interface MistralAIInput {
    apiKey?: string;
    batchSize?: number;
    cache?: boolean | BaseCache<Generation[]>;
    callbackManager?: CallbackManager;
    callbacks?: Callbacks;
    concurrency?: number;
    endpoint?: string;
    maxConcurrency?: number;
    maxRetries?: number;
    maxTokens?: number;
    metadata?: Record<string, unknown>;
    model?: string;
    onFailedAttempt?: FailedAttemptHandler;
    randomSeed?: number;
    streaming?: boolean;
    tags?: string[];
    temperature?: number;
    topP?: number;
    verbose?: boolean;
}

Hierarchy

  • BaseLLMParams
    • MistralAIInput

Implemented by

Properties

apiKey?: string

The API key to use.

{process.env.MISTRAL_API_KEY}
batchSize?: number

Batch size to use when passing multiple documents to generate

cache?: boolean | BaseCache<Generation[]>
callbackManager?: CallbackManager

Use callbacks instead

callbacks?: Callbacks
concurrency?: number

Use maxConcurrency instead

endpoint?: string

Override the default endpoint.

maxConcurrency?: number

The maximum number of concurrent calls that can be made. Defaults to Infinity, which means no limit.

maxRetries?: number

The maximum number of retries that can be made for a single call, with an exponential backoff between each attempt. Defaults to 6.

maxTokens?: number

The maximum number of tokens to generate in the completion. The token count of your prompt plus maxTokens cannot exceed the model's context length.

metadata?: Record<string, unknown>
model?: string

The name of the model to use.

"codestral-latest"
onFailedAttempt?: FailedAttemptHandler

Custom handler to handle failed attempts. Takes the originally thrown error object as input, and should itself throw an error if the input error is not retryable.

randomSeed?: number

The seed to use for random sampling. If set, different calls will generate deterministic results. Alias for seed

streaming?: boolean

Whether or not to stream the response.

{false}
tags?: string[]
temperature?: number

What sampling temperature to use, between 0.0 and 2.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

{0.7}
topP?: number

Nucleus sampling, where the model considers the results of the tokens with topP probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. Should be between 0 and 1.

{1}
verbose?: boolean