# Mistral conversation

Type: `conversation.mistral`

Status: alpha

Reference: https://docs.dapr.io/reference/components-reference/supported-conversation/mistral/

## Example

```
apiVersion: cra.diagrid.io/v1beta1
kind: Component
metadata:
  name: <name>
spec:
  type: conversation.mistral
  version: v1
  metadata:
    # API key for Mistral.
    - name: key
      value: | 
        **********
    # A time-to-live value for a prompt cache to expire. Uses Golang durations (Optional)
    #- name: cacheTTL
    #  value: "10m"
    # Default maximum number of tokens the model may generate per request. A request-level maxTokens value greater than zero overrides this default. When unset, no cap is sent and the provider's own default applies. (Optional)
    #- name: maxTokens
    #  value: "2048"
    # The Mistral LLM to use. Configurable via MISTRAL_MODEL environment variable. (Optional)
    #- name: model
    #  value: "open-mistral-7b"

```

## Authentication profiles

Available authentication profiles:

- API Key

### API Key

Authenticate using an API key

#### `key` (string)

**Required** - API key for Mistral.

Example value:

```
**********
```

## Metadata

### `cacheTTL` (string)

A time-to-live value for a prompt cache to expire. Uses Golang durations

Example value: `10m`

### `maxTokens` (number)

Default maximum number of tokens the model may generate per request. A request-level maxTokens value greater than zero overrides this default. When unset, no cap is sent and the provider's own default applies.

Example value: `2048`

### `model` (string)

The Mistral LLM to use. Configurable via MISTRAL_MODEL environment variable.

Default value: `open-mistral-7b`

Example value: `open-mistral-7b`