perfectly sense

    • @Scarsuna
      @Scarsuna 9 днів тому

      @@martingrillo6956 Or she used her AI skills to generate the teleprompter output she's reading? ;)

  • @roberthuff3122
    @roberthuff3122 10 місяців тому +4

    🎯 Key Takeaways for quick navigation:
    00:00 💲 *Reviewing Income and Expense Breakdown*
    - Explained the process of analyzing financial transactions.
    - Talked about classification of expenses into categories.
    - Spoke about using low-tech ways and an AI assistant for classification.
    02:16 💻 *Running a Large Language Model Locally*
    - Discussed different ways to run an open-source language model locally.
    - Listed various popular frameworks to run models on personal devices.
    - Explained why these frameworks are needed, emphasizing the size of the model and memory efficiency.
    04:18 📚 *Installing and Understanding Language Models *
    - Demonstrated how to install a language model through the terminal.
    - Showed the interaction with the language model through queries in the terminal.
    - Assessed the model's math capabilities, showing a failed example.
    06:48 🎯 *Evaluating Expense Classification of Language Models*
    - Checked if the language models can categorize expenses properly through the terminal.
    - Demonstrated how to switch models, correctly installing another model.
    - Showed the differences between the models and preferred one due to answer formatting.
    08:24 🛠️ *Creating Custom Language Models*
    - Explained how to specify base models and set parameters for language models.
    - Demonstrated how to create a custom model through the terminal.
    - Discussed viewing the list of models available and building a custom blueprint to meet specific requirements.
    11:46 🔄 *Creating For Loop to Classify Expenses *
    - Discussed forming a for loop to classify multiple expenses.
    - Detailed how to chunk long lists of transactions to avoid token limit in the language model.
    - Mentioned the unpredictability of language models and potential need for multiple queries.
    14:32 🔍 *Analyzing and Categorizing Expenses*
    - Demonstrated how to analyze and categorize transactions.
    - Showed how to group transactions together, clean up the dataframe, and merge it with the main transaction dataframe.
    15:14 📊 *Creating Personal Finance Dashboard *
    - Detailed the creation of a personal finance dashboard, that includes income and expenses breakdown for two years.
    - Introduced useful visualization tools such as Plotly Express and Panel, giving a short tutorial on how to use them.
    - Demonstrated the assembling of a data dashboard from charts and supplementing it with custom text.
    17:02 📈 *Visualizing Financial Behavior Over Time*
    - Demonstrated the use of the finance dashboard, drawing observations.
    - Concluded with a note on importance of incorporating assets into financial management.
    - Highlighted the value of running large language models on personal devices for tasks like these.
    Made with HARPA AI

  • @whatifi-scenarios
    @whatifi-scenarios 9 місяців тому +12

    This is great. We're in the process of integrating LLMs into our "what if" scenario modelling platform and this gave me a few ideas on next steps. Sharing this video with my dev team!

  • @xugefu
    @xugefu 10 місяців тому +1

    Thanks!

  • @AshishRanjan-jn7re
    @AshishRanjan-jn7re 10 місяців тому +111

    Great video... My 2 cents: we can force LLMs to respond only in json format by stating it in system prompt, so you get consistent parsable response always (I've tried with gpt4), also you can provide list of possible expense categories to avoid grouping them together later (like 'Food & Beverage' and 'Food/Beverage')

    • @martinmoder5900
      @martinmoder5900 10 місяців тому

      Yeah, it is very powerful! However, is llama2 also providing this?

    • @NicolasCerveaux
      @NicolasCerveaux 9 місяців тому

      @@martinmoder5900 llama2 and even gemma:2b does that too, but when I tried it still generated "new" categories, and the json answers would be "odd" like sometime it would modify the name of the expense.

    • @siliconhawk
      @siliconhawk 2 місяці тому

      ​@@martinmoder5900 llama 3.1 (the new one) is pretty powerful so it should be able to do it for you. given enough compute power

  • @noahchristie5267
    @noahchristie5267 10 місяців тому +48

    Incredible intro video for the semi technical about how chat gpt and similar models will be used in daily life to improve the mundane tasks, with a side of cautions about incorrect answers and computational limitations! Great balance, I’m already sharing it around our team 😊

    • @Thuvu5
      @Thuvu5  10 місяців тому +1

      Thanks a lot for your comment and for sharing it around! Really appreciate it 🤩🙌

  • @johndoughto
    @johndoughto 4 місяці тому +2

    Awesome structure to convey a "simple" idea, without getting down into the weeds with how truly complicated it is. Thanks!

