Add use cases to the Readme

Author: AndyZe

.github/workflows/build.yml

@@ -1,36 +1,18 @@
-# This is a basic workflow to help you get started with Actions
-
 name: CI
 
-# Controls when the workflow will run
-on:
-  # Triggers the workflow on push or pull request events but only for the "main" branch
-  push:
-    branches: [ "main" ]
-  pull_request:
-    branches: [ "main" ]
-
-  # Allows you to run this workflow manually from the Actions tab
-  workflow_dispatch:
+on: [push, pull_request]
 
-# A workflow run is made up of one or more jobs that can run sequentially or in parallel
 jobs:
-  # This workflow contains a single job called "build"
-  build:
-    # The type of runner that the job will run on
+  industrial_ci:
+    strategy:
+      matrix:
+        env:
+          - {ROS_DISTRO: humble, ROS_REPO: main}
+          - {ROS_DISTRO: jazzy, ROS_REPO: main}
     runs-on: ubuntu-latest
-
-    # Steps represent a sequence of tasks that will be executed as part of the job
+    env:
+      UPSTREAM_WORKSPACE: upstream.repos
     steps:
-      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
-      - uses: actions/checkout@v4
-
-      # Runs a single command using the runners shell
-      - name: Run a one-line script
-        run: echo Hello, world!
-
-      # Runs a set of commands using the runners shell
-      - name: Run a multi-line script
-        run: |
-          echo Add other actions to build,
-          echo test, and deploy your project.
+      - uses: actions/checkout@v3
+      - uses: 'ros-industrial/industrial_ci@master'
+        env: ${{matrix.env}}

README.md

@@ -2,6 +2,18 @@
 
 OpenAI server node for ROS2 Applications
 
+## What is this useful for?
+
+If you don't have an image processing pipeline or a GPU on your robot, calls to OpenAI can replace much of that functionality. As of July 2024 we generally recommend yes/no questions, otherwise you will need to parse the response yourself. This package includes a simple filter which parses for yes/no. For example:
+
+- Is it safe for the robot to drive forward? Please respond in one word, yes or no.
+- Is the door open? Please respond in one word, yes or no.
+- Is there a customer at that table? Please respond in one word, yes or no.
+- Did the robot successfully grasp the cube?  Please respond in one word, yes or no.
+- Does the control panel look identical to the last time I checked? Please respond in one word, yes or no.
+
+Some of these examples are useful for reinforcement learning, i.e. for determining if a reward was earned.
+
 ## Setup
 
 Requires an OpenAI key as described here: https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key
@@ -16,11 +28,11 @@ Here's a quick example:
 
 Send it a prompt. Here's an example that returns a bool from a yes/no question. Not that the `image` field of the service request may be left empty.
 
-`ros2 service call /openai_bool_response ai_msgs/srv/BoolResponse prompt:\ "are you a pirate? please respond with a one-word answer, yes or no"`
+`ros2 service call /openai_bool_response ai_msgs/srv/BoolResponse prompt:\ "Are you a pirate? Please respond with a one-word answer, yes or no"`
 
 Here's an example that returns a full string.
 
-`ros2 service call /openai_string_response ai_msgs/srv/StringResponse prompt:\ "are you a pirate?"`
+`ros2 service call /openai_string_response ai_msgs/srv/StringResponse prompt:\ "Are you a pirate?"`
 
 There's an example client which sends an image of a wooden table and prompts whether it is indeed a wooden table:
 

upstream.repos

@@ -0,0 +1,5 @@
+repositories:
+  ai_msgs:
+    type: git
+    url: https://github.com/robosoft/ai_msgs.git
+    version: main