End To End Multi Language Invoice Extractor Project Using Google Gemini Pro Free LLM Model

[@fenixchow1]

Thank you Krish as alwasys, hats off for your contribution to data science community all over the world! from Texas, USA

[@jatinnandwani6678]

Thanks Krish!

[@sandipsalunkhe5025]

Thank you krish sir I was there working on this project for product based company

[@online_business_pokhara]

What's the hourly pay for remote freshers for developing LLM based model ?

[@theogman2761]

ModuleNotFoundError: No module named 'google.genrativeai' Any Solution for this error?

[@nizamuddinahmed5366]

@@theogman2761 pip install google-generativeai import google.generativeai as genai

[@Zaratch]

I will get to it tomorrow morning 🙌 someone do remind me at 11 am on 28/12/2023 🤝 thank you

[@Pubba_]

Bro!! Every new video of Krish makes me remember you😂

[@Zaratch]

@@Pubba_ 😂 I appreciate the reminder brother!!

[@sharadsisodiya3853]

thank you krish sir really you are doing great job i like your approach you are going with the tech of world

[@shantilalzanwar8687]

Sir, thanks for this. These end to end projects are helping a lot

[@rekhavs3779]

My question here is, does this kind of API's will it replace the traditional model building that data scientist do as part of their work. Because these kind of API's are more flexible enough we can restructure it based on the need & use case. Model training with right param is the super duper part in the lyf of data scientist (ML developer or whatever title we call). Say if that get replaced with these sort of Big LLM's for NLP and in future expecting more like this for CV. how can we see the job role (like day to day work) of data scientist in upcoming years. Because I was working for one of my client back in 2021 to extract info from resumes, where we struggled a lot to extract the semantics from those unstructed doc. now its easy-peasy just a one click do wonders. if this was present back then lot of research work gets reduced and development would have been completed in a week with just 3 engineers, where in we where 6 at that point of time. (Looking scary these reduces 50% of work force) & recent paytm layoff adds fuel to this fire as well. krish really need your thoughts here.

[@itskiash5631]

Thanks alot Krish Naik 🎉🎉🎉

[@ShehneelKhan-p3x]

Great Great stuff!

[@DataScienceAI-rf4kx]

Thank you for making the video best for me( automation enginner)

[@vanshkumar3445]

Great krish sir 😃

[@chandrachoodR]

Awesome Krish 🎉

[@pradipdutta7851]

Awesome Project Sir

[@Ikmal-ld7jo]

Thank you for the video, this really helps my project

[@gurjeet333]

Thanks for the amazing project. Can you also create a video of this project being deployed on AWS or any other cloud platforms

[@krishnaik06]

Sure

[@joeljoseph26]

@@krishnaik06 Thank you very much

[@IBM_-rx4gg]

Very good videos 👍 Sir can you make a video on creating LLM chatbot , which can process videos and answer questions related to videos. Similar to chat with pdf

[@manojbanoth5942]

Hi @krishnaik06 Can we fine-tune the Gemini-pro-vision model with our domain data for better results? If possible, please make a video on the same. Thank you

[@robinchriqui2407]

Same question, cannot find documentation about it yet

[@NiravShah-wc9xe]

looking for same answer. can we use Gemini-pro api to use with our domain data like pdf reader or chat with database?

[@solomonrajkumar5537]

Hello Krish Naik, hope you are doing well! I am always glad to see the way of your teaching people... my self and even my son is your fan follower... this is a great video... is it possible to automate this - like e.g. getting the image from the db one by one and categorize it (running this like a scheduler as and when the new image come into the db)... let me know if you need more clarity on my explanation - Thanks God Bless you!

[@abhikits]

Thank you for the great video, just a request to also add Vector Database integration with Gemini

[@happyhours.0214]

Hi Krish Sir, It's a great video. Please make a video on how to deploy these models.

[@sunilrskanda1588]

Hai Sir, please upload the video that is related to the Data Analyst/ Data Scientist Roadmap for 2024

[@robinchriqui2407]

Thank you, you are the best! Is there any way to fine tune gemini pro vision or not yet? Cannot find anything about it

[@KSB_2021]

I am getting this error when I upload Invoice Image. AxiosError: Request failed with status code 403

[@nehakothari9654]

Can we do same on colab, as on colab getting errors

[@sandipsalunkhe-p9l]

sir instead of question answering can we get the output in JSON format like {"Total Amount":"45000" , "Invoice No":"INV 123/2712/23-24"} I am working for this type of output. how it will possible help me to getting output like this format.

[@krishnaik06]

Change the prompt

[@sridevigogusetty8371]

With pydandantic it's possible

[@priyanshudhaked8728]

is it will work also for hand written text extraction from the image.

[@cyber_karthik]

Bro instead of fetching information in separate separate doc can we do for n number of docs?

[@anilchaudhry804]

will this work for CSV files? Leds say we want to derive some statistics from excel sheet

[@aryanyadav5137]

sir can you please bring a video on real time or static RAG based LLM application using LLM App

[@satanbaba9237]

Hi krish sir, Thanks a lot for the video. Would you be able to make a video about audio call analysis and insights extraction using LLM?

