Hopiu/llm
1
0
Fork 0
mirror of https://github.com/Hopiu/llm.git synced 2026-04-27 00:14:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Clarify lazy loading

Browse source 
https://bsky.app/profile/simonwillison.net/post/3lknwgbph522h

!stable-docs
This commit is contained in:
Simon Willison 2025-03-18 08:04:52 -07:00 committed by GitHub
parent bfbcc201b7
commit 0f47565530
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
docs/python-api.md
View file

@ -18,6 +18,12 @@ model.key = "sk-..."
response = model.prompt("Five surprising names for a pet pelican")
print(response.text())
```
Note that the prompt will not be evaluated until you call that `response.text()` method - a form of lazy loading.
If you inspect the response before it has been evaluated it will look like this:
<Response prompt='Your prompt' text='... not yet done ...'>
The `llm.get_model()` function accepts model IDs or aliases. You can also omit it to use the currently configured default model, which is `gpt-4o-mini` if you have not changed the default.
In this example the key is set by Python code. You can also provide the key using the `OPENAI_API_KEY` environment variable, or use the `llm keys set openai` command to store it in a `keys.json` file, see {ref}`api-keys`.