  • @etutorshop
    @etutorshop 7 місяців тому +2

    OMG this is inspiring I always wanted a 3rd party view about my expenses without loosing control of my data and this video hits the nail on the head.

    • @Thuvu5
      @Thuvu5  7 місяців тому

      So glad to hear! Good luck with your project 🤗

  • @jteichma
    @jteichma 8 місяців тому +1

    Thanks for the great overview of using aa local LLM Thuy! Very useful and informative.

  • @bimoariosuryandaru325
    @bimoariosuryandaru325 7 місяців тому +1

    This is great! I was recently experimenting on a personal finance tracker dashboard and connect it to a chatting apps, so the user could easily input their financial activity by only typing it. On the process, i try to use chat gpt to simplify and generalise the format so we can input the data faster, never have i thought that it could be done by a local LLM. Looking forward for your next video.

  • @kevinmanalang9182
    @kevinmanalang9182 10 місяців тому +6

    Hi Thu! Last year I had referenced your panel dashboard video to build my personal finance dashboard. I like seeing how you built yours. Your content is very useful. Thank you!

  • @SebastianSastre
    @SebastianSastre 10 місяців тому +4

    Thank you for sharing this dear! You covered the basics and shown the path to a great first goal with your own custom on premise and well licensed LLM. Huge!

    • @Thuvu5
      @Thuvu5  10 місяців тому

      You are so welcome! Glad it was helpful 🙌

  • @Codad
    @Codad 10 місяців тому +5

    This is such a great video. Thank you for making it. I had no idea this sort of thing was possible and I'm finding all sorts of ways to take advantage of it now.

  • @SamFigueroa
    @SamFigueroa 10 місяців тому +2

    I've noticed that most LLM understand that you would like a CSV formatted output and you use that to get more consistent output.

  • @PauloLeiteBR
    @PauloLeiteBR 9 місяців тому +1

    Excellent video, I used the concepts to enhance a project that I had already started in R and it worked fine, but so slow in my computer (like 5 min to analyse 10 registers). Now I know the concepts and I`ll keep experimenting with other LLM models. Thank you!

  • @brunogillet7132
    @brunogillet7132 5 місяців тому +1

    Thanks so much ! Being investigating AI for just one month, having so much to learn again (and that's cool), your videos really help.
    Being not a natural english speaker, it was a bit fast to follow, but no issue : It was clear, precise, and... I will find time to listen to it up to be sure having got any lesson from it.
    Same apply to your other videos, but change nothing :
    ( It could even help me improve my English level ;-)... )

    • @Thuvu5
      @Thuvu5  5 місяців тому

      Great to hear!

  • @voonoo2059
    @voonoo2059 5 годин тому

    Xin chao Thu, thanks for your great video. That's so mind blowing to see beyond the usual usage of ollama local AI.

  • @juliusprojeto
    @juliusprojeto 10 місяців тому

    Thank you very much

  • @borismeinardus
    @borismeinardus 9 місяців тому +2

    Love the video! The beginning sets up the project perjectly and the tutorial is very easy to follow!

  • @smiley3239
    @smiley3239 6 місяців тому +1

    Thank you! it's quite hard to follow up with this ollama thing, and you explain it so easily. thank you!!! please mae more of this!!!!

  • @n0n4m3y3t
    @n0n4m3y3t 3 місяці тому

    thank you for including the repo!! it makes the content 10x better!

  • @soky2466
    @soky2466 6 місяців тому +1

    Incredible video, I love how you simplified all the process. Your content inspired me I will try it on my personal projects as well

    • @Thuvu5
      @Thuvu5  6 місяців тому

      Awesome, go for it!

  • @anissaa1017
    @anissaa1017 7 місяців тому +1

    Thank you so much for sharing this with us!! I’ve been looking to do this for years but just thinking about the task ahead, I would give up. I will definitely analyze my own financial statements. Thanks mucho gusto!!

  • @gridaranbirthuvi
    @gridaranbirthuvi 8 місяців тому

    Great video .. The one project which I wanted to take up during my holidays .. Learn in the same time have a view on my personal finance ..

  • @MarketMoves365
    @MarketMoves365 3 місяці тому +1

    I love the content. Also, I have not seen anyone can program so fast!!!

  • @tolandmike
    @tolandmike 6 місяців тому +1

    You just earned a new subscriber, Thu. I mean, wow. Very inspirational to see what you built on a friggin laptop, no less. Goes to show you don't need thousands of compute cores, either. Ver very cool. 🎉

    • @Thuvu5
      @Thuvu5  6 місяців тому

      Wow, thanks you so much! Indeed, we definitely don't need to go broke buying super computer for this 🙌

  • @Jaybearno
    @Jaybearno 10 місяців тому +2

    Cool project! I'd like to try it myself. One interesting idea is to have the LLM generate a memo field for each transaction (which can be controlled via prompting). Then by embedding these and doing hybrid retrieval, you can search in natural language as well as by metadata for transactions.

    • @Thuvu5
      @Thuvu5  10 місяців тому +1

      That’s an interesting idea! Would love to see how well the retrieval works 🤗

  • @luismoriguerra669
    @luismoriguerra669 8 місяців тому +1

    this is one of the best videos I watched about llms

  • @korntron
    @korntron 10 місяців тому +18

    Outstanding video, especially for this beginner. Didn’t know you could run the models locally. Those ollama layers look like docker, fascinating how the context is setup. Time for me to spend some cycles on all your vids, not just the couple I’ve casually looked at. Thanks!

    • @Thuvu5
      @Thuvu5  10 місяців тому +2

      Glad to hear you found the videos helpful! Thanks for stopping by 🙌🏽

    • @pw4827
      @pw4827 10 місяців тому

      Me too. I thought you need to have some monstrous supercomputer and spend weeks on configuring everything to run one of these models locally

  • @PhilSmy
    @PhilSmy 9 місяців тому +1

    Great video. Very inspiring. Also...I used to live in Amstelveen (20+ years ago!). Funny to see that name in there.

    • @Thuvu5
      @Thuvu5  9 місяців тому

      Oh haha, the world is small! 😀

  • @apvitor
    @apvitor 8 місяців тому

    You are a very good presenter, easy to follow. Nice content

  • @youthresearches
    @youthresearches 10 місяців тому +3

    As always, high-quality content from a highly competent woman!

    • @Thuvu5
      @Thuvu5  10 місяців тому

      That's so kind of you, I'm trying to be ;)

  • @jman9545
    @jman9545 7 місяців тому +2

    Super cool! Great channel. Excited to watch more

  • @ricb4195
    @ricb4195 10 місяців тому +1

    I loved this and hope to try this out for myself (though my programming skills are very rusty)

  • @GeorgeZoto
    @GeorgeZoto 10 місяців тому +1

    Excellent video and practical application, you didn't get to cover pydantic much which solves a current challenge with LLMs. As for the dashboard, maybe another framework or approach with less or no code could be be more efficient :)

  • @bereniceflores81
    @bereniceflores81 9 місяців тому +1

    Always good to see more people bringing data skills to understand personal finance.

  • @Arsenik2
    @Arsenik2 4 місяці тому +4

    As a data scientist, I am blown away by your video's theme. You successfully managed to keep it simple to attract the interest of the majority and mention about technical details that is beneficial for more technical people watching this video. Best wishes!

  • @TheInternalNet
    @TheInternalNet 10 місяців тому +1

    I learned so so much watching this. Thank you so much.

  • @mustafadut8430
    @mustafadut8430 10 місяців тому +1

    If you want to give data as many as the number of tokens of the model. You don't need to calculate and know by hand. Instead, you can do this with "chunks" in Langchain. nice explanation thank you

  • @kylonguyen-we5mx
    @kylonguyen-we5mx 5 місяців тому +1

    Thanks sis, you're awesome!

  • @michaelmraz2707
    @michaelmraz2707 6 місяців тому

    How to make LLM learn and be able to correctly identify new categories? For example, creating an income statement from the list of all journal entries, but LLM need to identify each entries and correctly categorized it. Say, there's an entry for a plane ticket and wages paid to XYZ. The LLM reads the entries and correctly map it to expense item "travel expense" and "salaries/wages" expense.
    This is similar concept to your video, but more broad with the ability to learn.

