-
Notifications
You must be signed in to change notification settings - Fork 164
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
conversion from xml to json #843
base: exp-843
Are you sure you want to change the base?
Conversation
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
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.
Thanks @nugget-cloud.
Given this is an exploration work, we can start from some small experiments using agent-related templates (e.g., in prompts/agent
, prompts/tool
).
If they prove to be useful, we can extend the JSON structure to more prompts.
Some minor comments below:
Yep, it will be expensive to run it locally. However, PR experiments can only be run by the maintainer of this repo.
For simplicity, let's revert the conflict files for now (we need to start with some small experiments using agent-related templates anyway) so that you don't have to repeatedly fixing them. |
287db22
to
b082cb6
Compare
821989f
to
8dfbb9f
Compare
8dfbb9f
to
5e96c34
Compare
Hi , @DonggeLiu I signed the CLA but the error still persists , I am not sure what is the issue |
|
Converting this to a draft for now, but please let me know when you are ready. @nugget-cloud |
#743
@DonggeLiu
Hello, I made some changes by removing the XML tags from all the prompts in the prompts directory. Could you please provide some feedback on whether I'm doing this correctly?
I attempted to run
run_all_experiments.py
, but I stopped midway because I was concerned it was making too many calls and that the API might be expensive.