9-End To End Powerful Document Q&A Chatbot using Llama3,Langchain and Groq API

In this video we will create an end to end powerful Document Q&A Chatbot ussinf Llama3, Langchain and Groq
Code Github: github.com/krishnaik06/Update...
-----------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
/ @krishnaik06
-----------------------------------------------------------------------------------
Fresh Langchain Playlist: • Fresh And Updated Lang...
►LLM Fine Tuning Playlist: • Steps By Step Tutorial...
►AWS Bedrock Playlist: • Generative AI In AWS-A...
►Llamindex Playlist: • Announcing LlamaIndex ...
►Google Gemini Playlist: • Google Is On Another L...
►Langchain Playlist: • Amazing Langchain Seri...
►Data Science Projects:
• Now you Can Crack Any ...
►Learn In One Tutorials
Statistics in 6 hours: • Complete Statistics Fo...
End To End RAG LLM APP Using LlamaIndex And OpenAI- Indexing And Querying Multiple Pdf's
Machine Learning In 6 Hours: • Complete Machine Learn...
Deep Learning 5 hours : • Deep Learning Indepth ...
►Learn In a Week Playlist
Statistics: • Live Day 1- Introducti...
Machine Learning : • Announcing 7 Days Live...
Deep Learning: • 5 Days Live Deep Learn...
NLP : • Announcing NLP Live co...
---------------------------------------------------------------------------------------------------
My Recording Gear
Laptop: amzn.to/4886inY
Office Desk : amzn.to/48nAWcO
Camera: amzn.to/3vcEIHS
Writing Pad:amzn.to/3OuXq41
Monitor: amzn.to/3vcEIHS
Audio Accessories: amzn.to/48nbgxD
Audio Mic: amzn.to/48nbgxD

[@ricardolourencosilva1741]

Like your teaching style. Straight to the point and very clear. Thanks.

[@prasannakarthik7721]

Your videos are fantastic and very educational! Glad to support you in every way I can!

[@jayantisingh1534]

Thanks Krish for educating us in such a structured way

[@SahilSharma-xw8ud]

commented and liked only because you asked (and we want more of this!). Good work Krish!

[@rblessr]

Dear Kris, You are amazing and your sessions are very good. Thanks for all the pains you take for such resourceful teaching. Keep up the good work and May God Bless you.

[@rachitsingh3299]

is the code working?

[@zishankhan2763]

hey Krish you are awsome, the method to explain concepts you come up with is amazing.

[@achrajpachauri3494]

Thanks sir god bless you. Please keep on making those videos. They are really informative

[@kavintriplek]

Hi Krish, your videos are Very Helpful.

[@SonaliBhanudasMali]

Nice tutorial 🎉 Plz make more video tutorials for genai projects using llama3

[@bhaveshkipathshala]

Dear Krish Naik, You are making a very amazing informative video (especially an end-to-end project) with a very simple and easy-to-understand explanation. Thanks for all the videos; it's really very easy for developers and learners to implement in their own use cases. God bless you.

[@rachitsingh3299]

is the code working?

[@lionelshaghlil1754]

Thanks Krish, you deserve a million like 👍👍👍

[@lalaniwerake881]

like your content. I am learning a lot from you. Thanks!

[@yogeshupadhyay6612]

Hello Krish I am pleased with your work as you are doing for the community. If you can make a video to use LLM to get data from the database SQL/no SQL

[@anilrajejadhav9994]

hey Krish Thankss Bhai,,..

[@sagarmhaisne110]

your videos helps me in my genAI projects.. thanks kkrish..

[@BelhsanMohamed]

great work as always thanks for all the information !!!

[@syedhussain6358]

Awesome session.

[@Abhi_interiors]

Thanks for this Krish

[@kingkaurav]

Thank you for this wonderful video

[@robinchriqui2407]

Thank you for your video! Are you planning to create a video about fine tuning of a multimodal open source model?

[@rajamailtome]

Nice video.. would be helpful if we design application to retrieve records from SQL database with natural language using open-source LLM like Llama

[@bhaumiks.6543]

Amazing work Krish

[@kanishkasharma353]

paused this gem of a vdo because u asked to like and comment.

[@shubhambhardwaj8894]

Nice video sir👍

[@pankajkcodes]

Good Series Love this series

[@debanjanbanerjee9731]

Thanks Krish

[@klf-israelitaxlawfirm184]

Thanks for all the great content

[@shahrukhahmad4127]

Krish sir its a request from my side, please please upload videos in order and mention serial number as well in every video,.Also put the video in respective playlist. I started my data science journey with your videos, I got job because of your clear explanation, I genuinely thank you. But now a days your channel seemss very confusing because you're uploading random videos of generative AI topic, its already tough for us, explain in clear and serialised way so that we all can learn through it.. This particular video again has no serial number, now it is creating confusion when to watch it. Specially for the ones who watches late due to office timings.

[@hashimmuhmmadnadeem8199]

Best GenAI teacher!

[@sabghat90]

Thank you

[@seththunder2077]

Krish can you please show us how to save chat in a DB as well like mysql where we save the Q, A, time, and date? That would be very helpful

[@amritsubramanian8384]

gr8 video

[@VigneshNani-wz5ol]

Please make complete LLM tutorial

[@souradipmanna]

Insightful thanks

[@lionelshaghlil1754]

I have a question regarding the embedding, we agreed long time ago as per your instructions that the embedding should be implemented using the same as the the LLM used for prompting. will it be a problem here that we used in this video openAI embedding with Lama3 prompting?

[@robbadhorn9259]

Hi. @Krish, Awesome videos. Is this running completely off line or is there some on line API Usage you are using. and is that paid? I like the response times. Also if OFF line are you using GPU's or just CPU?

