Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[FEATURE} Deepseek R1 as a CrewAI assistant #2004

Open
Valdemar1863 opened this issue Jan 29, 2025 · 4 comments
Open

[FEATURE} Deepseek R1 as a CrewAI assistant #2004

Valdemar1863 opened this issue Jan 29, 2025 · 4 comments

Comments

@Valdemar1863
Copy link

Feature Area

Core functionality

Is your feature request related to a an existing bug? Please link it here.

Can a CrewAI assistant be powered by Deepseek R1 model? And can Deepseek R1 be supported without any issues for agents?

Describe the solution you'd like

I want to be able to switch to Deepseek R1 as a CrewAI assistant. And also I want to use it as an LLM for any agent

Describe alternatives you've considered

it would probably be better if it the LLM is DeepSeek-R1-Distill-Llama-70b hosted by Grok.

Additional context

No response

Willingness to Contribute

I can test the feature once it's implemented

@Valdemar1863 Valdemar1863 added the feature-request New feature or request label Jan 29, 2025
@mayankbohra
Copy link

You can use DeepSeek R1 model. In my country, I can't purchase DeepSeek API key, so I am using it through openrouter.
deepseek = LLM( model="openrouter/deepseek/deepseek-r1", api_key=os.getenv("OPENROUTER_API_KEY") )

Also, if you want to use DeepSeek-R1-Distill-Llama-70b hosted by Grok, then you can. Check out: LiteLLM, LiteLLM Groq

And, if you can purchase DeepSeek API key, then you can directly use it without the need of openrouter. Check this out: LiteLLM DeepSeek.

Hope this helps.

@chiora93
Copy link

chiora93 commented Feb 1, 2025

Yes but the crewai requirements (0.100.0) doesn't allow to install litellm version that add supports to DeepSeek https://docs.litellm.ai/release_notes/v1.59.8-stable

Any plan to upgrade this package?

@theCyberTech theCyberTech removed the feature-request New feature or request label Feb 2, 2025
@mayankbohra
Copy link

@chiora93 By the time, I would suggest to use DeepSeek through OpenRouter. I have tried that and its working for me.

@handysome6
Copy link

Currently, with the latest version of crewAI, liteLLM has been updated to v1.59.8 as @chiora93 mentioned.

Image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants