Local LLM Lab

Experiments with running local large language models on my own hardware.

This repo is my sandbox for:

• Chatting with local models (Ollama / LM Studio / others)
• Testing prompts and system instructions
• Trying small RAG (retrieval-augmented generation) ideas
• Exploring what’s possible without sending data to the cloud

---

Architecture (first version)

Backend: a local LLM server (starting with Ollama – but can be swapped for LM Studio or others).

Client: small Python scripts and notebooks that:

• Send a prompt to the local model
• Receive a response as JSON
• Log prompts + outputs for later analysis

---

Getting Started

1. Install requirements

Create a virtual environment (optional but recommended):

python3 -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
pip install -r requirements.txt