langchain.js
    Preparing search index...

    Class MistralAI

    MistralAI completions LLM.

    Hierarchy (View Summary)

    Implements

    Index

    Constructors

    constructor

    Properties

    apiKey batchSize beforeRequestHooks? endpoint httpClient? lc_namespace lc_serializable maxConcurrency? maxRetries? maxTokens? model randomSeed? requestErrorHooks? responseHooks? serverURL? streaming temperature topP?

    Accessors

    lc_aliases lc_secrets

    Methods

    _call _generate _llmType _streamResponseChunks addAllHooksToHttpClient completionWithRetry invocationParams removeAllHooksFromHttpClient removeHookFromHttpClient lc_name

    Constructors

    Properties

    apiKey: string

    The API key to use.

    {process.env.MISTRAL_API_KEY}
    batchSize: number = 20

    Batch size to use when passing multiple documents to generate

    beforeRequestHooks?: BeforeRequestHook[]

    A list of custom hooks that must follow (req: Request) => Awaitable<Request | void> They are automatically added when a ChatMistralAI instance is created

    endpoint: string

    use serverURL instead

    httpClient?: HTTPClient

    Optional custom HTTP client to manage API requests Allows users to add custom fetch implementations, hooks, as well as error and response processing.

    lc_namespace: string[] = ...
    lc_serializable: boolean = true
    maxConcurrency?: number
    maxRetries?: number
    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.

    model: string = "codestral-latest"

    The name of the model to use.

    "codestral-latest"
    randomSeed?: number

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

    requestErrorHooks?: RequestErrorHook[]

    A list of custom hooks that must follow (err: unknown, req: Request) => Awaitable They are automatically added when a ChatMistralAI instance is created

    responseHooks?: ResponseHook[]

    A list of custom hooks that must follow (res: Response, req: Request) => Awaitable They are automatically added when a ChatMistralAI instance is created

    serverURL?: string

    Override the default server URL used by the Mistral SDK.

    streaming: boolean = false

    Whether or not to stream the response.

    {false}
    temperature: number = 0

    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}

    Accessors

    • get lc_aliases(): undefined | { [key: string]: string }

      Returns undefined | { [key: string]: string }

    • get lc_secrets(): undefined | { [key: string]: string }

      Returns undefined | { [key: string]: string }

    Methods

    _call

    • _call(prompt: string, options: unknown): Promise<string>

      For some given input string and options, return a string output.

      Despite the fact that invoke is overridden below, we still need this in order to handle public APi calls to generate().

      Parameters

      • prompt: string
      • options: unknown

      Returns Promise<string>

    _generate

    • _generate(
          prompts: string[],
          options: unknown,
          runManager?: any,
      ): Promise<LLMResult>

      Parameters

      • prompts: string[]
      • options: unknown
      • OptionalrunManager: any

      Returns Promise<LLMResult>

    _llmType

    • _llmType(): string

      Returns string

    _streamResponseChunks

    • _streamResponseChunks(
          prompt: string,
          options: unknown,
          runManager?: any,
      ): AsyncGenerator<GenerationChunk>

      Parameters

      • prompt: string
      • options: unknown
      • OptionalrunManager: any

      Returns AsyncGenerator<GenerationChunk>

    • Returns void

    • Parameters

      • request: FIMCompletionRequest
      • options: unknown
      • stream: false

      Returns Promise<FIMCompletionResponse>

    • Parameters

      • request: FIMCompletionStreamRequest
      • options: unknown
      • stream: true

      Returns Promise<AsyncIterable<CompletionEvent, any, any>>

    • Parameters

      • options: unknown

      Returns Omit<
          MistralAIFIMCompletionRequest
          | MistralAIFIMCompletionStreamRequest,
          "prompt",
      >

    • Returns void

    • Parameters

      • hook: BeforeRequestHook | RequestErrorHook | ResponseHook

      Returns void

    • Returns string

    Settings

    Member Visibility

    On This Page

    Constructors
    Properties
    Accessors
    Methods