# Crewai is having major problem , its takes openai reference though using other llms

**URL:** <https://community.crewai.com/t/crewai-is-having-major-problem-its-takes-openai-reference-though-using-other-llms/6408>\
**Category:** General\
**Created:** [June 29, 2025, 4:52am UTC](https://community.crewai.com/t/crewai-is-having-major-problem-its-takes-openai-reference-though-using-other-llms/6408 "2025-06-29T04:52:14Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![royjoydeep1](https://avatars.discourse-cdn.com/v4/letter/r/41988e/32.png) [@royjoydeep1](https://community.crewai.com/u/royjoydeep1)\
**Post date:** [June 29, 2025, 4:52am UTC](https://community.crewai.com/t/crewai-is-having-major-problem-its-takes-openai-reference-though-using-other-llms/6408/1 "2025-06-29T04:52:14Z")

</div>

Crewai is having major problem , its takes openai reference though using other llms

- Many feature and tools are failing in other LLMs like bedrock ( PDFSearch)
- While using streamlit and gradio and using business logic its default taking openai references and giving openai.APIStatusError: Error code: 302
- Seems crewai is very much tightly coupled with OpenAI for complex scenarios .

Usecase-1  
Getting the below errors while trying to connect with JIRA , so that the agent can create and update JIRA stories.  
using bedrock details in .env file and as per community suggestion also put OPENAI\_API\_KEY=NA , though after running the code its giving the

Error  
**openai.APIStatusError: Error code: 302**

File “C:\Users\joydroy\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\_base\_client.py”, line 949, in request  
return self.\_request(  
^^^^^^^^^^^^^^  
File “C:\Users\joydroy\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\_base\_client.py”, line 1057, in \_request  
raise self.\_make\_status\_error\_from\_response(err.response) from None  
openai.APIStatusError: Error code: 302