feat: deepseek r1 alternative tool calling format #975
+116
−1
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
michaelneale
changed the title
alicehau
reviewed
Jan 31, 2025
| .and_then(|obj| obj.get_mut("messages")) | ||
| .and_then(|messages| messages.as_array_mut()) | ||
| { | ||
| // Add "cache_control" to the last and second-to-last "user" messages |
There was a problem hiding this comment.
cache_control is just for anthropic models
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
deepseek can be used (in many ways) from openrouter, so I am trying the largest ones with this.
I found that I can replace the tool calls with a system prompt and it works... a lot of the time. If this continues, could be a more general approach for models which don't support tool calling (use type of format).
cc @ahau-square for the idea