-
Notifications
You must be signed in to change notification settings - Fork 156
chore: Upgrade default model to command-r-08-2024 #1691
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
@julian-risch in addition manually verified to work nicely with agents. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Updating only the usage example and the https://haystack.deepset.ai/integrations/cohere integration page seems good to me though. |
Ok, I don't mind, but command-r is two generations behind and command-r-plus cost is inline with top of the line models from various providers |
We can leave this PR around and trigger integration - when needed |
Let's get an opinion from another team member. We could release a new major version cohere-v5.0.0 with that change. And we could also briefly explain the change in the weekly announcement https://github.com/deepset-ai/devrel-board/issues/604 |
What about a warning, just something in the stdout warning the user that this current release changed the default model, and the price is 10x more? We would then remove it in the next release. |
Yes, no problem, new piece of information: we should also investigate the situation why command-r doesn't work with our agent while command-r-plus and command-a do. Including multiple tool calls.
This one I found confusing because we do test for tool calling in cohere with command-r using actual live model yet agent doesn't like this format. Could be something simple, some setting, |
It is very common that such old models are cheap and new ones are more expensive. See the price chat above - nothing out of the ordinary here requiring warnings IMHO |
Even if all other models have the same base price as the new default, we should make clear to the user that this integration has changed, and the default model cost is now 10x the previous default. |
Maybe a release note is enough, but 10x is a big difference! |
@julian-risch and @davidsbatista I've updated description to reflect the finding that the |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good to me! 👍
command-r is an alias for command-r-03-2024 (Cohere docs)
and while command-r-03-2024 is not deprecated yet, support for models fine-tuned with Command-R-03-2024 ended on March 08, 2025. (Cohere docs)
For that reason, I believe it's a good idea to update our default from command-r-03-2024 to command-r-08-2024. And my understanding is that the price doesn't change at all, which is good.
Included in https://pypi.org/project/cohere-haystack/4.1.0/ release |
Why:
This PR upgrades the Cohere integration to use the
command-r-08-2024
chat model. Compared tocommand-r
, thecommand-r-08-2024
model seems to have more modern tool support and it works well with Haystack Agent. The oldcommand-r
had issues with resolving tools with OpenAI tool JSON format which we use. This description has been updated after we found out thatcommand-r-08-2024
works well with our tooling architecture. The discussion below refers tocommand-r-plus
which we though of using but have since found an update tocommand-r
that iscommand-r-08-2024
- which works well.What:
command-r-08-2024
instead ofcommand-r
.How can it be used:
No changes needed from the user—new pipelines using Cohere will default to the upgraded model automatically.
How did you test it:
Notes for the reviewer: