Fix issue #6048: Update documentation of recommended models and add deepseek
End-user friendly description of the problem this fixes or functionality that this introduces
- [x] Include this change in the Release Notes. If checked, you must provide an end-user friendly description for your change below
Update documentation of recommended models and add deepseek to verified providers
Give a summary of what the PR does, explaining any non-trivial design decisions
This adds deepseek to the verified providers and updates documentation with our recent recommendations for models that work OK.
Builds on #6063 to make this build on my computer, 6063 can be reviewed first.
Link of any specific issues this addresses
Fixes #6048
To run this PR locally, use the following command:
docker run -it --rm -p 3000:3000 -v /var/run/docker.sock:/var/run/docker.sock --add-host host.docker.internal:host-gateway -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:1f472ce-nikolaik --name openhands-app-1f472ce docker.all-hands.dev/all-hands-ai/openhands:1f472ce
As a side note, users in Discord are mentioning that even when they select deepseek-coder, it still selects deepseek-chat.
As a side note, users in Discord are mentioning that even when they select
deepseek-coder, it still selectsdeepseek-chat.
From what I recall, there used to be 2 different models until Deepseek 2.5, then it's only one for 2.5, and now 3.0. In any case, people can choose a different model than those in the drop-down by using Advanced Settings.
I do think that the drop-down should ideally allow you to type over it without resetting what you type, but it seems like a separate issue.
Hi @enyst and @mamoodi , sorry, just to clarify, is there anything you'd like me to fix before approving this PR?
No that's alright. The user opened an issue for what I'm talking about. Thanks for checking!