  • @olivermorris4209
    @olivermorris4209 10 місяців тому +6

    Thanks Thu, great demo of Ollama, sorry your arent going to be retiring anytime soon😢
    I really like the multimodal model support in Ollama, llava is a great model to try and runs on not much RAM.

    • @Thuvu5
      @Thuvu5  10 місяців тому

      Thank you Oliver! I would absolutely not mind making videos until I retire though 🤣. The multimodal support is interesting, I haven't tried it out yet but will look into those models a bit more 🙌🏽.

  • @akinwalehabib
    @akinwalehabib 9 місяців тому +1

    Amazing work you put in here. This is inspiring

  • @winhater
    @winhater 10 місяців тому +1

    I never ever ever comment on anything, but goddamn - what a great video/tutorial. Just finished playing with the notebook and I learned a ton!

    • @Thuvu5
      @Thuvu5  10 місяців тому

      That’s so awesome to hear! Thank you so much for commenting ❤️🤗

  • @gr8tbigtreehugger
    @gr8tbigtreehugger 10 місяців тому +10

    This was an excellent video - many thanks for sharing!

  • @Turbo_Tastic
    @Turbo_Tastic 9 місяців тому +1

    this is great.. thank you for the breakdown of all these options

  • @marijnstollenga1601
    @marijnstollenga1601 10 місяців тому +1

    You can get rid of the randomness by setting the temperature to 0, or controlling the seed.

    • @Thuvu5
      @Thuvu5  10 місяців тому

      Thank you, this would be better indeed!

    • @marijnstollenga1601
      @marijnstollenga1601 10 місяців тому

      Btw another good trick, at least with llama.cpp you can define a grammar for the output. So instead of coaxing it and validating, you can _force_ it to output e.g. json, or even a more specific grammar! @@Thuvu5

    • @marijnstollenga1601
      @marijnstollenga1601 10 місяців тому

      I lost my other reply I think. I wanted to point out that you can use grammars to force the output you want (in llama.cpp at least). So instead of asking to reply json and validating, you can set the grammar so only valid tokens are considered! Very overlooked feature @@Thuvu5

    • @xiyangyang1974
      @xiyangyang1974 10 місяців тому

      Would there be no disadvantage?

    • @marijnstollenga1601
      @marijnstollenga1601 10 місяців тому

      I think there is a higher chance of repetition, but you have repetition penalties for that. And indeed less 'creativity' but when you classify data in this case you don't want that anyway @@xiyangyang1974

  • @thinkingmachine7760
    @thinkingmachine7760 10 місяців тому +17

    Thank you so much. 🥰It is so well explained and a very cool project. I think LLMs are a powerful tool and running them locally will make it safe to share critical information with them.

    • @Thuvu5
      @Thuvu5  10 місяців тому +2

      Thank you, really appreciate it! ❤

  • @positivitywins8957
    @positivitywins8957 9 місяців тому +1

    Amazing job explaining this!

  • @icemelt7ful
    @icemelt7ful 9 місяців тому

    As a Javascript coder, this was a mindblowing video, I had no idea Python was this powerful.

  • @DorianIten
    @DorianIten 8 місяців тому

    Amazing.
    Thank you for sharing this, I learned so much!

  • @sanatdeveloper
    @sanatdeveloper 9 місяців тому +1

    Awesome research as always!

  • @franklimmaciel
    @franklimmaciel 5 місяців тому +1

    Thanks for this great video.

  • @DarkSoulGaming7
    @DarkSoulGaming7 7 місяців тому +1

    Thank you SOOOOOOO much for this !! this is an awesome tutorial

    • @Thuvu5
      @Thuvu5  7 місяців тому +1

      You are so welcome! Glad you like it!

  • @leonardvermeer7908
    @leonardvermeer7908 10 місяців тому +1

    What an amazing video! This is definitely a personal project that I've wanted to tackle and while I'm familiar with other languages, I'll definitely use your video as a guideline.

  • @andrewshatnyy
    @andrewshatnyy 10 місяців тому +1

    Wow this is fantastic video. Thank you, Thu!

