DeepSeek

Use DeepSeek models with Kern agents.

DeepSeek is a platform for providing endpoints for Large Language models. See their library of models here.

We recommend experimenting to find the best-suited model for your use-case. Here are some general recommendations:

deepseek-chat model is good for most basic use-cases.
deepseek-reasoner model is good for complex reasoning and multi-step tasks.

DeepSeek does not have rate limits. See their docs for information about how to deal with slower responses during high traffic.

Authentication

Set your DEEPSEEK_API_KEY environment variable. Get your key from here.

1export DEEPSEEK_API_KEY=***

1setx DEEPSEEK_API_KEY ***

Example

Use DeepSeek with your Agent:

1from kern.agent import Agent
2from kern.models.deepseek import DeepSeek
3
4agent = Agent(model=DeepSeek(id="deepseek-chat"), markdown=True)
5
6# Print the response in the terminal
7agent.print_response("Share a 2 sentence horror story.")

Note View more examples here.

Parameters

Parameter	Type	Default	Description
`id`	`str`	`"deepseek-chat"`	The id of the DeepSeek model to use
`name`	`str`	`"DeepSeek"`	The name of the model
`provider`	`str`	`"DeepSeek"`	The provider of the model
`api_key`	`Optional[str]`	`None`	The API key for DeepSeek (defaults to DEEPSEEK_API_KEY env var)
`base_url`	`str`	`"https://api.deepseek.com"`	The base URL for the DeepSeek API

DeepSeek extends the OpenAI-compatible interface and supports most parameters from the OpenAI model.

Note: DeepSeek's support for structured outputs is currently not fully compatible, so supports_native_structured_outputs is set to False.

Available Models

deepseek-chat - General-purpose conversational model, good for most use cases
deepseek-reasoner - Advanced reasoning model optimized for complex problem-solving and multi-step tasks