Skip to main content
memory.py

Run the Example

1

Set up your virtual environment

2

Install dependencies

3

Export your vLLM API key

4

Run PgVector

5

Install vLLM

Install vLLM in the environment that will serve the model:
6

Start vLLM

Serve the model used by this example with tool calling enabled:
7

Run the example

Save the code above as memory.py, then run:
Full source: cookbook/90_models/vllm/memory.py