  • @_stition9777
    @_stition9777 10 місяців тому +1

    Thank you so much for making this video. Subscribed, this is exactly the content I look for

  • @muhannadobeidat
    @muhannadobeidat 10 місяців тому +2

    Thanks for the video. Nicely done and presented, educational with an interesting use case

  • @MarcelRiegler
    @MarcelRiegler 10 місяців тому

    Quick Info for Windows Users: The ollama tool works inside of WSL too, including GPU/CUDA support.

    • @eldino
      @eldino 10 місяців тому

      Can you call it from VSCode for Windows?

  • @LukeBarousse
    @LukeBarousse 10 місяців тому +13

    "Although, as you can see I can't retire anytime soon" 😂😳
    Thu, this was a pretty ingenious way to label data; one of the biggest part of our time is data cleanup and this helps speed it up

    • @LukeBarousse
      @LukeBarousse 10 місяців тому +3

      out of curiousity, why did you choose ollama? (vice something like LM studio)

    • @Thuvu5
      @Thuvu5  10 місяців тому +1

      Haha, yeah I thought I'd saved much more.. 😂 Definitely, I hope to explore more analysis use cases for local LLMs. I heard about LM studio but somehow I just like the setup with Ollama better. I guess they are very much the same in the backend.

    • @FaruqAtilola
      @FaruqAtilola 10 місяців тому +3

      Trust me, clicking the video and scrolling through the comments, I was anticipating your comment to be at the very top😅

  • @NRICHMEMotivation
    @NRICHMEMotivation 3 місяці тому +1

    I am blown away by this video! If only I can get my CPA to do the same. I guess I’ll need to learn to code.

  • @chrisumali9841
    @chrisumali9841 9 місяців тому

    Thanks for the demo and info. So detailed and analytics are great. Have a great day

  • @davidtindell950
    @davidtindell950 10 місяців тому +2

    I just read about the latest Meta LLAMA model that is supposed to be better than GPT4 for s/w dev!
    I hope that we can run it as a LOCAL LLM ! Thank You for this timely vid.
    ...

    • @Thuvu5
      @Thuvu5  10 місяців тому

      Ooh that’s pretty cool! 🤩 So great to hear many models are approaching GPT4 capabilities 🤯

  • @user-jk9zr3sc5h
    @user-jk9zr3sc5h 10 місяців тому

    @13:37 instead of rerunning the prompt, look into token biases instead. Have a set amount of categories, and increase the token bias for those specifically. Ollama may not support it, but exllamav2 etc does.

  • @atenciop123y
    @atenciop123y 9 місяців тому

    Thanks again for another wonderful video. Ollama is now available on Windows as a preview. I used that preview version on the solution you shared here and it worked great! 🙂
    Can you recommend a tutorial on the panel library? Thanks in advance.

  • @mrbarkan
    @mrbarkan 8 місяців тому +1

    This is incredible, a bit far fetched from my skills and time in hands. But surely inspiring!

  • @SuHwak
    @SuHwak 9 місяців тому +1

    This seems a very interesting video, but more than anything else, it demonstrates the utter garbage the (Dutch) banks use for naming companies in the transactions, and more often middle man transaction processors without much or wholly inconsistent reference to the company you made a transaction with. Take for example Albert Heijn:
    It could be AH, A H, AlbertH, Albert H, AlbertHeijn, Albert Heijn, AH2Go, ahtogo, etc etc, and even more inconsistent with the place names. Same for McDonalds, MD, McD, Mc Donalds.
    Then with the middle man in between for some stores, you'd have to really remember with only the date and amount as clues what was bought.
    Its maddening to get rule based categorization set up this way, and I don't think any LLM without going through even more (as you show) cleaning up of the data is going to solve this. The Dutch banks should include a KvK number (Chamber of Commerce) if the transaction was with any business. Then we can easily use the KvK API or build our own relationship table of KvK numbers with the company names.

