Hitting rate limiter on OpenAI api - Rasa CALM - Rasa Community Forum
👋 Introducing the Rasa Playground
Hitting rate limiter on OpenAI api
post by jackpa99 on Sep 5, 2024
I started to run the GitHub - RasaHQ/calm-langgraph-customer-service-comparison: A reimplementation of langgraph's customer support example in Rasa's CALM paradigm and a quantiative evaluation of the 2 approaches implementation on CodeSpaces. (I obtained and updated the RASA PRO LICENSE key and OpenAI Api key in .env).
I hit an error relating to OpenAI limits:
Retrying langchain.embeddings.openai.embed_with_retry.<locals>._embed_with_retry in 8.0 seconds as it raised RateLimitError: You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors..
Below is a snippet of config.yml, updated to use a cheaper model. May be willing to upgrade on the OpenAPI api package but need to know what to upgrade to…
pipeline:
- name: custom.custom_cmd_gen.CustomLLMCommandGenerator
llm:
model_name: gpt-4o-mini-2024-07-18
request_timeout: 7
max_tokens: 256
temperature: 0
cache: false
prompt_template: prompt_templates/time_aware_prompt.jinja2