Homepage  • Privacy Policy & Imprint

Connect your project to Ollama and LM Studio

Lazarus Local LLM Wrapper

↗https://github.com/Benjimen1966/Lazarus-Free-Pascal-Local-LLM-wrapper

Licence: MIT, © 2026 Benjimen Chan

A demo for ↗Lazarus/FreePascal showing how to connect your desktop application to local Large Language Models (LLMs) via ↗Ollama and ↗LM Studio. This example demonstrates that AI integrations can be implemented in FreePascal - without Python, Node.js, or external run­times.

Ollama endpoint: http://localhost:11434/api/chat
LM Studio endpoint: http://localhost:1234/v1/chat/completions

The wrapper uses FreePascal's built-in ↗fpHttpClient to make plain HTTP/JSON requests. Requests run in an application's back­ground thread (TLocalLLMThread) so the UI stays respon­sive, and responses are parsed with ↗fpJson.

Example JSON request body:

{
  "model": "llama3.1",
  "messages": [
    { "role": "user", "content": "Hello, who are you?" }
  ],
  "stream": false
}

Multi-turn conversation history is kept client-side and re-sent with each request, since neither server maintains conver­sation state between calls.


Back  •  Scroll to Top  • Homepage