Sarah Connor?
summary
A live demo showing how to run local LLMs using Ollama on a Raspberry Pi 5 (8GB) with Go examples. It covers Ollama basics, using small "baby" LLMs with LangChainGo, setup and querying, streaming responses, building complex prompts and multi-turn conversation, and running WebAssembly plugins from the model.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 4:46Sarah Connor inspiration
- 10:48Code and base operation
- 22:15Memory improvement and bot customization
- 27:58RAG introduction and optimization
- 34:26RAG in action demo
- 38:18Final demo and interaction
- 40:47Conclusion
related talks
45mEverything You Need to Know About Running LLMs Locally
49mTame your Llama, run AI in Java
40mOpen Source LLMs in the Cloud: Scalable Solutions
43mRunning open large language models in production with Ollama and serverless GPUs
47mOwn Your LLM: Running Generative and Agentic AI Locally
27mBuilding Useful Apps With Small, Local LLMs
30mP2P Distributed LLM Inference Across Browsers With llama.cpp And WebRTC
44mKeynote Speaker - Simon Willison