The API request of ACTION_AGENT failed: OpenAI API request exceeded rate limit

[osbritod]

Why does this error appear when running ACTION_AGENT? In the openai api there is no option to increase the rate limit to more than 10k

Please enter your request to be completed🛸:
open new tab in chrome and go to google.com.br
Step 0: Selecting an application.
Observations👀: The current screenshot shows the Visual Studio Code application with a file named 'config.yaml' open. The Google Chrome application is not visible in the screenshot.
Thoughts💡: I need to open the Google Chrome application and navigate to google.com.br in a new tab. Since Google Chrome is not visible in the screenshot, I will select it from the list of available applications.
Selected application📲: New Discussion · microsoft/UFO - Google Chrome
Next Plan📚: (1) Open the window of 'New Discussion · microsoft/UFO - Google Chrome'.
(2) Use the 'Ctrl+T' keyboard shortcut to open a new tab in Chrome.
(3) Set text 'google.com.br' in the address bar.
(4) Press 'Enter' to navigate to google.com.br.
Comment💬: I will open Google Chrome and navigate to google.com.br in a new tab.
Creating an experience indexer...
Warning: Failed to load experience indexer from vectordb/experience/experience_db.
Step 1: Taking an action on application New Discussion · microsoft/UFO - Google Chrome.
The API request of ACTION_AGENT failed: OpenAI API request exceeded rate limit: Error code: 429 - {'error': {'message': 'Request too large for gpt-4-vision-preview in organization org-4E0xV9ldS6EFbhTZSFZUlI6m on tokens per min (TPM): Limit 10000, Requested 13119. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.', 'type': 'tokens', 'param': None, 'code': 'rate_limit_exceeded'}}.
Switching to use the backup engine...
Error occurs when calling LLM: OpenAI API returned an API Error: Error code: 404 - {'error': {'message': 'Invalid URL (POST /v1/chat/completions/chat/completions)', 'type': 'invalid_request_error', 'param': None, 'code': None}}
Request total cost is $0.07

[theospeak]

Hi . It might be a bit late and I just got into this. Still new to Python and AI.

You can change the rate limit in the config.yaml file. By default it is set to 1000. You can maybe increase it to 1500?

For GPT parameters

MAX_TOKENS: 2000 # The max token limit for the response completion
MAX_RETRY: 3 # The max retry limit for the response completion
TEMPERATURE: 0.0 # The temperature of the model: the lower the value, the more consistent the output of the model
TOP_P: 0.0 # The top_p of the model: the lower the value, the more conservative the output of the model
TIMEOUT: 60 # The call timeout(s), default is 1 min