A local LLM endpoint (e.g., LM Studio, Ollama) running at http://localhost:1234/v1.
The model name should be set in agent.py where model="<название модели в LM Studio>".
Installation
python -m venv .venv
source .venv/bin/activate # On Windows use .venv\Scripts\activate
pip install -r requirements.txt
Running the Agent
python agent.py
You will be prompted to enter a query. The agent will stream tokens to the console incrementally, separating each step with --- --- ---.
Example
Введите запрос: Какой у меня бюджет на продукты в Казани?
get_price({'product': 'молоко', 'city': 'Казань'})--- --- ---
... (streamed tokens) ...
--- --- ---
Ensure that the endpoint URL and model name match your local setup.