[@abhinayaphalphale9512]

The Gemini 1.0 Pro Vision model will be deprecated from Google AI services and tools as of June 12, 2024. Usage of the model in Vertex AI is not affected by this notice. What this means for you You’ll be able to use Gemini 1.0 Pro Vision until July 12, 2024. After July 12, saved prompts using Gemini 1.0 Pro Vision in Google AI Studio will switch to using Gemini 1.5 Flash. API calls that specify Gemini 1.0 Pro Vision will fail.

[@atharvavinashjoshi3482]

But that Gemini 1.5 Flash is only for the text ,right ?? What will be the other option for the gemini pro vision .can you help me??

[@nizamuddinahmed5366]

@@atharvavinashjoshi3482 it handles both text and images

[@AaronMartin-yx7wt]

Hello Krish, Is it possible to generate images with Gemini API? I have been searching but couldn't find any information about it. By the way, great content !

[@malleswararaomaguluri6344]

Thanks. Is there any generative ai models that works offline Krish sir?. If any please suggest.

[@swethakumari3263]

Hello, when I tried Gemini API using the python notebook, when making the API call, the call goes to localhost instead of generative API endpoint of Gemini. Anything I am doing incorrect?

[@swethakumari3263]

I am just trying the list_models API provided by Gemini, genai.list_models(): However I can see that it is trying to make a call to localhost instead of Google's generative AI endpoint.

[@swethakumari3263]

More details: InternalServerError: 500 GET localhost:35679/v1beta/models?pageSize=50&%24alt=json%3Benum-encoding%3Dint:

[@dineshkumarm-rz5yd]

do we require any premium purchased to carryout this project ??

[@rahulpatil2472]

Please create generative AI playlist, and add all GenAI project in that

[@srikkar]

Hi Mate, Thanks for your invaluable time to make these Videos and enabling us in a way to achieve more... Here I don't see the need for chromadb, which is usually used for embeddings. Sorry, if I missed something about. keen to see a video from you on embeddings using Gemini models/embedding-001 to use Chromadb or FAISS as vector store to get the answers using models/gemini-pro Thanks for your time and sharing the Knowledge.

[@Vir-se2kb]

Hi Kris. I have watched many of your GenAI videos. It's good, but it will be more helpful, if you can explain why you are writing the line of code. Now you are just watching your left screen & writing the same to the right screen, which will not help us in a long run.

[@namankumar2545]

Is this project for beginners in field of gan?!

[@nava5044]

Can you do stable diffusion XL paper and uscase

[@rishiraj2548]

💯🙏👍

[@arvindsinghrawat538]

did anyone faced ModuleNotFoundError: No module named 'google.generativeai' Please help

[@theogman2761]

same here, did you find the solution ?

[@malikmd1025]

Use python 3.10

[@arvindsinghrawat538]

@@malikmd1025 thank you 😄

[@kamalakantanayak3250]

Hii Krish ... Could you please make a video where we can generate a new image from multiple images using Gemini pro API???

[@chandanrao44]

Hi Krish, is there a way to do QA with JSON data using Gemini api please ?

[@tapasswinmanchala7249]

Hi Krish Sir can we have a video on meta Llama2 LLM Explanation in your style.

[@925_gulshanvarma_divb6]

Can we use this in node.js and javascript

[@sridevigogusetty8371]

Yes it's possible

[@shadabsheikh3859]

Hi Krish sir, thank you for this video. I want to know can we extract data from the table like in the given Invoice if I want to extract all items in the column in the Utpad Vivaran(product details) and the Rashi (price)? Also please make a video on training these LLMs on custom data (our use case specific)

[@sridevigogusetty8371]

Check out this to train on your custom data kzbin.info/www/bejne/gmaul56Am76mecksi=8ELs1J2tMHw1W6BC

[@NoDoglapan]

@krish Naik - please create a YT video on a chatbot to query custom data (pdf etc) using llama-index. thanks

[@SathwikBadikala]

Sir help us to build a project for flexible language translation using gemini api

[@DataPulse]

👍

[@izainonline]

API key free? for Gemini

[@krishnaik06]

yes free

[@naresh09022cm023]

please ping me API key link@@krishnaik06

[@shamanthshamanth5491]

api key is not working properly

[@srikanthm.d.v.n2422]

how to deploy this in heroku

[@angnat05]

anyone have error AxiosError: Request failed with status code 403 ?

[@ManujJoshi]

Who ask questions to invoice in industry???....🤣hahaha....I think invoice data to excel file is a time saving and useful use-case

[@jenny008]

Api is not working

[@arunr2265]

any discount coupon on ineuron courses :)

[@krishnaik06]

Visit the site :)

[@KumR]

OK

[@shwetashah7666]

Can we write the same code in Google colab notebook? I tried it but there is no output, nor is there any error! I tweaked the code a little bit: from google.colab import userdata import google.generativeai as genai genai.configure(api_key=userdata.get('GOOGLE_API_KEY')) where I have enabled the use of GOOGLE_API_KEY as the secret. Hope I am making sense :).