Explore multimodal Retrieval-Augmented Generation (RAG) with this comprehensive video.
Learn how to build an end-to-end RAG pipeline that handles text, images, graphs, tables, and audio data using Weaviate as a vector database.
This video covers everything from data collection to system testing, with a focus on ESG and Finance applications. Perfect for AI engineers, data scientists, and machine learning enthusiasts looking to expand their skills in building versatile and powerful RAG systems.
ℹ️ CHAPTERS OF THE VIDEO
0:00 - Introduction
0:53 - Overview of Multimodal RAG
5:50 - Text, Images, Tables, and Audio Data Collection & Preprocessing
41:34 - Set Up Weaviate
49:40 - Data Ingestion into Weaviate
54:21 - Implementing the Retriever Component
58:47 - Building the Augmented Generation Component
01:03:41 - Testing and Optimizing the RAG System
01:09:42 - Clean Workspace
01:09:54 - Conclusion and Next Steps
Code: https://github.com/keitazoumana/multimodal-rag-esg
Connect:
- Medium: https://zoumanakeita.medium.com/
- LinkedIn: https://www.linkedin.com/in/zoumana-keita/
- Twitter: https://twitter.com/zoumana_keita_
- TikTok: https://www.tiktok.com/@zoumdatascience
- Email me: [email protected]
🎙️ Support me: https://www.buymeacoffee.com/zoumanakeig
#artificialintelligence #gpt4 #openai #largelanguagemodels