Class: EmbeddingSimilarityClassifier<VALUE, CLUSTERS>
Classifies values based on their distance to the values from a set of clusters. When the distance is below a certain threshold, the value is classified as belonging to the cluster, and the cluster name is returned. Otherwise, the value is classified as null.
Type parameters
| Name | Type |
|---|---|
VALUE | VALUE |
CLUSTERS | extends ValueCluster<VALUE, string>[] |
Implements
Classifier<VALUE,ClusterNames<CLUSTERS> |null,EmbeddingSimilarityClassifierSettings<VALUE,CLUSTERS>>
Accessors
settingsForEvent
• get settingsForEvent(): Partial<EmbeddingSimilarityClassifierSettings<VALUE, CLUSTERS>>
Returns settings that should be recorded in observability events. Security-related settings (e.g. API keys) should not be included here.
Returns
Partial<EmbeddingSimilarityClassifierSettings<VALUE, CLUSTERS>>
Implementation of
Classifier.settingsForEvent
Defined in
packages/modelfusion/src/model-function/classify/EmbeddingSimilarityClassifier.ts:129
Constructors
constructor
• new EmbeddingSimilarityClassifier<VALUE, CLUSTERS>(settings): EmbeddingSimilarityClassifier<VALUE, CLUSTERS>
Type parameters
| Name | Type |
|---|---|
VALUE | VALUE |
CLUSTERS | extends ValueCluster<VALUE, string>[] |
Parameters
| Name | Type |
|---|---|
settings | EmbeddingSimilarityClassifierSettings<VALUE, CLUSTERS> |
Returns
EmbeddingSimilarityClassifier<VALUE, CLUSTERS>
Defined in
packages/modelfusion/src/model-function/classify/EmbeddingSimilarityClassifier.ts:52
Methods
doClassify
▸ doClassify(value, options): Promise<{ class: null | ClusterNames<CLUSTERS> ; rawResponse: undefined = undefined }>
Parameters
| Name | Type |
|---|---|
value | VALUE |
options | FunctionCallOptions |
Returns
Promise<{ class: null | ClusterNames<CLUSTERS> ; rawResponse: undefined = undefined }>
Implementation of
Defined in
packages/modelfusion/src/model-function/classify/EmbeddingSimilarityClassifier.ts:90
getEmbeddings
▸ getEmbeddings(options): Promise<{ clusterName: string ; clusterValue: VALUE ; embedding: Vector }[]>
Parameters
| Name | Type |
|---|---|
options | FunctionCallOptions |
Returns
Promise<{ clusterName: string ; clusterValue: VALUE ; embedding: Vector }[]>
Defined in
packages/modelfusion/src/model-function/classify/EmbeddingSimilarityClassifier.ts:58
withSettings
▸ withSettings(additionalSettings): EmbeddingSimilarityClassifier<VALUE, CLUSTERS>
The withSettings method creates a new model with the same configuration as the original model, but with the specified settings changed.
Parameters
| Name | Type |
|---|---|
additionalSettings | Partial<EmbeddingSimilarityClassifierSettings<VALUE, CLUSTERS>> |
Returns
EmbeddingSimilarityClassifier<VALUE, CLUSTERS>
Example
const model = new OpenAICompletionModel({
model: "gpt-3.5-turbo-instruct",
maxGenerationTokens: 500,
});
const modelWithMoreTokens = model.withSettings({
maxGenerationTokens: 1000,
});
Implementation of
Defined in
packages/modelfusion/src/model-function/classify/EmbeddingSimilarityClassifier.ts:148
Properties
modelInformation
• Readonly modelInformation: Object
Type declaration
| Name | Type |
|---|---|
modelName | string |
provider | string |
Implementation of
Defined in
packages/modelfusion/src/model-function/classify/EmbeddingSimilarityClassifier.ts:39
settings
• Readonly settings: EmbeddingSimilarityClassifierSettings<VALUE, CLUSTERS>
Implementation of
Defined in
packages/modelfusion/src/model-function/classify/EmbeddingSimilarityClassifier.ts:37