วีดีโอ

I forgot to add this, I also tried running open llms on colab with GPU but again the response time is horrible.

Hi sir, very deatiled explanation, how about the data privacy sir, if I use open AI? We are trying to build custom chatbot with open llms but as you said, the response is very pathetic. Does the performance improve if we run it on GPU instance ? Here the major concern is data privacy, so hesitant to use Azure open AI. May I know your suggestions on our usecase ? Thank you.

This is good, Joy. But, can we have something like ChatAll, or GodMode browser? ChatAll and Godmode have a little cluttered UI, and I cannot use live online models like ChatGPT, Claude 3.5, Gemini, etc. in conjunction with local offline ollama models, or models from llmstudio. Thanks!

you have not attached any link with it

does it handle large amount of data?? like more that 3L data

Super Great Explanation, and easy to Understandable Thank you lot !

Hello sir, can you share the codes?

Please provide pre-requisite installation otherwise as a beginner no one can recreate.

I've tried your code and I uploaded my own csv file however its only showing the dataframe whenever I ask any question. It doesnt compute or anything.

There is some background noise

Hey, great video, thanks to you I got it working. Is there a possibility to change the code, so that not the first modelfile is downloaded? I want to download Q4 Mistral for examble but the code gives Q2. I am pretty new to this, sorry if this is a silly question.

can you attach notebook?

Thank you sir , have you used open source LLMS such as Claude 3 , Llama 3 or Mistral ? what do you think of a fine tuned model ? some companies don't like closed source models (security ...)

Hi, I am getting error ModuleNotFoundError: No module named 'langchain.chat_models' please help

Thanks Joy. Once the vector DB is loaded with schema and if we have some sample questions and corresponding SQLs how can we add it to the vector DB for better results ? Also does the vector DB keeps updating itself with more interaction or how can we improve by manually adding more questions and SQLs?

does it work with image based pdf? and if doesn't how can i make one? please suggest

Thanks. This will help me !

Thank you, Joy. I am a new learner on RAG. Would you mind show us a demo on using module with OpenAI (not AzureChatOpenAI) and use MySQL (with full database tables provided)? I hope can follow with you to build up the chatbot step by step successfully. Thanks!

Hey Joy, Can you plz help how can we use input as book cover image and find similar book search with the same code , also provide the code for the same , dataset??

Can you plz provide the pdf of document that you used

Thank you so much, this explanation is great! This really help me a lot but, i'm stuck at adding my own gguf models to my project. Like when i'm trying to add it my code didn't detect it and downloaded the other version of the model id. Can i download the models manually from Hugging Face than downloading it from the script? Because the file i downloaded from the script, is not even a gguf file or any type of that.

Darun session

Thanks for the video, does this work for multiple documents as well with good accuracy?

*Promosm* 😓

Can we make this as conversational?

THIS IS amazing...

I see you have some good use cases. I've been working on similar projects. How about we have a little chat and exchange notes?

This was a very very veryyyyy interesting video. Please continue this

Hello I am having few queries how can I reach you out please help me

how to make api of model

Hello, thank you so much for this video. i have a question related of summarize questions in LLM documents. For example in vector database with thousands documents with date property, and i want ask the model how much document i received in the last week?

Hey, please add your contact email to TH-cam. I have a project you will be interested in.

Hey good video. I am trying to recreate this, created the .env all of that is situated, however when I run ui.py using streamlit, getting error AttributeError: module 'openai' has no attribute 'error'. Can you help??

I have two queries. It would be helpful if you can assist in that. 1. Template which you are using for prompt , in the first line you have provided f string. But however in the next lines you are not giving where you have {context}, {question}. So wouldn't that make it a string rather taking context and questions as variable? Or the model will understand that? 2. My second question is that I have tested the code. It is working for most part except Chat history. Even in the same session, it is not able to remember the previous questions. It is getting updated in the chat history though. But when u explicitly ask what is my previous question or ask like explain more on previous question, it is not taking the chat history rather giving halucinated questions or says it doesnt know previous question. Kindly clarify on the above two questions

Thank you sir for this informative video

Sir, thanks for the video, I just want to ask from where I could learn all these libraries and their use.

thx the video! sorry my question but im a beginner in this code. What files I see github I tried to run on Codespace with no success. Is there any other file, enviroment info I should have to try and run your RAG app? Could you pls help me regarding this as a beginner?

hey this is really useful.can you explain how to extract text from pdfs for indic langugaes.these like to extract hindi languages we are not able to extract with regular pypdf or ocr techniques.kindly help with some codes.

'promosm'

Sir can you please upload the same video for open source LLM Model- MPT 7B

Please, Upload the same video for LLM Model - MPT 7B.

Sir, what type of computer do you recommend for running local GPT’s? I have PrivateGPT, but it’s painfully slow on replies.

Great job bro I was assigned this task and I was struggling a lot but your tutorial helped me a lot

Great one! Can you make a tutorial on, how can we finetune our custom dataset locally and use that finetuned model for getting domain-specific results locally?

Guru Bhalo Likhechish, I hope you know who I am. Don't disclose 😜. Ami Finally toke subscribe korlam. Keep going.

github link is not working

Why not share google colab link itself, as Github link is giving 404

Wonderful!!!

Can you please redo the Github link?

This is awesome! 👍