-
Notifications
You must be signed in to change notification settings - Fork 44.2k
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
Error: The following AI output couldn't be converted to a JSON: #2229
Comments
Seems related to #21 |
I'm having the same issue: -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= |
Attempted to access path outside of working directory is related to #2278 |
Are there any resolution to this error. I am facing the same issue. ALthough I might mention that my bot is telling me to check that I have a PAID OpenAI API Account, which I don't have. |
same error here: 2023-04-18 20:26:22,597 ERROR logs:_log:120 Error: The following AI output couldn't be converted to a JSON: i'm running on docker open api paid account try gpt-3 and 4 |
Tell ChatGPT to write you a UI to access the web version ;) thank me later peace |
HI, can you kindly be more specific? I am a newbie |
Error: The following AI output couldn't be converted to a JSON: |
'y -N' |
GPT-3 or GPT-4
Steps to reproduce 🕹
AI Name: Hama
Hama here! I am at your service.
Describe your AI's role: For example, 'an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.'
Hama is: An AI created to teach AZ 305 courses to students who only have basic knowledge of Azure and are expected to pass the certification after the training.
Enter up to 5 goals for your AI: For example: Increase net worth, Grow Twitter Account, Develop and manage multiple businesses autonomously'
Enter nothing to load defaults, enter nothing when finished.
Goal 1: Provide comprehensive and engaging AZ 305 lessons to students with limited prior knowledge of Azure.
Goal 2: Ensure that students understand all the key concepts and technologies covered in the AZ 305 certification exam.
Goal 3: Foster students' ability to apply their knowledge of Azure in real-world scenarios.
Goal 4: Provide students with regular opportunities to practice and test their knowledge through quizzes, exercises, and other interactive activities.
Goal 5: Help students prepare effectively for the AZ 305 certification exam, including offering guidance on best practices for taking the exam and providing access to relevant study materials.
Using memory of type: LocalCache
Using Browser: chrome
| Thinking...
[....]
Let's use the "message_agent" command to delegate a task to the GPT agent we just started. We should provide the agent's key and a message containing the task we want it to perform.
NEXT ACTION: COMMAND = start_agent ARGUMENTS = {'name': 'AZ305_GPT_Agent', 'task': 'Creating quizzes, generating lecture materials, and providing guidance on best practices for taking the AZ 305 certification exam', 'prompt': 'What specific task would you like me to perform?'}
SYSTEM: Command start_agent returned: Agent AZ305_GPT_Agent created with key 7. First response: As an AI language model, I don't have any specific task for you to perform. However, if you have any questions or need any assistance, feel free to ask me.
Current behavior 😯
error.log
No matter what Input is added, loop into that result :*
Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ...
Input:CHANGE THE REQUEST FOR CHAT GPT IN THE NEXT ACTION
SYSTEM: Human feedback: CHANGE THE REQUEST FOR CHAT GPT IN THE NEXT ACTION
Error: The following AI output couldn't be converted to a JSON:
I'm sorry, but I'm not sure what you mean by "CHANGE THE REQUEST FOR CHAT GPT IN THE NEXT ACTION". Can you please provide more context or clarify your request?
NEXT ACTION: COMMAND = human_feedback ARGUMENTS = {'name': 'AZ305_GPT_Agent', 'task': 'Creating quizzes, generating lecture materials, and providing guidance on best practices for taking the AZ 305 certification exam', 'prompt': 'What specific task would you like me to perform?'}
Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ...
Input:
Expected behavior 🤔
No response
Your prompt 📝
# Paste your prompt here
The text was updated successfully, but these errors were encountered: