Multi-modal in LlamaIndex : Get Structured Responses from Images using GPT-4o

In this video, we will cover how to interact with images and get structured output using multi-modal functionality along with GPT-4o model in LlamaIndex.

This video is part of full fledged LlamaIndex course published on Udemy.
Please check below link to go through the LlamaIndex tutorial from scratch:
*********************************************************************
https://www.udemy.com/course/query-your-custom-documents-using-llamaindex/?referralCode=FF8DF567E075045AB128

Chapters :
***********************************************
0:00 Overview of Multi-Modality
1:40 Code : Integrate multi-modality in LlamaIndex
6: 03 Define Pydantic class for Structured output
6:14 Get the internal Prompt detail passed to LLM to get structured response
9:01 How to refine Structured output for Image ?

Please refer the code here :
*********************************************************************
https://github.com/PraveenKS30/GenerativeAI/tree/main/llamaindex/multimodal

Please check other videos on Generative AI :
************************************************
https://www.youtube.com/playlist?list=PLO66QfE8gWT3L3SCxIhXxVnKY8153kZJB

Looking for interview guide on Kafka ?
************************************************
If you are planning for interview on real time process and looking for tech questions on Kafka and Spring Kafka, look no further and grab your copy of "75 Interview Questions on Kafka and Spring Kafka".

Available here : https://techytacos.gumroad.com/l/weqdh

Видео Multi-modal in LlamaIndex : Get Structured Responses from Images using GPT-4o канала TechyTacos