Skip to main content

DeepSeek

DeepEval allows you to use deepseek-chat and deepseek-reasoner directly from DeepSeek to run all of DeepEval's metrics, which can be set through the CLI or in python.

Command Line​

To configure your DeepSeek model through the CLI, run the following command:

deepeval set-deepseek --model deepseek-chat \
    --api-key="your-api-key" \
    --temperature=0

The CLI command above sets deepseek-chat as the default model for all metrics, unless overridden in Python code. To use a different default model provider, you must first unset DeepSeek:

deepeval unset-deepseek
Persisting settings

You can persist CLI settings with the optional --save flag. See Flags and Configs -> Persisting CLI settings.

Python​

You can also specify your model directly in code using DeepSeekModel.

from deepeval.models import DeepSeekModel
from deepeval.metrics import AnswerRelevancyMetric

model = DeepSeekModel(
    model="deepseek-chat",
    api_key="your-api-key",
    temperature=0
)

answer_relevancy = AnswerRelevancyMetric(model=model)

There are TWO mandatory and ONE optional parameters when creating a DeepSeekModel:

  • model: A string specifying the name of the DeepSeek model to use. Either be deepseek-chat or deepseek-reasoner.
  • api_key: A string specifying your DeepSeek API key for authentication.
  • [Optional] temperature: A float specifying the model temperature. Defaulted to 0.
  • [Optional] generation_kwargs: A dictionary of additional generation parameters supported by your model provider.
tip

Any **kwargs you would like to use for your model can be passed through the generation_kwargs parameter. However, we request you to double check the params supported by the model and your model provider in their official docs.

Available DeepSeek Models​

Below is the comprehensive list of available DeepSeek models in DeepEval:

  • deepseek-chat
  • deepseek-reasoner