  • @TheSabatuer
    @TheSabatuer 10 місяців тому +1

    FYI The multiplication example you tried wasn't accurate, the 2nd input number was different than the example you tried.
    49,792 x 857,294.2 = 42,632,383,271.8! 45 mil is still way off

  • @palakgoel5656
    @palakgoel5656 10 місяців тому +1

    Great video like always Thu! You never fail to fascinate me with your content as you make Data Science seem so fun to experiment with! Do you happen to have experience with the Bloomberg Terminal or any project idea to do using it? Would be amazing to know what you think of it! 🥰💛

    • @Thuvu5
      @Thuvu5  10 місяців тому

      Thank you for such kind words! No I haven’t had the chance to try out Bloomberg Terminal. It’s perhaps worth looking into for a future video 🤔

    • @palakgoel5656
      @palakgoel5656 10 місяців тому

      @@Thuvu5 excited and hoping to have a look at it 💫💕

  • @yezarniko9621
    @yezarniko9621 7 місяців тому +1

    That what I'm looking for !!! Thanks

  • @SteelWolf13
    @SteelWolf13 10 місяців тому

    Nice. Might give this a try over the weekend. Just need to figure out how to get my banks data.

  • @kcm624
    @kcm624 10 місяців тому

    Awesome video, learned a lot of new tools and want to try this out.
    For the dashboard, wonder if using Excel would be easier? Not sure.

  • @nimeshkumar8508
    @nimeshkumar8508 8 місяців тому +1

    Thankyou so much for this video. I relly like the explanation. Thanks

  • @dasurao7736
    @dasurao7736 10 місяців тому +1

    Your videos are well thought out .. Keep them coming - Dont want you "retiring soon" 🙂

    • @Thuvu5
      @Thuvu5  10 місяців тому

      Haha thank you for this! Don’t worry, with UA-cam I don’t want to retire anytime soon 😉🤗

  • @60pluscrazy
    @60pluscrazy 10 місяців тому +1

    Wow 🎉🎉🎉thanks 🎉🎉🎉

  • @hrgagan9192
    @hrgagan9192 10 місяців тому +1

    Wow absolutely wow, thank you for such a great project, so many ideas ringing in my head. Cheers

  • @heijd
    @heijd 10 місяців тому +2

    A faster and cheaper way to do this is to use the LLM embeddings directly. This is what happens anyway behind the scenes, but it makes the data nicer to handle.

    • @pieterjdw
      @pieterjdw 9 місяців тому

      Could you give some guidance to this approach?

  • @nguyentrananhnguyen7900
    @nguyentrananhnguyen7900 10 місяців тому

    ayo, i'm just doing my first step that's logging every expenses i got since the start of this year
    i'm just thinking about doing some sort of software that help me manage my expenses and savings
    and this is exactly what i think of
    thank you for the high quality video

  • @chocolatecookie8571
    @chocolatecookie8571 10 місяців тому +2

    I have a great admiration for the younger generations who know how to do all this tech stuff. It looks very complicated to me.

    • @Thuvu5
      @Thuvu5  9 місяців тому +1

      Haha, that’s so kind of you. I’m sure it’s less complicated than it looks

  • @TheBenJiles
    @TheBenJiles 10 місяців тому +1

    Thanks so much! It giving me inspiration for using this in a security analysis context.

  • @haqk4583
    @haqk4583 10 місяців тому +1

    Thanks for the great intro into how to get started with local LLMs. I'll give it a go after Tết 😄

    • @Thuvu5
      @Thuvu5  10 місяців тому

      Happy Tet holiday! 😀🎉

  • @batosato
    @batosato 3 місяці тому +1

    Did I just read Beta Boulders Amsterdam? I go to Beta Boulders Copenhagen. I believe they belong to the same company. Hello fellow climber!! Nice video though :)

    • @Thuvu5
      @Thuvu5  3 місяці тому

      Oh how cool! Great to hear you go climbing at Beta Boulders too 🙌

  • @lionelshaghlil1754
    @lionelshaghlil1754 8 місяців тому +1

    Thanks, That was inspiring indeed :)

  • @bengriffin6157
    @bengriffin6157 10 місяців тому +3

    Very well explained. Looking forward to you posting the github repo.

