Expose more contexts as output from gather_evidence tool #793
Conversation
This file contains hidden or 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
dosubot
bot
added
size:M
jamesbraza
reviewed
Jan 7, 2025
| ] | ||
| ) | ||
|
|
||
| best_evidence = f" Best evidence(s):\n\n{top_contexts}" if top_contexts else "" |
There was a problem hiding this comment.
Two comments here:
- Is there a leading space by design?
- Can we do
"{self.settings.agent.agent_evidence_n} best evidence:"to be more precise- This may be a bad idea also, so feel free to not do this
There was a problem hiding this comment.
yea, there's a leading space by design, it's been there. On your second bullet -- that seems more confusing to me? i.e. "3 best evidence:"
There was a problem hiding this comment.
Okay agreed, and also when agent_evidence_n = 1 it will be confusing too. Ignore the second one
Co-authored-by: James Braza <jamesbraza@gmail.com>
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Outdated suggestions cannot be applied.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.
When we approach more complex trajectories, the agent models need more info for decision making. We only return by default 1 top-ranked context, this allows us to expose more to the agent model.