タグアーカイブ programming

#!/usr/bin/env python3
import rospy
from openai_ros.srv import GptService, GptServiceResponse
import openai

def handle_gpt_request(req):
#    openai.api_key = 'your-api-key'
    openai.api_key = rospy.get_param('~key')
    
    response = openai.ChatCompletion.create(
#        model="gpt-4.0-turbo",
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "{} '{}'".format(req.prompt, req.input)}
        ]
    )

    return GptServiceResponse(response['choices'][0]['message']['content'])

def gpt_service():
    rospy.init_node('gpt_service')
    s = rospy.Service('gpt_service', GptService, handle_gpt_request)
#    print("Ready to handle GPT-4 requests.")
    print("Ready to handle GPT-3.5 requests.")
    rospy.spin()

if __name__ == "__main__":
    gpt_service()

# GptService.srv
string prompt
string input
---
string output

add_service_files(
  FILES
  Completion.srv
  GptService.srv
)

<launch>
  <arg name="key" default="$(env OPENAI_API_KEY)" />
  <arg name="max_tokens" default="256" />
  <arg name="model" default="gpt-4.0-turbo" />

  <node pkg="openai_ros" type="openai_chat_node.py" name="openai_chat" output="screen">
    <param name="key" value="$(arg key)" />
    <param name="max_tokens" value="$(arg max_tokens)" />
    <param name="model" value="$(arg model)" />
  </node>  
</launch>

robotuser@robotuser-PC:~/openai_ws$ source ~/openai_ws/devel/setup.bash
robotuser@robotuser-PC:~/openai_ws$ roslaunch openai_ros openai_chat.launch 
... logging to /home/robotuser/.ros/log/9d61ced2-f54d-11ed-b5ca-c10df8d90fa9/roslaunch-robotuser-PC-41157.log
Checking log directory for disk usage. This may take a while.
Press Ctrl-C to interrupt
Done checking log file disk usage. Usage is <1GB.

started roslaunch server http://robotuser-PC:35595/

SUMMARY
========

PARAMETERS
 * /openai_chat/key: sk-3JDluBbxsNuIhi...
 * /openai_chat/max_tokens: 256
 * /openai_chat/model: gpt-4.0-turbo
 * /rosdistro: noetic
 * /rosversion: 1.16.0

NODES
  /
    openai_chat (openai_ros/openai_chat_node.py)

auto-starting new master
process[master]: started with pid [41165]
ROS_MASTER_URI=http://localhost:11311

setting /run_id to 9d61ced2-f54d-11ed-b5ca-c10df8d90fa9
process[rosout-1]: started with pid [41175]
started core service [/rosout]
process[openai_chat-2]: started with pid [41182]
Ready to handle GPT-3.5 requests.

robotuser@robotuser-PC:~/openai_ws$ source ~/openai_ws/devel/setup.bash
robotuser@robotuser-PC:~/openai_ws$ rosservice call /gpt_service '{prompt: "Translate following to French:", input: "My name is Robotuser."}'
output: "Mon nom est Robotuser."
robotuser@robotuser-PC:~/openai_ws$ rosservice call /gpt_service '{prompt: "Translate following to Spanish:", input: "My name is Robotuser."}'
output: "Mi nombre es Robotuser."
robotuser@robotuser-PC:~/openai_ws$ rosservice call /gpt_service '{prompt: "Translate following to Japanese:", input: "My name is Robotuser."}'
output: "\u79C1\u306E\u540D\u524D\u306F\u30ED\u30DC\u30C3\u30C8\u30E6\u30FC\u30B6\u30FC\u3067\
  \u3059\u3002"
robotuser@robotuser-PC:~/openai_ws$ 

私の名前はロボットユーザーです．