If you’re reading this page, chances are you’ve attended my workshop and want to follow along with the code—or perhaps add your own features and improvements.

Let’s start with the repository link:
https://github.com/MehdiMohseni82/dotnet-talk.ai.profile.finder

To work with this system, you’ll need a PostgreSQL instance and an Open WebUI instance.
Both are included in the repository.
To start each one, simply navigate to its folder and run:

docker compose up -d

Model Downloads

For this project, you’ll need at least one compatible LLM model file. You can download them here:

• Qwen2-7B-Instruct-FP16.gguf:
  https://huggingface.co/Qwen/Qwen2-7B-Instruct-GGUF/tree/main

• Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf (a good choice for running on most laptops):
  https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/tree/main

Just download your preferred model and place it in the appropriate models folder as described in the repository instructions.