In this 3rd video in the unstructured playlist, I will explain you how to extract image and image data from PDF and use LlaVa model via Ollama to explain the image.
80% of enterprise data exists in difficult-to-use formats like HTML, PDF, CSV, PNG, PPTX, and more. Unstructured effortlessly extracts and transforms complex data for use with every major vector database and LLM framework.
Link ⛓️💥
unstructured.io/
Code 👨🏻💻
github.com/sudarshan-koirala/...
------------------------------------------------------------------------------------------
Timestamps ⏰
00:00 Introduction
02:25 Setup
05:05 Image Info Extraction
11:04 Image + Image Info Extraction
14:44 Multimodal ( Explain Image with Llava via Ollama and LangChain )
20:11 Conclusion
------------------------------------------------------------------------------------------
☕ Buy me a Coffee: ko-fi.com/datasciencebasics
✌️Patreon: / datasciencebasics
------------------------------------------------------------------------------------------
🤝 Connect with me:
📺 RU-vid: / @datasciencebasics
👔 LinkedIn: / sudarshan-koirala
🐦 Twitter: / mesudarshan
🔉Medium: / sudarshan-koirala
💼 Consulting: topmate.io/sudarshan_koirala
#unstructureddata #langchain #llava #ollama #unstructuredio #llm #datasciencebasics
7 авг 2024