Build Your Own RAG Using Unstructured, Llama3 via Groq, Qdrant & LangChain

Опубликовано: 19 Август 2026
на канале: Data Science Basics

15,046

253

In this 5th video in the unstructured playlist, I will explain you how to create your own Retrieval Augmented Generation (RAG) bot using the following tech stack.
LangChain as framework
UnstructuredIO for data prep
Fastembed for embedding
Qdrant Cloud as vectorstore
Llama3 via GroqInc

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 ⛓️‍💥
https://unstructured.io/

Code 👨🏻‍💻
https://github.com/sudarshan-koirala/...

------------------------------------------------------------------------------------------
Timestamps ⏰
00:00 Introduction
02:33 Setup
04:58 Preprocess PDF
10:42 Preprocess Markdown (Readme)
14:08 Load the document into the VectorDB
17:27 Now the RAG part
22:24 Qdrant Cloud and LangSmith
25:19 Conclusion

------------------------------------------------------------------------------------------

☕ Buy me a Coffee: https://ko-fi.com/datasciencebasics
✌️Patreon:   / datasciencebasics

------------------------------------------------------------------------------------------
🤝 Connect with me:
📺 Youtube:    / @datasciencebasics
👔 LinkedIn:   / sudarshan-koirala
🐦 Twitter:   / mesudarshan
🔉Medium:   / sudarshan-koirala
💼 Consulting: https://topmate.io/sudarshan_koirala

#unstructureddata ##unstructuredio #rag #langchain #llm #datasciencebasics