-
Notifications
You must be signed in to change notification settings - Fork 39
feat: rai_whoami #540
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
feat: rai_whoami #540
Conversation
7564d5c
to
50c8105
Compare
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.
@maciejmajek
I briefly checked the new structure and it looks great! I added some minor comments to the code and I have questions:
- How about adding an example of the module usage with rai_core agents.
- Do you plan to add a tool for RAG in the vector database?
12b3f98
to
ecfa9a6
Compare
fix: dump model on
chore: rename loaders -> models
feat: export tools
ecfa9a6
to
d02129e
Compare
f82e223
to
d3a8683
Compare
refactor: minor changes
I followed instructions in README, sample documentation got from https://github.com/RobotecAI/rai/blob/development/docs/create_robots_whoami.md. |
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.
Code changes also looks fine, good job! I posted only 1 question
Purpose
rai_whoami has been one of the first packages built under the RAI ecosystem. During migration from 1.x to 2.x, the package has been removed to make space for a new solution designed from the ground up.
rai_whoami allows automatic documentation parsing (images, documens, urdfs) into EmbodimentInfo (e.g., rules, capabilities, system prompt...)
Proposed Changes
Issues
#489 #470
Testing