Are you curious about the power of AI but concerned about data privacy, cloud costs, or just want to experiment on your own terms? Look no further! Learn with Cisco brings you a special episode featuring our experts Jason Belk, Hank Preston, and Jesus Illescas, as they demystify running Large Language Models (LLMs) locally using LM Studio. In this insightful compilation, you'll discover:
- Why Run LLMs Locally: Understand the benefits of privacy, cost savings, and local experimentation.
- Getting Started with LM Studio: A practical guide to installing, downloading models (like Meta Llama), and interacting with them with ease.
- Advanced Use Cases for Network Engineers: Explore how to leverage LM Studio for network configuration analysis, Retrieval Augmented Generation (RAG) with network documentation, and even analyzing network diagrams.
- Building AI Agents with LangChain: See how to create custom tools and agents for network troubleshooting and automation, integrating with platforms like PIATS and WebEx.
- The Power of Local Testing: Learn how to build and test AI agents in a contained environment before going to production, saving tokens and costs.
