You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Here, the ID refers to the model, but I couldn't find a way to specify the name. So, what ends up happening is that I don't see the names of the models in my HTML output anymore.
The text was updated successfully, but these errors were encountered:
Thanks for raising this, you're right that it's an issue when you include the provider in the way that you described. I'd like to add a label field or similar to the provider object, and get rid of the map that is used right now to label providers. That will make it easy for you to add a label.
#563 adds this capability, e.g. with the following setup:
promptfooconfig.yaml:
prompts:
- 'Respond to the following instruction: {{message}}'providers:
- file://lowtemp.yaml
- file://hightemp.yamltests:
- vars:
message: What's the capital of France?# ...
Currently, I can write:
This means the model is
openai:gpt-3.5-turbo
, and the name of the model that's also visible in the output HTML isopenai-gpt-3.5-turbo-hightemp
.If the provider is coming from a file like this one:
Then the provider file looks like this:
Here, the ID refers to the model, but I couldn't find a way to specify the name. So, what ends up happening is that I don't see the names of the models in my HTML output anymore.
The text was updated successfully, but these errors were encountered: