👋 Introducing the Rasa Playground

S exceeded its OpenAI usage limits, causing problems during rasa pro training (even though I'm using gemini API)

post by sree1 on Sep 20, 2024

2024-09-20 21:19:46 ERROR    rasa.dialogue_understanding.generator.flow_retrieval  - [error    ] Failed to populate the FAISS store with the provided flows. error=ProviderClientAPIException("Failed to embed documents\nOriginal error: litellm.RateLimitError: RateLimitError: OpenAIException - Error code: 429 - {'error': {'message': '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.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}})")
error_type=ProviderClientAPIException event_key=flow_retrieval.populate_vector_store.not_populated
2024-09-20 21:19:46 ERROR    rasa.dialogue_understanding.generator.llm_based_command_generator  - [error    ] Flow retrieval store is inaccessible. error=ProviderClientAPIException("Failed to embed documents\nOriginal error: litellm.RateLimitError: RateLimitError: OpenAIException - Error code: 429 - {'error': {'message': '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.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}})")
event_key=llm_based_command_generator.train.failed
2024-09-20 21:19:46 ERROR    rasa.engine.graph  - [error    ] graph.node.error_running_component node_name=train_SingleStepLLMCommandGenerator0
ProviderClientAPIException: ProviderClientAPIException:
Failed to embed documents
Original error: litellm.RateLimitError: RateLimitError: OpenAIException - Error code: 429 - {'error': {'message': '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.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}

I'm using gemini API,

recipe: default.v1
language: en
pipeline:

- name: SingleStepLLMCommandGenerator
  llm:
    provider: gemini
    model: gemini-1.5-flash

policies:

- name: FlowPolicy

# - name: EnterpriseSearchPolicy

# - name: RulePolicy

this how my config.yml looks like, don’t know who to resolve it. Thanks in advance

post by Elliot94 on Sep 20, 2024

Maybe try setting the flow_retrieval under the SingleStepLLMCommandGenerator to false. This uses OpenAI embeddings by default and might be causing this issue.

  - name: SingleStepLLMCommandGenerator
    llm:
      provider: gemini
      model: "gemini-1.5-flash"
    flow_retrieval:
      active: false