# S exceeded its OpenAI usage limits, causing problems durin rasa pro training (eventhough im using gemini api)

**URL:** <https://forum.rasa.com/t/s-exceeded-its-openai-usage-limits-causing-problems-durin-rasa-pro-training-eventhough-im-using-gemini-api/63489>\
**Category:** Rasa CALM\
**Created:** [September 20, 2024, 4:04pm UTC](https://forum.rasa.com/t/s-exceeded-its-openai-usage-limits-causing-problems-durin-rasa-pro-training-eventhough-im-using-gemini-api/63489 "2024-09-20T16:04:36Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![Elliot94](https://avatars.discourse-cdn.com/v4/letter/e/ba8739/32.png) [@Elliot94](https://forum.rasa.com/u/Elliot94)\
**Post date:** [September 20, 2024, 7:20pm UTC](https://forum.rasa.com/t/s-exceeded-its-openai-usage-limits-causing-problems-durin-rasa-pro-training-eventhough-im-using-gemini-api/63489/2 "2024-09-20T19:20:14Z")

</div>

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

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

```

---

_[View the full topic](https://forum.rasa.com/t/s-exceeded-its-openai-usage-limits-causing-problems-durin-rasa-pro-training-eventhough-im-using-gemini-api/63489)._