Let the model call your code safely You wrap a host capability with a name, purpose, typed arguments, result, and handler. The model sees when and how to call it while your app keeps control of execution. python academy academy/topics/typed-tools website/content-src/academy/course.mjs academy Let the model call your code safely
ax
Python axllm
TypeScript Python Java C++ Go Rust
Unit 3 · Build a reliable AI-powered feature

Let the model call your code safely

You wrap a host capability with a name, purpose, typed arguments, result, and handler. The model sees when and how to call it while your app keeps control of execution.

fn()8 focused minutesNot started
Worked example

See the idea in context

from axllm import f, fn

search = (
    fn('search')
    .description('Search docs')
    .arg('query', f.string('Search query'))
    .handler(lambda args: ['hit for ' + args['query']])
    .build()
)
  1. Explain when to call it

    The name and description orient the model toward product documentation searches.

  2. Constrain the call

    query must be a string and the result is declared as a string.

  3. Bind trusted code

    searchDocs runs in your host environment when the tool is selected.

Run itIn your own project
pip install axllm

from axllm import ai, ax

llm = ai('openai', api_key=os.environ['OPENAI_API_KEY'])
classify = ax('review:string -> sentiment:class "positive, negative, neutral"')

Set OPENAI_APIKEY in your environment before running provider-backed code.

In the ax repo

From a clone of the ax repo:

npm run example -- python src/examples/python/generation/axgen-openai.py
Active practice

Show that you can use it

Answer 2 in a row to learn this · attempt 1
Keep exploring

Source-backed follow-up