Interested in AI development? Then you are in the right place! Today I'm going to be showing you how to develop an advanced AI agent that uses multiple LLMs. If you want to land a developer job: https://techwithtim.net/dev ๐ Video Resources ๐ Code: https://github.com/techwithtim/AI-Agent-Code-Generator Requirements.txt: https://github.com/techwithtim/AI-Agent-Code-Generator/blob/main/requirements.txt Download Ollama: https://github.com/ollama/ollama Create a LlamaCloud Account to Use LLama Parse: https://cloud.llamaindex.ai Info on LLama Parse: https://www.llamaindex.ai/blog/introducing-llamacloud-and-llamaparse-af8cedf9006b Understanding RAG: https://www.youtube.com/watch?v=uO6r0vQmGB0 ⏳ Timestamps ⏳ 00:00 | Video Overview 00:42 | Project Demo 03:49 | Agents & Projects 05:44 | Installation/Setup 09:26 | Ollama Setup 14:18 | Loading PDF Data 21:16 | Using llama Parse 26:20 | Creating Tools & Agents 32:31 | The Code Reader Tool 38:50 | Output-Parser & Second LLM 48:20 | Retry Handle 50:20 | Saving To A File Hashtags #techwithtim #machinelearning #aiagents
Multi-LLM agent stacks multiply VRAM needs per active model. Before scaling up, check this guide to GPUs for LLM workloads covers it in detail. Watch next: Ollama Tutorial | Run Llama2 locally | 7 billion parameter model | No GPU | LangChain Integration.
