Agentic RAG: Build Your First Agentic RAG Using Qdrant and Phidata
Curious about the difference between traditional RAG and Agentic RAG?
🔹 Traditional RAG: Uses simple search and prompt stuffing — great for straightforward tasks but struggles with complex queries 😕
🔹 Agentic RAG: Gives the agent a tool to search for information independently, exactly when it needs it! 🚀
In this video, we’ll break down why Agentic RAG is the next step for more nuanced, powerful information retrieval. Learn how to implement it step-by-step using Qdrant and Phidata using Llama 3 via Ollama!
Links ⛓️💥
https://ollama.com/
https://qdrant.tech/documentation/qui...
https://www.docker.com/get-started/
https://docs.phidata.com/introduction
https://blog.gopenai.com/how-to-build...
https://github.com/phidatahq/phidata/...
TimeStamps ⏰
00:00 Introduction
00:14 Understanding Traditional RAG
01:15 Indexing and Querying with RAG
02:31 Setting Up the Development Environment
03:39 Exploring Traditional vs Agentic RAG via Notebook
04:01 Working with Qdrant
06:55 Creating and Managing Vector Databases
13:00 Building and Running Agents
14:21 Advanced Agent Configuration and Usage
20:06 Understanding Tool Responses
22:19 Complex Questions and Decomposition
29:58 Using the UI for Better Interaction
36:15 Final Thoughts and 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
#agenticrag #agents #phidata #ollama #llama3 #datasciencebasics