Interface ChatOllamaInput

Input to chat model class.

interface ChatOllamaInput {
    baseUrl?: string;
    cache?: boolean | BaseCache<Generation[]>;
    callbackManager?: CallbackManager;
    callbacks?: Callbacks;
    checkOrPullModel?: boolean;
    disableStreaming?: boolean;
    embeddingOnly?: boolean;
    f16Kv?: boolean;
    fetch?: {
        (input: RequestInfo | URL, init?: RequestInit): Promise<Response>;
        (input: string | Request | URL, init?: RequestInit): Promise<Response>;
    };
    format?: string | Record<string, any>;
    frequencyPenalty?: number;
    headers?: Record<string, string> | Headers;
    keepAlive?: string | number;
    logitsAll?: boolean;
    lowVram?: boolean;
    mainGpu?: number;
    maxConcurrency?: number;
    maxRetries?: number;
    metadata?: Record<string, unknown>;
    mirostat?: number;
    mirostatEta?: number;
    mirostatTau?: number;
    model?: string;
    numBatch?: number;
    numCtx?: number;
    numGpu?: number;
    numKeep?: number;
    numPredict?: number;
    numThread?: number;
    numa?: boolean;
    onFailedAttempt?: FailedAttemptHandler;
    penalizeNewline?: boolean;
    presencePenalty?: number;
    repeatLastN?: number;
    repeatPenalty?: number;
    seed?: number;
    stop?: string[];
    streaming?: boolean;
    tags?: string[];
    temperature?: number;
    tfsZ?: number;
    think?: boolean;
    topK?: number;
    topP?: number;
    typicalP?: number;
    useMlock?: boolean;
    useMmap?: boolean;
    verbose?: boolean;
    vocabOnly?: boolean;
}

Hierarchy (view full)

Implemented by

Properties

baseUrl? cache? callbackManager? callbacks? checkOrPullModel? disableStreaming? embeddingOnly? f16Kv? fetch? format? frequencyPenalty? headers? keepAlive? logitsAll? lowVram? mainGpu? maxConcurrency? maxRetries? metadata? mirostat? mirostatEta? mirostatTau? model? numBatch? numCtx? numGpu? numKeep? numPredict? numThread? numa? onFailedAttempt? penalizeNewline? presencePenalty? repeatLastN? repeatPenalty? seed? stop? streaming? tags? temperature? tfsZ? think? topK? topP? typicalP? useMlock? useMmap? verbose? vocabOnly?

Properties

OptionalbaseUrl

baseUrl?: string

The host URL of the Ollama server.

Default

"http://127.0.0.1:11434"

Optionalcache

cache?: boolean | BaseCache<Generation[]>

OptionalcallbackManager

callbackManager?: CallbackManager

Deprecated

Use callbacks instead

Optionalcallbacks

callbacks?: Callbacks

OptionalcheckOrPullModel

checkOrPullModel?: boolean

Whether or not to check the model exists on the local machine before invoking it. If set to true, the model will be pulled if it does not exist.

Default

false

OptionaldisableStreaming

disableStreaming?: boolean

Whether to disable streaming.

If streaming is bypassed, then stream() will defer to invoke().

  • If true, will always bypass streaming case.
  • If false (default), will always use streaming case if available.

OptionalembeddingOnly

embeddingOnly?: boolean

Optionalf16Kv

f16Kv?: boolean

Optionalfetch

fetch?: {
    (input: RequestInfo | URL, init?: RequestInit): Promise<Response>;
    (input: string | Request | URL, init?: RequestInit): Promise<Response>;
}

The fetch function to use.

Type declaration

    • (input, init?): Promise<Response>

    • MDN Reference

      Parameters

      • input: RequestInfo | URL
      • Optionalinit: RequestInit

      Returns Promise<Response>

    • (input, init?): Promise<Response>

    • Parameters

      • input: string | Request | URL
      • Optionalinit: RequestInit

      Returns Promise<Response>

Default

fetch

Optionalformat

format?: string | Record<string, any>

OptionalfrequencyPenalty

frequencyPenalty?: number

Optionalheaders

headers?: Record<string, string> | Headers

Optional HTTP Headers to include in the request.

OptionalkeepAlive

keepAlive?: string | number

Default

"5m"

OptionallogitsAll

logitsAll?: boolean

OptionallowVram

lowVram?: boolean

OptionalmainGpu

mainGpu?: number

OptionalmaxConcurrency

maxConcurrency?: number

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

OptionalmaxRetries

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.

Optionalmetadata

metadata?: Record<string, unknown>

Optionalmirostat

mirostat?: number

OptionalmirostatEta

mirostatEta?: number

OptionalmirostatTau

mirostatTau?: number

Optionalmodel

model?: string

The model to invoke. If the model does not exist, it will be pulled.

Default

"llama3"

OptionalnumBatch

numBatch?: number

OptionalnumCtx

numCtx?: number

OptionalnumGpu

numGpu?: number

OptionalnumKeep

numKeep?: number

OptionalnumPredict

numPredict?: number

OptionalnumThread

numThread?: number

Optionalnuma

numa?: boolean

OptionalonFailedAttempt

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.

OptionalpenalizeNewline

penalizeNewline?: boolean

OptionalpresencePenalty

presencePenalty?: number

OptionalrepeatLastN

repeatLastN?: number

OptionalrepeatPenalty

repeatPenalty?: number

Optionalseed

seed?: number

Optionalstop

stop?: string[]

Optionalstreaming

streaming?: boolean

Optionaltags

tags?: string[]

Optionaltemperature

temperature?: number

OptionaltfsZ

tfsZ?: number

Optionalthink

think?: boolean

OptionaltopK

topK?: number

OptionaltopP

topP?: number

OptionaltypicalP

typicalP?: number

OptionaluseMlock

useMlock?: boolean

OptionaluseMmap

useMmap?: boolean

Optionalverbose

verbose?: boolean

OptionalvocabOnly

vocabOnly?: boolean

Settings

Member Visibility

On This Page

Properties