Build RAG pipeline with Llama 3.1
@meta released Llama 3.1 405B which is the first openly available model that rivals the top AI models when it comes to state-of-the-art capabilities in general knowledge, steerability, math, tool use, and multilingual translation.
In this video we will use a variant of Llama 3.1 8B model to create a RAG pipeline with @LlamaIndex and @GroqInc model inference. Refer this same collab notebook to create your pipeline with Llama 3.1 405B
Thank you for watching please like share and subscribe!!
0:00 Introduction
0:18 Meta releases Llama 3.1 405B
1:56 Installation
2:58 Import libraries
3:40 Adding Groq API key
4:17 Data ingestion and chunking
5:08 Defining embedding model and Llama 3.1 LLM
6:50 Creating Service context and Vector Store index
8:04 Persist indexe
9:05 Load index from disk
9:34 Define query engine
9:49 Finally querying the RAG pipeline
10:10 Conclusion
10:44 Like Share and subscribe
@Google Collab - https://colab.research.google.com/gis...
Llama 3.1 405B documentation - https://ai.meta.com/blog/meta-llama-3-1/
Groq - https://console.groq.com/docs/models
LlamaIndex - https://docs.llamaindex.ai/en/stable/