[@velugucharan8096]

Try implement one end to end project using Gemini medical llm

[@aryanirani9326]

could you do a video for using multiple pdfs and csv tables as base data for the llm? and how such a model could be deployed for intra dept purposes

[@AnmolSingh-dz6tj]

Amazing!

[@shankar9063]

Should we create embedding for new data every time before query. If so how does graq inference helpful?

[@RakeshChoudhary-lp5xg]

hello sir im a student and just passed 12 and wanted a favour to make a video for students who just want to get into the data science field and what they should take care of and prepare well i have watched your roadmap video too and wanted this favour too from you .. Hope you doing well

[@ssen081]

Hi Krish - Please make some videos on LLM model evaluation. One ardent request

[@not_amanullah]

thanks ❤

[@animalbyte453]

How the app will handle the requests,if multiple users working parallelyy,eg: If A is asking question related to politics,if B is asking the questions related to sports parallelly, how the app handles this situation:) Your suggestions would be helpfull

[@nagalakshminimmagadda3743]

Is it possible to search with image and extract response from the document using GenAI?

[@KumR]

Loved this.. But can we pass in a PDF to streamlit instead of picking all files in folder ? Also is GroQ like hugging face?

[@thegroomingguide0824]

Can we use this same approach with csv files instead if pdfs ?

[@jeeshanansari615]

Sir, Please create a playlist a Data science interview Questions updated. It's been too long to create a interview Questions video...

[@patila-ov6ks]

Hello Krish! Could you please make a video on deploying GEMINI-PRO-VISION app as API using fastAPI.

[@subhamdutta516]

Hii Krish Sir, As you are my sole mentor i am urging you to give some idea about Phi-3 by Microsoft (SLM-small language model). I am working on Document QnA for Banks. So will it work?

[@__john663]

Hey krish bro, Is the groq completely free or there is any subscription or hidden charges?

[@shalabhchaturvedi6290]

Gold

[@qzwwzt]

Another issue: let's supose the App is used by several users, or companies. How can I charge each user who is consuming different values ​​from the key? Or will each user have their own apiKey?

[@vivekjeeva6653]

Is there any open source model to write unit tests?

[@yashsonune4391]

Hello Krish, can you fix your previous video 8 in the langchain playlist, it is frozen after 12.00.

[@foysalmamun5106]

559 half done

[@__john663]

Hi krish anna Can make a video using llama3 8b model with llama-index and chat engine because I need the ai is capable to document retrieval and general interactions. Is this capable to do

[@shankar9063]

Can we use llamaEmbedding instead OPENAIEMBEDDING? OPENAI charges to generate embedding rigth?

[@ravenx4453]

U got it ??? Can we use the llamaembding

[@praveenkumar-mca21]

i working on excel dataset how can i do this using same way please suggest me approach.

[@rakeshkumarrout2629]

Hey this is really impressive.how can I get some good greetings response from the rag bot ? Like "hi my name is [company name] and I am your assistant.kindly guide?

[@RishiRajxtrim]

🙂👍🙏

[@kapilaminbhavi1440]

can you do this for a csv file as well please

[@aviratsharma771]

keep getting this error "ValueError: Error raised by inference API HTTP code: 404, {"error":"model 'llama2' not found, try pulling it first") " i have checked api key from groq but its not working. Need HELP!!

[@user-my8yh3nr4l]

Your code only matches the headlines of the passage and retrieves answers from the heading questions. Have you tried it with questions inside the passage? It will not work well, as you showed in the video.

[@naysemuala8038]

Hi Krish i keep getting the following error after clicking the "Documents Embedding" button. AttributeError: module 'streamlit' has no attribute 'session_state_embeddings' Traceback: File "C:\Users\HP\anaconda3\Lib\site-packages\streamlit untime\scriptrunner\script_runner.py", line 542, in _run_script exec(code, module.__dict__) File "C:\Users\HP\Desktop\myapp-New\RAG-\app.py", line 48, in vector_embedding() File "C:\Users\HP\Desktop\myapp-New\RAG-\app.py", line 43, in vector_embedding st.session_state.vectors=FAISS.from_documents(st.session_state.final_documents,st.session_state_embeddings) How do i resolve it?

[@qzwwzt]

Great vão, but I looking for a solution completely free. I didn't get why you had tô call openAI. Could someone explain it please?

[@anuragsingh-tp6sm]

first 🥇

[@yashinfinite8338]

Can somebody explain me why krish defined second prompt

[@krishnaik06]

For the search input

[@yashinfinite8338]

@@krishnaik06 oh thank you Krish ! The master himself!

[@shikharsrivastava2645]

Cbfr

[@shankar9063]

index = faiss.IndexFlatL2(len(embeddings[0])) IndexError: list index out of range Anyone help on this issue?

[@mritunjayraj8505]

same issue, have you got any solution

[@Manoharpalanisamy977]

Got error index = faiss.IndexFlatL2(len(embeddings[0])) ~~~~~~~~~~^^^ IndexError: list index out of range try to solve it please. even I have used one pdf in the directory

[@mritunjayraj8505]

any solutions you got?

[@priyanka9672]

Is anyone facing ValueError: Error raised by inference endpoint: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/embeddings (Caused by NewConnectionError(': Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it')) issue, if yes please provide solution

[@patila-ov6ks]

Hello Krish! Could you please make a video on deploying GEMINI-PRO-VISION app as API using fastAPI.

[@patila-ov6ks]

Hello Krish! Could you please make a video on deploying GEMINI-PRO-VISION app as API using fastAPI.

[@patila-ov6ks]

Hello Krish! Could you please make a video on deploying GEMINI-PRO-VISION app as API using fastAPI.

[@patila-ov6ks]

Hello Krish! Could you please make a video on deploying GEMINI-PRO-VISION app as API using fastAPI.