ROS Index
|
llm_config package from ros-llm repollm_bringup llm_config llm_input llm_interfaces llm_model llm_output llm_robot |
Package Summary
| Tags | No category tags. |
| Version | 0.0.1 |
| License | Apache-2.0 |
| Build type | AMENT_PYTHON |
| Use | RECOMMENDED |
Repository Summary
| Description | ROS-LLM is a framework designed for embodied intelligence applications in ROS. It allows natural language interactions and leverages Large Language Models (LLMs) for decision-making and robot control. With an easy configuration process, this framework allows for swift integration, enabling your robot to operate with it in as little as ten minutes. |
| Checkout URI | https://github.com/auromix/ros-llm.git |
| VCS Type | git |
| VCS Version | ros2-humble |
| Last Updated | 2023-07-10 |
| Dev Status | UNKNOWN |
| CI status | No Continuous Integration |
| Released | UNRELEASED |
| Tags | ros gpt llm embodied-intelligence |
| Contributing |
Help Wanted (0)
Good First Issues (0) Pull Requests to Review (0) |
Package Description
Additional Links
Maintainers
- Herman Ye
Authors
llm_config
Package Description
The llm_config package configures the behavior and user preferences of a robot. It consists of two functionalities, the robot_behavior.py and user_config.py modules.
robot_behavior.py
The robot_behavior.py module controls the movement of the robot by customizing a list of robot functions. To modify the robot’s behavior, the functions in this module must be edited correspondingly with the llm_robot/turtle_robot.py real functions.
user_config.py
The user_config.py module allows users to specify various parameters that affect the AI’s output, including the OpenAI language model used, temperature, top probability cutoff, and frequency and presence penalties. Users can also set the chat prompt, the prefix for the AI’s response, and the maximum number of tokens and length allowed in the response. The module can store chat history in a JSON file with a maximum length limit. it also enables further customization of the assistant’s behavior using a RobotBehavior object and a list of robot functions. This module contains API credentials for Amazon AWS along with parameters for services such as AWS S3, Transcribe, and Polly, as well as audio recording.
For instructions on usage and customization details, please refer to the individual module files.
Wiki Tutorials
Package Dependencies
| Deps | Name |
|---|---|
| ament_copyright | |
| ament_flake8 | |
| ament_pep257 |
System Dependencies
| Name |
|---|
| python3-pytest |