Building Multimodal AI RAG with LlamaIndex, NVIDIA NIM, and Milvus | LLM App Development

This video explains how to create a multimodal AI retrieval-augmented generation (RAG) application, including the following steps:
1. Document processing: Convert documents into text form using vision language models, specifically NeVA 22B for general image understanding and DePlot for charts and plots.
2. Vector database: Explore the power of GPU-accelerated Milvus for efficient storage and retrieval of your embeddings.
3. Inference with Llama 3: Leverage the NVIDIA NIM API Llama 3 model to handle user queries and generate accurate responses.
4. Orchestration with LlamaIndex: Integrate and manage all components seamlessly with LlamaIndex for a smooth Q&A experience.
📗 Learn more with this notebook: github.com/NVI...
Join the NVIDIA Developer Program: nvda.ws/3OhiXfl
Read and subscribe to the NVIDIA Technical Blog: nvda.ws/3XHae9F
#llm #llms #llama3 #llamaindex #nvidiaai #nvidianim #langchain #milvus
NVIDIA NIM, code review, LangChain, llamaIndex, Llama 3, Milvus, NIM APIs, Mixtral, NeVA/DePlot

[@gnanaprakash-ravi]

Very informative. Thanks, Jay Rodge!!

[@KevalShah-s7l]

I am not able to access / view the linked notebook. Can you share the code / github link?

[@dertrojanischeesel4441]

Great Content, thanks for sharing. How did you create your drawings?

[@FredyGonzales]

Excelente, muchas gracias.

[@AhmadAbuznaid91]

What is the environment used here, GPU requirements ?

[@robrever]

Can this be done locally?

[@ephemeral.3817]

what are requirements to install?

[@dangelgeek]

Awesome!

[@progressivenetwork3584]

Super cool

[@samarbid13]

9:08 Bro! rotate your keys ...

[@__________________________6910]

lol

[@CanalianInc]

Have any of you actually used your own documents they are abysmal you lack of uptake for act an ai can directly attributed to this. images for blueprints that can’t be read, one page where the plum print is totally different to the other old outdated docs. Developer advocate stop making videos and fix you docs.

[@NVIDIADeveloper]

Could you send us the specifics? Which docs are you referring to? Best to email: [e-mail]
Thank you!

[@kareemyoussef2304]

@@NVIDIADeveloper nah fk u , the guys right

[@BlauGhost]

No module named 'llama_index.llms.nvidia'.... this is wild even the docs on the website are all missleading or have you download outdated packages