End To End Document Q&A RAG App With Gemma And Groq API

Gemma is a family of lightweight, open models built from the research and technology that Google used to create the Gemini models.In this video we will create an end to end Document Q&A RAG App wwith Google Gemma And GRoq API
Code Github: github.com/kri...
----------------------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
/ @krishnaik06
-----------------------------------------------------------------------------------
►GenAI on AWS Cloud 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

[@ssen081]

Thanks for the informative video. And again reiterating my request- Please upload videos on LLM evaluation. It’s badly needed.

[@yashksaini]

00:03 Creating an end-to-end document Q&A chatbot using Google open source model Gemma and Groq API
02:09 Grock Cloud provides fast and efficient inferencing with its language processing unit (LPU).
06:18 Creating an API key and setting up environment variables
08:38 How to create a Google API key
13:22 Using libraries for document Q&A and embedding techniques
15:52 Importing Environment Variables and Using API Keys
20:22 Applying Google generative Ai embeddings for vector store DB
22:29 Setting up data injection and text splitting process
26:59 Setting up Vector State variable and Vector DB for efficient document retrieval.
28:54 Creating Retriever Dochain and invoking function for response retrieval and context display in StreamLab

[@achrajpachauri3494]

Thank you sir!! In the end we are doing similarity search in which llm first take context of input and give some more result related to those input context.

[@Rahul_Singh_Rajput_04]

can we use any another approach

[@harshgurawaliya-yu7li]

APPRECIATE YOUR HARDWORK BRO !!!

[@anshulesh]

Thank you Krish!! This is really helpful for my project.
Couple of questions :
1. My data is in Google drive or 0ne drive or other cloud storage. How I can load this document or create pipelines to load data from my google drive.
2. What make change in the code for get top 3 k=3 similarity search results.

[@aneeshamanke5191]

Thankyou for all your efforts Sir,
Your videos did help us a lot!

[@macmohan9556]

This was really good Krish

[@ayushmishra5861]

Sir, how about adding a memory or follow-up feature in one of any RAG videos. That'd be really helpfull.

[@muhammedyaseenkm9292]

You can use pinecone, llm buff memmory

[@shalabhchaturvedi6290]

Love you Krish. Respect!

[@dordekodzic6279]

Thanks Krish for all the value you share with us! For the end-to-end projects, could you also include various alternatives of deploying the AI solutions to (Azure, Google Cloud, AWS...)?

[@mohsenghafari7652]

thank you krish. please use model llama3 and show we how use it as llm for Q&A and RAG

[@DAvgGamer98]

I really appreciate your efforts and excellent content. Thank you 😊

[@SagnikSarkar96]

Great video!Really really helpful. Can you please modify this code to add a conversational feature so that we can ask follow-up questions?

[@vivek7654321]

Thanks Krishna, for the amazing video, appreciate on your smart work. I have one doubt, did you miss to pass context in the prompt, saw you passed the question only, or is it optional? 29:13

[@globea2z]

very nice u r a instutution Thanks for good work

[@SwaminathanSekar-ks9vb]

Great session indeed. But still curious to know one thing. you have created "venv" conda environment, in which you have created necessary libraries. But 12:10 timeframe, when you tried acessing cmd, it was showing different environment, (development). How could this possible?.

[@koushalreddy8452]

Thank you boss you are amazing

[@satyajitmohanty5039]

Precise 💯

[@ashishkumarbajpai]

Krish I really appreciate your videos. Can you please create a video on multimodal model creation.

[@jallaaswini9253]

Hello Krish, Can you make video on how to deal with structured format of data like excel using aws knowledge base and LLM models

[@shubhambhardwaj8894]

Thank you sir 😊

[@nemesis2477]

Hello Sir, I wanted to learn how do we deploy such a model. Since while deploying it we cannot use ollama embeddings simce they are om our local server. How do we install and pull ollama models like llama or "nomdic embeddings" before apps like strealit run the code. So they dont run into an error.

[@ELITEWEB_ai]

hi ,the document provided by you is working but not my personal document and i need to add memory how can i add to it

[@sarangakumarapeli4348]

Will Groq use the data that we are passing to LLMs for train models?

[@__john663]

How to use llama3 model in production, In local we have downloaded llama3 8b model. In live how to deploy the model. Please teach me bro❤

[@09_amitkumargupta16]

Use sagemaker notebook and use deploy method to deploy.

[@yashwankhede-c8e]

what are your views about igpt

[@muhammedyaseenkm9292]

When i loading pdf, is it possible to load table, image, or is it get all the elements. I think It can only accept text element.

[@muhammedyaseenkm9292]

Krish i always seeking this question to get most accurate solution. Rather than getting a dummy code that available in model reference published

[@revanthbhuvanagiri9177]

I'm not sure, but in the case of tabular data we can use LlamaIndex instead of Langchain, LlamaIndex is good option for tabular type of data to build RAG.

[@jyoti-bs1bm]

can anyone help me with the error
"Error during the retrieval process: Connection error."
I got this error while implementing this project.

[@foysalmamun5106]

Thank you

[@devloper.hs14]

Can we load any pdf and get our output?

[@priyank1149]

Make a LLM Evaluation on this RAG using this groq model

[@SwaminathanSekar-ks9vb]

Krish Naik sir, I got APIConnectionError: connection error

[@alpha7s708]

Same

[@RishiRajxtrim]

👍

[@ShaikKarishma-c8q]

ImportError: cannot import name 'LangSmithParams' from 'langchain_core.language_models.chat_models'
I am getting. this error after running streamline
Hope you guys can help me with this

[@sanskruteaaa]

i had an error with the interpreter
make sure your interpreter is set as venv