Getting Started With Nvidia NIM-Building RAG Document Q&A With Nvidia NIM And Langchain

Explore the latest community-built AI models with an API optimized and accelerated by NVIDIA, then deploy anywhere with NVIDIA NIM inference microservices.
-------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
-----------------------------------------------------------------------------------

►Data Science Projects:

►Learn In One Tutorials

End To End RAG LLM APP Using LlamaIndex And OpenAI- Indexing And Querying Multiple Pdf's

►Learn In a Week Playlist

---------------------------------------------------------------------------------------------------
My Recording Gear

[krishnaik]

Check out my udemy course on Machine learning and NLP with end to end projects

[IdPreferNot]

Such an excellent video with 3 awesome components. A very tight Langchain RAG implementation, on Streamlit, highlighting the capabilities of Nvidia's NIM inference.

Thank you for sharing!

[kumargaurav]

How is it different from Groq api inference service where LPUs are way faster than GPUs for inferencing. NIM is more like hosting hf models inside NVIDIA ecosystem with inferencing facility alongwith.But as groq has also got pretty good models, just for inferencing using groq api will be much wiser option for speed for same kind of models.

[syedfarhanahmed]

Krish Sir thank you for all the RAG videos you shared. I added one feature into this application of Roman Hindi, where user can ask in Hindi and get response in Hindi too..

[victorakakpo]

I love you Krish. I always pick my phone to see if you have posted something new

[yvonne]

Thank you for the nice overview..I somehow keep getting 400 error with respect to inference, any heads up how i could sort it out ?

[rahulpatil]

Try to create RAG deployment using GenerativeAIExamples repo with nvidia nim container for llm inference

[davh]

how do we ensure that the digital humans or nims are accountable and striving for higher nps?

[uniqueavi]

Hello sir, instead of Streamlit application all the time, can you do sometimes where we can just run locally through terminal?

[dimpleagrawal]

It's a request that please do add the version if libraries used in the requirements.txt document for the ease in running the application

[_satyamrai]

Sir, in this your are first creating an OpenAI object 'client' and then using Llama3 model from it. How?

[rcky]

does the udemy course offer anything else from his previous playlists?I mean why should i choose the course over the free playlist apart from the certification??anyone?

[anandasekhar]

Does your laptop have GPU's . How did you ensure that the code runs on GPU's and not CPU's

[Compact]

Sir when we create an embedding so obviously it stores in local directory so could you please tell, if we deploy this application so where should we save this embedding if we use nomic embedding and chroma

[JebliMohamed]

Have you compared the inference speed of GROQ CLOUD with Nvidia Nim?

[amitbandyopadhyay]

I am getting "ModuleNotFoundError: No module named What am i missing?

[sergeistadnik]

I cheer for 1M subscribers for your channel !

[bodhisattadas]

Hi, Krish, Can we use this to extract information from the pdf? Like invoice number, invoice dates or the description which contains table?

[khadarvali]

Chainlit authentication pe ek video karo sir

[pradhyumnasg]

Sir can u tell us about Lighting AI plz