wehub-resource-sync
98 lines
3.9 KiB
Plaintext
98 lines
3.9 KiB
Plaintext
---
|
|
# id: deepseek
|
|
title: DeepSeek
|
|
sidebar_label: 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:
|
|
|
|
```bash
|
|
deepeval set-deepseek --model=deepseek-chat \
|
|
--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:
|
|
|
|
```bash
|
|
deepeval unset-deepseek
|
|
```
|
|
|
|
:::tip[Persisting settings]
|
|
You can persist CLI settings with the optional `--save` flag.
|
|
See [Flags and Configs -> Persisting CLI settings](/docs/evaluation-flags-and-configs#persisting-cli-settings-with---save).
|
|
:::
|
|
|
|
### Python
|
|
|
|
You can also specify your model directly in code using `DeepSeekModel`.
|
|
|
|
<Tabs items={["Python", "ENV"]}>
|
|
<Tab value="Python">
|
|
|
|
```python
|
|
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)
|
|
```
|
|
|
|
</Tab>
|
|
<Tab value="ENV">
|
|
|
|
To use any DeepSeek model directly in `deepeval`, set the `USE_DEEPSEEK_MODEL=1` in your `env` and simply pass the name of your desired model in your metric initialization:
|
|
|
|
```python
|
|
from deepeval.metrics import AnswerRelevancyMetric
|
|
|
|
answer_relevancy = AnswerRelevancyMetric(
|
|
model="deepseek-chat",
|
|
)
|
|
```
|
|
|
|
You should also set the other necessary vars like `DEEPSEEK_API_KEY` to be able to use the Deepseek models as shown above.
|
|
|
|
</Tab>
|
|
</Tabs>
|
|
|
|
There are **ZERO** mandatory and **SIX** optional parameters when creating a `DeepSeekModel`:
|
|
|
|
- [Optional] `model`: A string specifying the name of the DeepSeek model to use. Defaults to `DEEPSEEK_MODEL_NAME` if not passed; raises an error at runtime if unset.
|
|
- [Optional] `api_key`: A string specifying your DeepSeek API key for authentication. Defaults to `DEEPSEEK_API_KEY` if not passed; raises an error at runtime if unset.
|
|
- [Optional] `temperature`: A float specifying the model temperature. Defaults to `TEMPERATURE` if not passed; falls back to `0.0` if unset.
|
|
- [Optional] `cost_per_input_token`: A float specifying the cost for each input token for the provided model. Defaults to `DEEPSEEK_COST_PER_INPUT_TOKEN` if available in `deepeval`'s model cost registry, else `None`.
|
|
- [Optional] `cost_per_output_token`: A float specifying the cost for each output token for the provided model. Defaults to `DEEPSEEK_COST_PER_OUTPUT_TOKEN` if available in `deepeval`'s model cost registry, else `None`.
|
|
- [Optional] `generation_kwargs`: A dictionary of additional generation forwarded to the OpenAI `chat.completions.create(...)` call.
|
|
|
|
Parameters may be explicitly passed to the model at initialization time, or configured with optional settings. The **mandatory** parameters are required at runtime, but you can provide them either explicitly as constructor arguments, **or** via `deepeval` settings / environment variables (constructor args take precedence). See [Environment variables and settings](/docs/evaluation-flags-and-configs#model-settings-deep-seek) for the DeepSeek-related environment variables.
|
|
|
|
:::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](https://api-docs.deepseek.com/api/create-chat-completion#request).
|
|
:::
|
|
|
|
### Available DeepSeek Models
|
|
|
|
Below is the comprehensive list of available DeepSeek models in `deepeval`:
|
|
|
|
- `deepseek-chat`
|
|
- `deepseek-v3.2`
|
|
- `deepseek-v3.2-exp`
|
|
- `deepseek-v3.1`
|
|
- `deepseek-v3`
|
|
- `deepseek-reasoner`
|
|
- `deepseek-r1`
|
|
- `deepseek-r1-lite`
|
|
- `deepseek-v2.5`
|
|
- `deepseek-coder`
|
|
- `deepseek-coder-6.7b`
|
|
- `deepseek-coder-33b`
|