🗣️Private Chat with Docs in 30 lines of Code | Local RAGs using Ollama and AGNO

In this video, we are going to implement a fully functional RAG (Retrieval Augmented Generation) using our Local LLMs on Ollama. The system that makes this possible is Agno.

Agno (formerly Phidata) is an open-source platform designed to help you build, deploy, and monitor high-performance AI agents with memory, knowledge, and tools.

Let’s walk through the video, step by step and set this up on our local system.

#AI, #LLM, #Agno, #AIAgents, #MachineLearning, #Automation, #ArtificialIntelligence, #DeepLearning, #FutureTech, #OpenSource, #AIInnovation, #Tech

Links:
Introduction post: https://www.agno.com/blog/introducing-agno
Website: https://www.agno.com
Docs: https://docs.agno.com/introduction
Ollama models: https://ollama.com/search
Github Codes: https://github.com/PromptEngineer48/Agno\_Codes\_RAG

------------------------------------------------
Learn More:
Try Out Gloud GPUs on Novita AI (Affiliate Link): https://fas.st/t/EvuzAkeX
-------------------------------------------------

CHANNEL LINKS:
🕵️‍♀️ Join my Patreon for keeping up with the updates: https://www.patreon.com/PromptEngineer975
☕ Buy me a coffee: https://ko-fi.com/promptengineer
📞 Get on a Call with me at $50 Calendly: https://calendly.com/prompt-engineer48/call
💀 GitHub Profile: https://github.com/PromptEngineer48
🔖 Twitter Profile: https://twitter.com/prompt48

Timeline:
0:00 Intro
0:30 Focus Local
0:48 Install Ollama
3:48 Agno Intro
4:30 VS Code Editor
4:47 uv package
5:25 Easy Environment
6:06 uv Installations
7:40 RAG Agent Code
13:32 Run Code
16:28 Web Interface Code
18:17 Run Code
19:00 Web Interface
19:43 Conclusion