    • @Thuvu5
      @Thuvu5  10 місяців тому +2

      Thank you for watching! I've added the repo link in the description 🙌🏽

  • @RDraps
    @RDraps 3 місяці тому

    This video explains excellent how to use Llama 2 locally for your finances. But it doesn't recognise correctly all your spendings. I did even use the script with LLama 3.1 ( 8B ) but not only you need to patch your transactions linked to the correct categories ( which is missing in script, I added it ), also you need to regroup the categories ( like explained in this video ).
    I think it would work a lot better, if you could find a long list of shops ( also online ones ) with their categorie, so you can train llama with it, so it gives the correct categorie for each transaction. This list for f.e. USA, Mexico or Europe ( or per country )...
    Or you think it would work better with the llama 3.1 70 B ? the 405B is way to big for most of us

  • @bhavyajain3420
    @bhavyajain3420 10 місяців тому +1

    That's awesome. I would also use Llama to write the code for generating plotly charts/dashboards haha!

  • @EricSchroeder-cc4hf
    @EricSchroeder-cc4hf 8 місяців тому +1

    very good! thank you for sharing!

  • @gaelanmelanson3532
    @gaelanmelanson3532 5 місяців тому +1

    Such a cool project!

  • @lucasjenkinson
    @lucasjenkinson 8 днів тому

    This is a life-changing video

  • @agyeirichmondowusu9670
    @agyeirichmondowusu9670 4 місяці тому +1

    You earned a new subscriber today. Thanks for how intuitive this video is. I also love how you pronounce "O-lla_ma"😹..kidding

    • @Thuvu5
      @Thuvu5  4 місяці тому +1

      Haha, thank you for the subs! 🎉

  • @gmostafaali
    @gmostafaali 10 місяців тому +2

    Your content always useful! I like the Panel lots.

    • @Thuvu5
      @Thuvu5  10 місяців тому +1

      Thank you so much! So happy to hear 🤩

    • @gmostafaali
      @gmostafaali 10 місяців тому

      @@Thuvu5 💛

  • @IdeationGeek
    @IdeationGeek 10 місяців тому +1

    I see how this is useful for being one's own accountant :) Super!

  • @clamhammer2463
    @clamhammer2463 9 місяців тому

    This can also be done with a much smaller custom recurrent LSTM network that can maybe even run on a phone or browser, avoiding the 4-7gb LLM install. It's a great video, but not all problems are optimally solved with an LLM.

  • @haralc
    @haralc 10 місяців тому +201

    There's no language models that can do math. It can answer 2 + 2 = 4, because it has seen people talking about it, but it doesn't really do computation.

    • @Dom-zy1qy
      @Dom-zy1qy 10 місяців тому +1

      Can RAG not used to do simple calculations?

    • @joe_hoeller_chicago
      @joe_hoeller_chicago 10 місяців тому +28

      Actually no. It depends on which LLM, some like Orca2 are trained in math.

    • @gammalgris2497
      @gammalgris2497 10 місяців тому +8

      The LLM cannot but an artificial neural network can maybe help as its just a pile of linear algebra. But then you have to think about what you actually want to do. Do you want to find spending patterns? There are easier ways to do math.
      Finding categories is an arbitrary task. Check that the LLM doesnt' mix up your numbers/ spending numbers.

    • @GeekProdigyGuy
      @GeekProdigyGuy 10 місяців тому +12

      ​@@joe_hoeller_chicagoLLMs trained to do math are like dogs trained to do math. It might do mostly OK for a bit, but errors are a matter of when, not if.

    • @Tyrone-Ward
      @Tyrone-Ward 10 місяців тому +6

      ChatGPT said, "LLMs are quite capable of performing mathematical tasks, including arithmetic, algebra, calculus, and even some advanced mathematical concepts. They can solve equations, perform calculations, and provide explanations for mathematical principles". So you're wrong.

  • @AlexandreRousselet
    @AlexandreRousselet 10 місяців тому +2

    J'ai adoré, vidéo super clair allant droit au but et qui nous la joie d'aller découvrir le code

  • @TeaForecast
    @TeaForecast 10 місяців тому +1

    Very concise and informative video. I appreciate it.

  • @parmeshwarmathpati2916
    @parmeshwarmathpati2916 8 місяців тому

    you can assign temperature value to 0 to get unique results

  • @bhusanchettri8594
    @bhusanchettri8594 9 місяців тому

    Great insights and well explained!

  • @RicardoJuanito
    @RicardoJuanito 10 місяців тому

    The pricing numbers seem low, given what sounds the scale of the company.
    Maybe get a feel for how much his yearly expenses on Salesforce are, which your solution is partly replacing or enhancing. That should give an idea on the actual value your delivering for the company.