# Local llm error with enviromental variable OPENAI key

**URL:** <https://forum.rasa.com/t/local-llm-error-with-enviromental-variable-openai-key/63655>\
**Category:** Rasa CALM\
**Created:** [October 1, 2024, 3:14pm UTC](https://forum.rasa.com/t/local-llm-error-with-enviromental-variable-openai-key/63655 "2024-10-01T15:14:54Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![Gray430](https://avatars.discourse-cdn.com/v4/letter/g/cab0a1/32.png) [@Gray430](https://forum.rasa.com/u/Gray430)\
**Post date:** [March 17, 2025, 10:31am UTC](https://forum.rasa.com/t/local-llm-error-with-enviromental-variable-openai-key/63655/6 "2025-03-17T10:31:14Z")

</div>

Thanks a mil!! It really helps. Plus, if someone is using llama.cpp, specifically llama-server.exe, need to add a --pooling mean param to fit the API.

---

_[View the full topic](https://forum.rasa.com/t/local-llm-error-with-enviromental-variable-openai-key/63655)._