# Client code

We provide client codes in both Python and Javascript.

### Installation[​](https://docs.mistral.ai/platform/client/#installation) <a href="#installation" id="installation"></a>

Follow installation instructions in the repository for our Python Client or Javascript Client.

### Chat Completion[​](https://docs.mistral.ai/platform/client/#chat-completion) <a href="#chat-completion" id="chat-completion"></a>

The chat completion API allows you to chat with a model fine-tuned to follow instructions.

* python
* javascript
* curl

```
from nido.client import NidoClient
from nido.models.chat_completion import ChatMessage

api_key = os.environ["NIDO_API_KEY"]
model = "nido-tiny"

client = NidoClient(api_key=api_key)

messages = [
    ChatMessage(role="user", content="What is the best French cheese?")
]

# No streaming
chat_response = client.chat(
    model=model,
    messages=messages,
)

# With streaming
for chunk in client.chat_stream(model=model, messages=messages):
    print(chunk)
```

We allow users to provide a custom system prompt (see API reference). A convenient `safe_mode` flag allow to force chat completion to be moderated against sensitive content (see Guardrailing).

### Embeddings[​](https://docs.mistral.ai/platform/client/#embeddings) <a href="#embeddings" id="embeddings"></a>

The embeddings API allows you to embed sentences.

* python

```
from nido.client import NidoClient

api_key = os.environ["NIDO_API_KEY"]
client = NidoClient(api_key=api_key)

embeddings_batch_response = client.embeddings(
      model="nido-embed",
      input=["Embed this sentence.", "As well as this one."],
  )
```

## Third-Party Clients

Here are some clients built by the community for various other languages:

### Go[​](https://docs.mistral.ai/platform/client/#go) <a href="#go" id="go"></a>

[Gage-Technologies](https://github.com/Gage-Technologies/mistral-go)